diff --git "a/open-llm-leaderboard.json" "b/open-llm-leaderboard.json" new file mode 100644--- /dev/null +++ "b/open-llm-leaderboard.json" @@ -0,0 +1,101462 @@ +[ + { + "T": "\ud83d\udd36", + "Model": "binbi\/Ein-72B-v0.1", + "Average \u2b06\ufe0f": 80.99, + "ARC": 76.45, + "HellaSwag": 89.43, + "MMLU": 77.14, + "TruthfulQA": 78.09, + "Winogrande": 84.77, + "GSM8K": 80.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "84ec4c0fcefc5af86f649a70c9d3ff493334e868", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SF-Foundation\/Ein-72B-v0.11", + "Average \u2b06\ufe0f": 80.81, + "ARC": 76.79, + "HellaSwag": 89.02, + "MMLU": 77.2, + "TruthfulQA": 79.02, + "Winogrande": 84.06, + "GSM8K": 78.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "40d451f32b1a6c9ad694b32ba8ed4822c27f3022", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SF-Foundation\/Ein-72B-v0.13", + "Average \u2b06\ufe0f": 80.79, + "ARC": 76.19, + "HellaSwag": 89.44, + "MMLU": 77.07, + "TruthfulQA": 77.82, + "Winogrande": 84.93, + "GSM8K": 79.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1f302e0e15f3d3711778cd61686eb9b28b0c72ae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "binbi\/Ein-72B-v0.1", + "Average \u2b06\ufe0f": 80.79, + "ARC": 76.54, + "HellaSwag": 89.2, + "MMLU": 77.11, + "TruthfulQA": 78.47, + "Winogrande": 84.06, + "GSM8K": 79.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "84ec4c0fcefc5af86f649a70c9d3ff493334e868", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SF-Foundation\/Ein-72B-v0.12", + "Average \u2b06\ufe0f": 80.72, + "ARC": 76.19, + "HellaSwag": 89.46, + "MMLU": 77.17, + "TruthfulQA": 77.78, + "Winogrande": 84.45, + "GSM8K": 79.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "84d38e29fec0dc9c274237968fdafe9396702f9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Smaug-72B-v0.1", + "Average \u2b06\ufe0f": 80.48, + "ARC": 76.02, + "HellaSwag": 89.27, + "MMLU": 77.15, + "TruthfulQA": 76.67, + "Winogrande": 85.08, + "GSM8K": 78.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 351.0, + "Available on the hub": true, + "Model sha": "54a8c35600ec5cb30ca2129247854ece23e57f57", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/alpaca-dragon-72b-v1", + "Average \u2b06\ufe0f": 79.3, + "ARC": 73.89, + "HellaSwag": 88.16, + "MMLU": 77.4, + "TruthfulQA": 72.69, + "Winogrande": 86.03, + "GSM8K": 77.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "4df251a558c53b6b6a4c459045b161951cfc3c4e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "moreh\/MoMo-72B-lora-1.8.7-DPO", + "Average \u2b06\ufe0f": 78.55, + "ARC": 70.82, + "HellaSwag": 85.96, + "MMLU": 77.13, + "TruthfulQA": 74.71, + "Winogrande": 84.06, + "GSM8K": 78.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 61.0, + "Available on the hub": true, + "Model sha": "c64edea08b27be1e7e2ae6a95bcdd74849cb887e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16", + "Average \u2b06\ufe0f": 77.91, + "ARC": 74.06, + "HellaSwag": 86.74, + "MMLU": 76.65, + "TruthfulQA": 72.24, + "Winogrande": 83.35, + "GSM8K": 74.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "cd29cfa124072c96ba8601230bead65d76e04dcb", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "HanNayeoniee\/LHK_DPO_v1", + "Average \u2b06\ufe0f": 77.62, + "ARC": 74.74, + "HellaSwag": 89.3, + "MMLU": 64.9, + "TruthfulQA": 79.89, + "Winogrande": 88.32, + "GSM8K": 68.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "4e2c0a8fb1a1654312a573e85fec79832bfa489c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/TomGrc_FusionNet_34Bx2_MoE_v0.1_full_linear_DPO", + "Average \u2b06\ufe0f": 77.52, + "ARC": 74.06, + "HellaSwag": 86.67, + "MMLU": 76.69, + "TruthfulQA": 71.32, + "Winogrande": 83.43, + "GSM8K": 72.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e8e558b5fd4ac9da839577b1295d10ca75fc2663", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "yunconglong\/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B", + "Average \u2b06\ufe0f": 77.44, + "ARC": 74.91, + "HellaSwag": 89.3, + "MMLU": 64.67, + "TruthfulQA": 78.02, + "Winogrande": 88.24, + "GSM8K": 69.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 38.0, + "Available on the hub": true, + "Model sha": "915651208ea9f40c65a60d1f971a09f9461ee691", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Asura_v1", + "Average \u2b06\ufe0f": 77.43, + "ARC": 73.89, + "HellaSwag": 89.07, + "MMLU": 75.44, + "TruthfulQA": 71.75, + "Winogrande": 86.35, + "GSM8K": 68.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7dd3ddea090bd63f3143e70d7d6237cc40c046e4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/UNA-SimpleSmaug-34b-v1beta", + "Average \u2b06\ufe0f": 77.41, + "ARC": 74.57, + "HellaSwag": 86.74, + "MMLU": 76.68, + "TruthfulQA": 70.17, + "Winogrande": 83.82, + "GSM8K": 72.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "e1cdc5b02c662c5f29a50d0b22c64a8902ca856b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FusionNet_34Bx2_MoE_v0.1", + "Average \u2b06\ufe0f": 77.38, + "ARC": 73.72, + "HellaSwag": 86.46, + "MMLU": 76.72, + "TruthfulQA": 71.01, + "Winogrande": 83.35, + "GSM8K": 73.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "6c7ec6d2ca1c0d126a26963fedc9bbdf5210b0d1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-72B-v1.5b", + "Average \u2b06\ufe0f": 77.3, + "ARC": 71.25, + "HellaSwag": 85.53, + "MMLU": 76.63, + "TruthfulQA": 71.99, + "Winogrande": 81.45, + "GSM8K": 76.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "dc092ecc5d5a424678eac445a9f4443069776691", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "moreh\/MoMo-70B-lora-1.8.6-DPO", + "Average \u2b06\ufe0f": 77.29, + "ARC": 70.14, + "HellaSwag": 86.03, + "MMLU": 77.4, + "TruthfulQA": 69.0, + "Winogrande": 84.37, + "GSM8K": 76.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "76389d5d825c3743cc70bc75b902bbfdad11beba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "moreh\/MoMo-72B-lora-1.8.6-DPO", + "Average \u2b06\ufe0f": 77.29, + "ARC": 70.14, + "HellaSwag": 86.03, + "MMLU": 77.4, + "TruthfulQA": 69.0, + "Winogrande": 84.37, + "GSM8K": 76.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "76389d5d825c3743cc70bc75b902bbfdad11beba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Smaugv0.1", + "Average \u2b06\ufe0f": 77.29, + "ARC": 74.23, + "HellaSwag": 86.76, + "MMLU": 76.66, + "TruthfulQA": 70.22, + "Winogrande": 83.66, + "GSM8K": 72.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "036927bc2b54d408bb9e9357c3df8353f5853ea8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Smaug-34B-v0.1", + "Average \u2b06\ufe0f": 77.29, + "ARC": 74.23, + "HellaSwag": 86.76, + "MMLU": 76.66, + "TruthfulQA": 70.22, + "Winogrande": 83.66, + "GSM8K": 72.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 37.0, + "Available on the hub": true, + "Model sha": "7b74a95019f01b59630cbd6469814c752d0e59e5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE", + "Average \u2b06\ufe0f": 77.28, + "ARC": 72.87, + "HellaSwag": 86.52, + "MMLU": 76.96, + "TruthfulQA": 73.28, + "Winogrande": 83.19, + "GSM8K": 70.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "097b951c2524e6113252fcd98ba5830c85dc450f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Luminex-32B-v0.2", + "Average \u2b06\ufe0f": 77.19, + "ARC": 74.49, + "HellaSwag": 86.76, + "MMLU": 76.55, + "TruthfulQA": 70.21, + "Winogrande": 83.27, + "GSM8K": 71.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "3880710724abcaffbdf8fa4031e1d02066fbfe9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "senseable\/Wilbur-30B", + "Average \u2b06\ufe0f": 77.18, + "ARC": 74.06, + "HellaSwag": 86.68, + "MMLU": 76.7, + "TruthfulQA": 69.96, + "Winogrande": 83.43, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "eab679f95e078efb71fbaa7b1aa0be05bb4e46ca", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "RubielLabarta\/LogoS-7Bx2-MoE-13B-v0.2", + "Average \u2b06\ufe0f": 77.15, + "ARC": 74.4, + "HellaSwag": 89.09, + "MMLU": 64.9, + "TruthfulQA": 74.53, + "Winogrande": 88.4, + "GSM8K": 71.57, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "354f0eb0a1299473c861c0505c2ede04ced90972", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "RubielLabarta\/LogoS-7Bx2-MoE-13B-v0.1", + "Average \u2b06\ufe0f": 77.14, + "ARC": 74.49, + "HellaSwag": 89.07, + "MMLU": 64.74, + "TruthfulQA": 74.57, + "Winogrande": 88.32, + "GSM8K": 71.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1e4670ddb878fa696f2e6293a4db9d8657993fd8", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "yunconglong\/DARE_TIES_13B", + "Average \u2b06\ufe0f": 77.1, + "ARC": 74.32, + "HellaSwag": 89.5, + "MMLU": 64.47, + "TruthfulQA": 78.66, + "Winogrande": 88.08, + "GSM8K": 67.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": [ + "other" + ], + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "74c6e4fbd272c9d897e8c93ee7de8a234f61900f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "yunconglong\/13B_MATH_DPO", + "Average \u2b06\ufe0f": 77.08, + "ARC": 74.66, + "HellaSwag": 89.51, + "MMLU": 64.53, + "TruthfulQA": 78.63, + "Winogrande": 88.08, + "GSM8K": 67.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "96c62ad90f2b82016a1cdbfe96cfa5c4bb278e21", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FusionNet_34Bx2_MoE", + "Average \u2b06\ufe0f": 77.07, + "ARC": 72.95, + "HellaSwag": 86.22, + "MMLU": 77.05, + "TruthfulQA": 71.31, + "Winogrande": 83.98, + "GSM8K": 70.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "c5575550053c84a401baf56174cb2e5d5bd9e79a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Luminex-34B-v0.1", + "Average \u2b06\ufe0f": 77.06, + "ARC": 73.63, + "HellaSwag": 86.59, + "MMLU": 76.55, + "TruthfulQA": 69.68, + "Winogrande": 83.43, + "GSM8K": 72.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "d3efc551679d7ec00da14722d44151c948a48d25", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yunconglong\/MoE_13B_DPO", + "Average \u2b06\ufe0f": 77.05, + "ARC": 74.32, + "HellaSwag": 89.39, + "MMLU": 64.48, + "TruthfulQA": 78.47, + "Winogrande": 88.0, + "GSM8K": 67.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d8d6a47f877fee3e638a158c2bd637c0013ed4e4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Asura_v3.0", + "Average \u2b06\ufe0f": 77.03, + "ARC": 72.95, + "HellaSwag": 88.86, + "MMLU": 75.41, + "TruthfulQA": 69.1, + "Winogrande": 85.08, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06fd0e293aeb3b2722e3910daefcd185fad4558c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO", + "Average \u2b06\ufe0f": 76.95, + "ARC": 73.21, + "HellaSwag": 86.11, + "MMLU": 75.44, + "TruthfulQA": 72.78, + "Winogrande": 82.95, + "GSM8K": 71.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "other", + "#Params (B)": 31.8, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "331bb6bdba4140bbf0031bd37076f2c8a76d7dbb", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "alchemonaut\/QuartetAnemoi-70B-t0.0001", + "Average \u2b06\ufe0f": 76.86, + "ARC": 73.38, + "HellaSwag": 88.9, + "MMLU": 75.42, + "TruthfulQA": 69.53, + "Winogrande": 85.32, + "GSM8K": 68.61, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "392d963e63267650f2aea7dc26c60ee6fd2b26d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Asura_v1.1.0", + "Average \u2b06\ufe0f": 76.75, + "ARC": 73.21, + "HellaSwag": 88.55, + "MMLU": 75.43, + "TruthfulQA": 69.55, + "Winogrande": 85.32, + "GSM8K": 68.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "baf3e2cc3a8d18098199b3cee4bdf79f00935be1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "cloudyu\/Yi-34Bx2-MoE-60B", + "Average \u2b06\ufe0f": 76.72, + "ARC": 71.08, + "HellaSwag": 85.23, + "MMLU": 77.47, + "TruthfulQA": 66.19, + "Winogrande": 84.85, + "GSM8K": 75.51, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 52.0, + "Available on the hub": true, + "Model sha": "483359d70b3fef480cdaeb6d722a18626d34f0ce", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "cloudyu\/Mixtral_34Bx2_MoE_60B", + "Average \u2b06\ufe0f": 76.66, + "ARC": 71.33, + "HellaSwag": 85.25, + "MMLU": 77.34, + "TruthfulQA": 66.59, + "Winogrande": 84.85, + "GSM8K": 74.6, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 102.0, + "Available on the hub": true, + "Model sha": "f49d7cf0a7b99b15bc98b0ef4a681e7f0f4aa92c", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Eurdem\/megatron_2.1_MoE_2x7B", + "Average \u2b06\ufe0f": 76.64, + "ARC": 72.95, + "HellaSwag": 88.94, + "MMLU": 64.56, + "TruthfulQA": 78.2, + "Winogrande": 84.53, + "GSM8K": 70.66, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3104c1f36336085fdf0ad44e62695b0215c5e5b9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "cloudyu\/Mixtral_34Bx2_MoE_60B", + "Average \u2b06\ufe0f": 76.63, + "ARC": 71.25, + "HellaSwag": 85.36, + "MMLU": 77.28, + "TruthfulQA": 66.61, + "Winogrande": 84.69, + "GSM8K": 74.6, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 102.0, + "Available on the hub": true, + "Model sha": "f49d7cf0a7b99b15bc98b0ef4a681e7f0f4aa92c", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "Undi95\/Miqu-70B-Alpaca-DPO", + "Average \u2b06\ufe0f": 76.6, + "ARC": 73.21, + "HellaSwag": 88.6, + "MMLU": 75.41, + "TruthfulQA": 69.44, + "Winogrande": 85.4, + "GSM8K": 67.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": false, + "Model sha": "f7ee9b9099cd518060e9e61ff7ae11a39428bd93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "152334H\/miqu-1-70b-sf", + "Average \u2b06\ufe0f": 76.59, + "ARC": 73.04, + "HellaSwag": 88.61, + "MMLU": 75.49, + "TruthfulQA": 69.38, + "Winogrande": 85.32, + "GSM8K": 67.7, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 187.0, + "Available on the hub": false, + "Model sha": "97c24b15a7e26985fb18540800516aa2ac03ad03", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "zhengr\/MixTAO-7Bx2-MoE-Instruct-v7.0", + "Average \u2b06\ufe0f": 76.55, + "ARC": 74.23, + "HellaSwag": 89.37, + "MMLU": 64.54, + "TruthfulQA": 74.26, + "Winogrande": 87.77, + "GSM8K": 69.14, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "69b9280ee4d2a20ef5645798621e62dd9777c139", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "alchemonaut\/BoreanGale-70B", + "Average \u2b06\ufe0f": 76.48, + "ARC": 73.89, + "HellaSwag": 89.37, + "MMLU": 75.19, + "TruthfulQA": 68.6, + "Winogrande": 84.53, + "GSM8K": 67.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "f7768207c1f37d3f4374dccc182d7a86c6539ead", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B", + "Average \u2b06\ufe0f": 76.48, + "ARC": 71.25, + "HellaSwag": 85.24, + "MMLU": 77.28, + "TruthfulQA": 66.74, + "Winogrande": 84.29, + "GSM8K": 74.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6ba7b5acb65dd62c28585cba298e0d3671c14f3a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Yi-34Bx2-MoE-60B-DPO", + "Average \u2b06\ufe0f": 76.44, + "ARC": 71.25, + "HellaSwag": 85.1, + "MMLU": 77.36, + "TruthfulQA": 66.24, + "Winogrande": 84.77, + "GSM8K": 73.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "3d0181b920304bca0bdfd41aff55188a574c85e3", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "macadeliccc\/SmaugDolphin-60B", + "Average \u2b06\ufe0f": 76.44, + "ARC": 73.38, + "HellaSwag": 86.55, + "MMLU": 76.78, + "TruthfulQA": 67.44, + "Winogrande": 83.5, + "GSM8K": 70.96, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cf8bc1d4103c4fde2a3da0cf86bdfcec95f5fe35", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/ogno-monarch-jaskier-merge-7b", + "Average \u2b06\ufe0f": 76.43, + "ARC": 73.04, + "HellaSwag": 89.09, + "MMLU": 64.78, + "TruthfulQA": 77.44, + "Winogrande": 84.77, + "GSM8K": 69.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a1179e6c346ba93db60c45d6d219ca86f2260102", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bardsai\/jaskier-7b-dpo-v5.6", + "Average \u2b06\ufe0f": 76.41, + "ARC": 73.04, + "HellaSwag": 89.0, + "MMLU": 64.38, + "TruthfulQA": 77.81, + "Winogrande": 84.53, + "GSM8K": 69.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "25c0f5c1edad0ed1ab02347adf02fe03e0a3b62a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Asura_v2.1", + "Average \u2b06\ufe0f": 76.41, + "ARC": 72.53, + "HellaSwag": 88.75, + "MMLU": 74.96, + "TruthfulQA": 67.33, + "Winogrande": 85.87, + "GSM8K": 68.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "546cdd443abc56b48aaadb4ebb5fb9249015f0bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/MonaTrix-v4", + "Average \u2b06\ufe0f": 76.38, + "ARC": 73.38, + "HellaSwag": 89.11, + "MMLU": 64.08, + "TruthfulQA": 78.02, + "Winogrande": 84.85, + "GSM8K": 68.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "323db6a9bd5ce5e56e663a954838f446b3aeb385", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/neurotic-crown-clown-7b-ties", + "Average \u2b06\ufe0f": 76.38, + "ARC": 72.35, + "HellaSwag": 88.61, + "MMLU": 64.77, + "TruthfulQA": 76.5, + "Winogrande": 84.69, + "GSM8K": 71.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c990d5a67bb589e73c355a81e99940c8d7155c34", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bardsai\/jaskier-7b-dpo-v6.1", + "Average \u2b06\ufe0f": 76.36, + "ARC": 73.29, + "HellaSwag": 88.89, + "MMLU": 64.39, + "TruthfulQA": 77.47, + "Winogrande": 84.69, + "GSM8K": 69.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "aa3528c04c38fa49b5b65e1d064c46db3e9774f1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/ogno-monarch-jaskier-merge-7b-v2", + "Average \u2b06\ufe0f": 76.35, + "ARC": 72.87, + "HellaSwag": 89.15, + "MMLU": 64.77, + "TruthfulQA": 77.76, + "Winogrande": 84.29, + "GSM8K": 69.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0468ff62a3f4b152a80c9acf34a8419b01bb9569", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bardsai\/jaskier-7b-dpo-v4.3", + "Average \u2b06\ufe0f": 76.35, + "ARC": 72.61, + "HellaSwag": 89.09, + "MMLU": 64.29, + "TruthfulQA": 78.27, + "Winogrande": 84.77, + "GSM8K": 69.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dc22b7692b8d54575545f1614029ebc898c9a6e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "paulml\/OGNO-7B", + "Average \u2b06\ufe0f": 76.34, + "ARC": 73.12, + "HellaSwag": 89.0, + "MMLU": 64.59, + "TruthfulQA": 76.52, + "Winogrande": 84.69, + "GSM8K": 70.13, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a5d97f2e6962dc2c539a5bbca6a1160f87ccce84", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_25-7B-dare_ties", + "Average \u2b06\ufe0f": 76.33, + "ARC": 73.46, + "HellaSwag": 88.89, + "MMLU": 64.37, + "TruthfulQA": 76.54, + "Winogrande": 84.29, + "GSM8K": 70.43, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6918e7ea07572b932ba43e7e339cc79406b75e30", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "liminerity\/Omningotex-7b-slerp", + "Average \u2b06\ufe0f": 76.33, + "ARC": 73.29, + "HellaSwag": 88.96, + "MMLU": 64.69, + "TruthfulQA": 76.32, + "Winogrande": 84.21, + "GSM8K": 70.51, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "8d31526e43bbc2aa7324a4e5182d25aedcd24f1e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "eren23\/dpo-binarized-NeutrixOmnibe-7B", + "Average \u2b06\ufe0f": 76.31, + "ARC": 72.78, + "HellaSwag": 89.05, + "MMLU": 64.6, + "TruthfulQA": 76.9, + "Winogrande": 85.08, + "GSM8K": 69.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5c485c124bf1af920ebfba6c0de615db5dcb5ae4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kukedlc\/NeuTrixOmniBe-7B-model-remix", + "Average \u2b06\ufe0f": 76.3, + "ARC": 72.7, + "HellaSwag": 89.03, + "MMLU": 64.57, + "TruthfulQA": 76.9, + "Winogrande": 85.08, + "GSM8K": 69.52, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a9516ed719359e08e5b716bcf9d80d91f81fa471", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "yleo\/OgnoMonarch-7B", + "Average \u2b06\ufe0f": 76.3, + "ARC": 72.61, + "HellaSwag": 88.92, + "MMLU": 64.94, + "TruthfulQA": 77.06, + "Winogrande": 84.21, + "GSM8K": 70.05, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1aaa8b8fd3f7a455be518c4d70b4a434b9977c87", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_21-7B-slerp", + "Average \u2b06\ufe0f": 76.29, + "ARC": 74.23, + "HellaSwag": 88.95, + "MMLU": 65.05, + "TruthfulQA": 73.81, + "Winogrande": 84.61, + "GSM8K": 71.11, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "92cd3ea976fe78cfdbf3f45a9d81ca30dc5fdc38", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "mlabonne\/Monarch-7B", + "Average \u2b06\ufe0f": 76.25, + "ARC": 73.04, + "HellaSwag": 89.03, + "MMLU": 64.41, + "TruthfulQA": 77.35, + "Winogrande": 84.61, + "GSM8K": 69.07, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "1ccf1b7b37818c3b11d14dc0ef6fe4344a3cb4d5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kukedlc\/NeuTrixOmniBe-7B-model-remix", + "Average \u2b06\ufe0f": 76.24, + "ARC": 72.61, + "HellaSwag": 89.07, + "MMLU": 64.63, + "TruthfulQA": 76.91, + "Winogrande": 85.08, + "GSM8K": 69.14, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a9516ed719359e08e5b716bcf9d80d91f81fa471", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "jsfs11\/MixtureofMerges-MoE-4x7b-v4", + "Average \u2b06\ufe0f": 76.23, + "ARC": 72.53, + "HellaSwag": 88.85, + "MMLU": 64.53, + "TruthfulQA": 75.3, + "Winogrande": 84.85, + "GSM8K": 71.34, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4d233a36010353fde821dc65434194a797e4f7bd", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "moreh\/MoMo-70B-lora-1.8.4-DPO", + "Average \u2b06\ufe0f": 76.23, + "ARC": 69.62, + "HellaSwag": 85.35, + "MMLU": 77.33, + "TruthfulQA": 64.64, + "Winogrande": 84.14, + "GSM8K": 76.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a2c3a87dd53a87dc9fc622ce4ddbb05d3e9cf6a9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "moreh\/MoMo-72B-lora-1.8.4-DPO", + "Average \u2b06\ufe0f": 76.23, + "ARC": 69.62, + "HellaSwag": 85.35, + "MMLU": 77.33, + "TruthfulQA": 64.64, + "Winogrande": 84.14, + "GSM8K": 76.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a2c3a87dd53a87dc9fc622ce4ddbb05d3e9cf6a9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yleo\/ParrotOgno-7B", + "Average \u2b06\ufe0f": 76.22, + "ARC": 73.04, + "HellaSwag": 89.03, + "MMLU": 64.51, + "TruthfulQA": 76.53, + "Winogrande": 84.61, + "GSM8K": 69.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "95d7acea20309a1eeb0be3c4db77ecba5fdf6df9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nlpguy\/AlloyIngotNeoX", + "Average \u2b06\ufe0f": 76.21, + "ARC": 74.32, + "HellaSwag": 89.07, + "MMLU": 64.97, + "TruthfulQA": 74.57, + "Winogrande": 84.53, + "GSM8K": 69.83, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0d4277f842643d3c23fad0c86cfb1edd658adab7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Grafted-Wind-Elementals-2x70B", + "Average \u2b06\ufe0f": 76.21, + "ARC": 73.38, + "HellaSwag": 89.08, + "MMLU": 75.79, + "TruthfulQA": 65.57, + "Winogrande": 84.85, + "GSM8K": 68.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 125.35, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "46f056338f51bcc7c80745b95e9198aec4c198d4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "paulml\/DPOB-INMTOB-7B", + "Average \u2b06\ufe0f": 76.21, + "ARC": 73.21, + "HellaSwag": 89.0, + "MMLU": 64.54, + "TruthfulQA": 76.6, + "Winogrande": 84.69, + "GSM8K": 69.22, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a8871af9db183f2e7fe7c30bb2242b3b7827e53f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_24-7B-slerp", + "Average \u2b06\ufe0f": 76.21, + "ARC": 73.98, + "HellaSwag": 89.09, + "MMLU": 64.99, + "TruthfulQA": 75.52, + "Winogrande": 84.69, + "GSM8K": 68.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c0b444df4fbeb1106fc6e2a3ceb9ff0521de32bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/merged-dpo-binarized-NeutrixOmnibe-7B", + "Average \u2b06\ufe0f": 76.2, + "ARC": 72.7, + "HellaSwag": 89.03, + "MMLU": 64.59, + "TruthfulQA": 76.9, + "Winogrande": 85.08, + "GSM8K": 68.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "616d72f1c130f9ea0118c45d5a6f12f3848a97db", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/AlloyIngot", + "Average \u2b06\ufe0f": 76.2, + "ARC": 73.98, + "HellaSwag": 89.05, + "MMLU": 64.83, + "TruthfulQA": 75.12, + "Winogrande": 85.08, + "GSM8K": 69.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e9bda1899505cae6cbdde05dc763c2fad5e2183e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mayacinka\/Buttercup-7b-dpo-slerp", + "Average \u2b06\ufe0f": 76.19, + "ARC": 72.7, + "HellaSwag": 89.09, + "MMLU": 64.5, + "TruthfulQA": 77.17, + "Winogrande": 84.77, + "GSM8K": 68.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a9f4d04b59d764a45fabac9dd3d7f72b795967f0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mayacinka\/Buttercup-7b-dpo-ties", + "Average \u2b06\ufe0f": 76.19, + "ARC": 72.7, + "HellaSwag": 89.09, + "MMLU": 64.5, + "TruthfulQA": 77.17, + "Winogrande": 84.77, + "GSM8K": 68.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "608d7998c1b8f4707e065642a7cfa3d0ddb80100", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_26-7B-dare_ties", + "Average \u2b06\ufe0f": 76.19, + "ARC": 72.95, + "HellaSwag": 89.0, + "MMLU": 64.35, + "TruthfulQA": 76.39, + "Winogrande": 84.45, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "38dc5cdc607d7171ef9a21a820d4fc58d6b9811b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Yi-34Bx3-MoE-90B", + "Average \u2b06\ufe0f": 76.18, + "ARC": 70.9, + "HellaSwag": 85.33, + "MMLU": 77.41, + "TruthfulQA": 66.31, + "Winogrande": 84.29, + "GSM8K": 72.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 87.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b4b717be590394a4e70853cb444bd0964526c500", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_27-7B-dare_ties", + "Average \u2b06\ufe0f": 76.17, + "ARC": 73.72, + "HellaSwag": 89.0, + "MMLU": 64.5, + "TruthfulQA": 76.36, + "Winogrande": 84.61, + "GSM8K": 68.84, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "828713b163db29b7836c20ce72c50f269c3086f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_23-7B-slerp", + "Average \u2b06\ufe0f": 76.17, + "ARC": 73.55, + "HellaSwag": 88.9, + "MMLU": 64.87, + "TruthfulQA": 75.13, + "Winogrande": 84.29, + "GSM8K": 70.28, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b6369c9e0b592d8be55d5f00076159c7d3fa9f64", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralMaxime-7B-slerp", + "Average \u2b06\ufe0f": 76.17, + "ARC": 73.38, + "HellaSwag": 89.18, + "MMLU": 64.44, + "TruthfulQA": 77.79, + "Winogrande": 84.45, + "GSM8K": 67.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "055dc83f36a3a6c6d477dba1547f60a9592b3978", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "eren23\/dpo-binarized-NeuralTrix-7B", + "Average \u2b06\ufe0f": 76.17, + "ARC": 72.35, + "HellaSwag": 88.89, + "MMLU": 64.09, + "TruthfulQA": 79.07, + "Winogrande": 84.61, + "GSM8K": 68.01, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "853370b5907d272f93870b47e67a5622da643801", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "sumo43\/Yi-32b-x2-v2.0", + "Average \u2b06\ufe0f": 76.17, + "ARC": 73.04, + "HellaSwag": 85.95, + "MMLU": 76.79, + "TruthfulQA": 73.22, + "Winogrande": 82.79, + "GSM8K": 65.2, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1e61f28b326fe0080ad476ce2b1dd041ec9f147f", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuTrixOmniBe-DPO", + "Average \u2b06\ufe0f": 76.17, + "ARC": 72.78, + "HellaSwag": 89.03, + "MMLU": 64.28, + "TruthfulQA": 77.21, + "Winogrande": 85.16, + "GSM8K": 68.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "1b1cf19bc1d574906c7d100a8dbb85ec4cad5bb5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_22-7B-slerp", + "Average \u2b06\ufe0f": 76.16, + "ARC": 73.72, + "HellaSwag": 89.03, + "MMLU": 64.8, + "TruthfulQA": 74.9, + "Winogrande": 84.77, + "GSM8K": 69.75, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7fad5c740489e631fd94d4e1b54fb959ec953c2e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FusionNet_7Bx2_MoE_v0.1", + "Average \u2b06\ufe0f": 76.16, + "ARC": 74.06, + "HellaSwag": 88.9, + "MMLU": 65.0, + "TruthfulQA": 71.2, + "Winogrande": 87.53, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "a0d648c1bcc3f1615bb2f0a94c6d32e7abde355d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/NeuralTrix-7B-dpo", + "Average \u2b06\ufe0f": 76.15, + "ARC": 72.27, + "HellaSwag": 88.91, + "MMLU": 64.06, + "TruthfulQA": 79.06, + "Winogrande": 84.61, + "GSM8K": 68.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f820ce616f062fa76c13845fb198490418676223", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mlabonne\/NeuralMonarch-7B", + "Average \u2b06\ufe0f": 76.15, + "ARC": 73.21, + "HellaSwag": 89.09, + "MMLU": 64.41, + "TruthfulQA": 77.79, + "Winogrande": 84.61, + "GSM8K": 67.78, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "d98f13e5e25a34bfa67d310e5922c5a2ffb6c4eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "eren23\/OGNO-7b-dpo-truthful", + "Average \u2b06\ufe0f": 76.14, + "ARC": 72.95, + "HellaSwag": 89.02, + "MMLU": 64.61, + "TruthfulQA": 76.61, + "Winogrande": 84.69, + "GSM8K": 68.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b30fc2edf47ab3d2c472d91611f7f3bae99174bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "moreh\/MoMo-70B-lora-1.8.5-DPO", + "Average \u2b06\ufe0f": 76.14, + "ARC": 69.54, + "HellaSwag": 85.6, + "MMLU": 77.49, + "TruthfulQA": 65.79, + "Winogrande": 84.14, + "GSM8K": 74.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7a0aadea285a82d50c96b0988b12cc3c6267249a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/MBX-7B-v3-DPO", + "Average \u2b06\ufe0f": 76.13, + "ARC": 73.55, + "HellaSwag": 89.11, + "MMLU": 64.91, + "TruthfulQA": 74.0, + "Winogrande": 85.56, + "GSM8K": 69.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "099b9c3e105fbb579d561fe93174ae3bd75dac8d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuTrixOmniBe-DPO", + "Average \u2b06\ufe0f": 76.13, + "ARC": 72.95, + "HellaSwag": 89.04, + "MMLU": 64.34, + "TruthfulQA": 77.22, + "Winogrande": 84.93, + "GSM8K": 68.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "40d3c8030b014b0c6fc7de07a4ee300e850a4566", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bardsai\/jaskier-7b-dpo-v3.3", + "Average \u2b06\ufe0f": 76.12, + "ARC": 72.27, + "HellaSwag": 88.89, + "MMLU": 64.34, + "TruthfulQA": 79.0, + "Winogrande": 84.37, + "GSM8K": 67.85, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e1460ba3fe5adcad670796528d9a163e13099c6d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/MonarchLake-7B", + "Average \u2b06\ufe0f": 76.1, + "ARC": 74.15, + "HellaSwag": 89.29, + "MMLU": 64.44, + "TruthfulQA": 74.97, + "Winogrande": 85.48, + "GSM8K": 68.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f1dc346e4c117d73dd706971a50d6b393390984b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/CarbonBeagle-11B-truthy", + "Average \u2b06\ufe0f": 76.1, + "ARC": 72.27, + "HellaSwag": 89.31, + "MMLU": 66.55, + "TruthfulQA": 78.55, + "Winogrande": 83.82, + "GSM8K": 66.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "5c649b6bbb8aa16d52dda26c5ce8574d1c7a3274", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_29-7B-dare_ties", + "Average \u2b06\ufe0f": 76.09, + "ARC": 73.04, + "HellaSwag": 89.04, + "MMLU": 64.29, + "TruthfulQA": 76.98, + "Winogrande": 84.53, + "GSM8K": 68.69, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9a628dcfb95cd17d0343467c29bc11053ad6851a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dddsaty\/FusionNet_7Bx2_MoE_Ko_DPO_Adapter_Attach", + "Average \u2b06\ufe0f": 76.09, + "ARC": 73.89, + "HellaSwag": 88.94, + "MMLU": 65.03, + "TruthfulQA": 71.24, + "Winogrande": 87.61, + "GSM8K": 69.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0c9f2823a900408cf3c70c532288f89e452067f7", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Capricorn-7B-DPO", + "Average \u2b06\ufe0f": 76.04, + "ARC": 72.87, + "HellaSwag": 88.47, + "MMLU": 64.29, + "TruthfulQA": 77.23, + "Winogrande": 83.11, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bfba5a5114005c849a49662b4c7e53debac98105", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "liminerity\/binarized-ingotrix-slerp-7b", + "Average \u2b06\ufe0f": 76.04, + "ARC": 73.21, + "HellaSwag": 88.64, + "MMLU": 64.85, + "TruthfulQA": 75.57, + "Winogrande": 82.87, + "GSM8K": 71.11, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a8b29283e9a14ebbe162639339fa7f6cb37a3388", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/AlloyIngotNeo", + "Average \u2b06\ufe0f": 76.02, + "ARC": 72.87, + "HellaSwag": 88.99, + "MMLU": 64.61, + "TruthfulQA": 75.95, + "Winogrande": 84.29, + "GSM8K": 69.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a05c142502808099af9d1daec3002a3ccaad5b31", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/MonaTrix-v6", + "Average \u2b06\ufe0f": 76.01, + "ARC": 72.78, + "HellaSwag": 88.9, + "MMLU": 64.45, + "TruthfulQA": 77.45, + "Winogrande": 84.61, + "GSM8K": 67.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c1f07a85b276483239956c4aa7d8e062c7ce8da1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "paulml\/DPOB-NMTOB-7B", + "Average \u2b06\ufe0f": 76.0, + "ARC": 73.12, + "HellaSwag": 88.95, + "MMLU": 64.7, + "TruthfulQA": 75.08, + "Winogrande": 85.16, + "GSM8K": 68.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "547fe9adccf3ab12b91bb77f6ee5daa033757a15", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abideen\/AlphaMonarch-laser", + "Average \u2b06\ufe0f": 76.0, + "ARC": 73.12, + "HellaSwag": 89.21, + "MMLU": 64.43, + "TruthfulQA": 77.9, + "Winogrande": 84.61, + "GSM8K": 66.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "bff2cd7ba1f8a742cd22cd9df22485636c3b6410", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mlabonne\/AlphaMonarch-7B", + "Average \u2b06\ufe0f": 75.99, + "ARC": 73.04, + "HellaSwag": 89.18, + "MMLU": 64.4, + "TruthfulQA": 77.91, + "Winogrande": 84.69, + "GSM8K": 66.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 78.0, + "Available on the hub": true, + "Model sha": "9a1c8000e25d27264c66c58603590f0acb8ef168", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "paulml\/OmniBeagleSquaredMBX-v3-7B-v2", + "Average \u2b06\ufe0f": 75.98, + "ARC": 74.06, + "HellaSwag": 88.93, + "MMLU": 64.53, + "TruthfulQA": 72.93, + "Winogrande": 85.56, + "GSM8K": 69.9, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7eb4f63abc5c6891503008eb613287eff8c15e30", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "touqir\/Cyrax-7B", + "Average \u2b06\ufe0f": 75.98, + "ARC": 72.95, + "HellaSwag": 88.19, + "MMLU": 64.6, + "TruthfulQA": 77.01, + "Winogrande": 83.9, + "GSM8K": 69.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "783a2f1231542b9fe8bc728dc676745c62f35b9f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "paulml\/NMTOB-7B", + "Average \u2b06\ufe0f": 75.97, + "ARC": 73.04, + "HellaSwag": 88.94, + "MMLU": 64.63, + "TruthfulQA": 75.06, + "Winogrande": 85.16, + "GSM8K": 68.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "27380e38769851edfc8d720ec88a066b40d8a85e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "flemmingmiguel\/MBX-7B-v3", + "Average \u2b06\ufe0f": 75.97, + "ARC": 74.15, + "HellaSwag": 88.91, + "MMLU": 65.06, + "TruthfulQA": 71.87, + "Winogrande": 85.56, + "GSM8K": 70.28, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "ca8c55fbbb2a0f7dd0de41579d98bbf24946b712", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "paulml\/OmniBeagleMBX-v3-7B", + "Average \u2b06\ufe0f": 75.96, + "ARC": 73.81, + "HellaSwag": 89.07, + "MMLU": 64.66, + "TruthfulQA": 73.52, + "Winogrande": 85.4, + "GSM8K": 69.29, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "01bc122ec9d4a523fc012e792e2ba23f0f9bea68", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bardsai\/jaskier-7b-dpo-v4.1", + "Average \u2b06\ufe0f": 75.95, + "ARC": 72.95, + "HellaSwag": 89.07, + "MMLU": 64.75, + "TruthfulQA": 75.92, + "Winogrande": 84.69, + "GSM8K": 68.31, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ee2a4761bb0030ef340120b30f6f52ae78f74e71", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "zhengr\/MixTAO-7Bx2-MoE-Instruct-v6.0", + "Average \u2b06\ufe0f": 75.94, + "ARC": 73.38, + "HellaSwag": 89.02, + "MMLU": 64.61, + "TruthfulQA": 70.45, + "Winogrande": 89.27, + "GSM8K": 68.92, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "29ceaff6300241003171ae2219ae1bfa77128b54", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment21-7B", + "Average \u2b06\ufe0f": 75.93, + "ARC": 71.42, + "HellaSwag": 89.03, + "MMLU": 63.92, + "TruthfulQA": 79.79, + "Winogrande": 85.48, + "GSM8K": 65.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "36a9851b8c9213c4e1bcfd2c46b3f799c36caa69", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "paulml\/NeuralOmniBeagleMBX-v3-7B", + "Average \u2b06\ufe0f": 75.93, + "ARC": 73.38, + "HellaSwag": 88.91, + "MMLU": 64.99, + "TruthfulQA": 73.1, + "Winogrande": 84.21, + "GSM8K": 70.96, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "37084955ee092548abfe356be4e6cfc46daa9cb4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/NeuralTrix-7B-dpo-laser", + "Average \u2b06\ufe0f": 75.92, + "ARC": 71.33, + "HellaSwag": 88.51, + "MMLU": 63.99, + "TruthfulQA": 78.15, + "Winogrande": 84.45, + "GSM8K": 69.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ac42a1ab3cb135dd8ff9ab600d5562251e8c6986", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FusionNet_7Bx2_MoE_14B", + "Average \u2b06\ufe0f": 75.91, + "ARC": 73.55, + "HellaSwag": 88.84, + "MMLU": 64.68, + "TruthfulQA": 69.6, + "Winogrande": 88.16, + "GSM8K": 70.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 33.0, + "Available on the hub": true, + "Model sha": "a619fd0fcbdfcc897054491c2f285677bee38a11", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "paulml\/OmniBeagleSquaredMBX-v3-7B", + "Average \u2b06\ufe0f": 75.91, + "ARC": 74.4, + "HellaSwag": 88.82, + "MMLU": 65.09, + "TruthfulQA": 72.7, + "Winogrande": 85.24, + "GSM8K": 69.22, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "88928f55d51c0819de3b64e6c37689b87a89aac4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment22-7B", + "Average \u2b06\ufe0f": 75.9, + "ARC": 71.5, + "HellaSwag": 88.89, + "MMLU": 64.13, + "TruthfulQA": 79.47, + "Winogrande": 84.77, + "GSM8K": 66.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "46afad714b0528863bcf67b2bf5fcd4318235ccf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YKM12\/Mistral-7B-summ-privatev1", + "Average \u2b06\ufe0f": 75.9, + "ARC": 74.15, + "HellaSwag": 88.85, + "MMLU": 64.99, + "TruthfulQA": 71.89, + "Winogrande": 85.32, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7ba08a489f9dff577b853077466aae751615fdf0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/MiquMaid-v2-2x70B-DPO", + "Average \u2b06\ufe0f": 75.89, + "ARC": 72.53, + "HellaSwag": 88.36, + "MMLU": 75.31, + "TruthfulQA": 66.5, + "Winogrande": 85.32, + "GSM8K": 67.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 125.35, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "30e44c452e38ff3d879d7ba92a130fa2cc072754", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Mixtral_7Bx2_MoE_DPO", + "Average \u2b06\ufe0f": 75.88, + "ARC": 73.04, + "HellaSwag": 88.76, + "MMLU": 64.94, + "TruthfulQA": 81.5, + "Winogrande": 82.16, + "GSM8K": 64.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bf4cb27f17bfc58aaf6011a8ba8393a1177ebbe7", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "alnrg2arg\/blockchainlabs_joe_bez_seminar", + "Average \u2b06\ufe0f": 75.85, + "ARC": 73.81, + "HellaSwag": 88.72, + "MMLU": 65.12, + "TruthfulQA": 71.86, + "Winogrande": 85.16, + "GSM8K": 70.43, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "17ead25f366603e2c21d08485e01fefdb7f5f740", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "vanillaOVO\/supermario_v4", + "Average \u2b06\ufe0f": 75.85, + "ARC": 73.46, + "HellaSwag": 88.77, + "MMLU": 65.41, + "TruthfulQA": 72.07, + "Winogrande": 85.24, + "GSM8K": 70.13, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7a5f87e239e9d24a4455bb81717d6ae0f3c2e7a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/NeuralTrix-7B-v1", + "Average \u2b06\ufe0f": 75.81, + "ARC": 74.15, + "HellaSwag": 89.27, + "MMLU": 64.55, + "TruthfulQA": 74.87, + "Winogrande": 84.93, + "GSM8K": 67.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c39ed28b498cdd86294ed3102cb7bdd5de5ec4fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kquant03\/Samlagast-7B-bf16", + "Average \u2b06\ufe0f": 75.81, + "ARC": 73.98, + "HellaSwag": 89.34, + "MMLU": 64.58, + "TruthfulQA": 73.9, + "Winogrande": 85.48, + "GSM8K": 67.55, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0b134ed1f5abb3a0f10fb64166f1b6b33eb99a68", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/NeuralKrishna-7B-slerp", + "Average \u2b06\ufe0f": 75.79, + "ARC": 73.46, + "HellaSwag": 88.96, + "MMLU": 64.62, + "TruthfulQA": 74.29, + "Winogrande": 83.27, + "GSM8K": 70.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5d25e45fbb1eb8301eee7e16884689e37cf02792", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "alnrg2arg\/blockchainlabs_joe_bez_seminar", + "Average \u2b06\ufe0f": 75.77, + "ARC": 73.98, + "HellaSwag": 88.75, + "MMLU": 65.17, + "TruthfulQA": 71.9, + "Winogrande": 85.24, + "GSM8K": 69.6, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "17ead25f366603e2c21d08485e01fefdb7f5f740", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "yleo\/EmertonMonarch-7B-slerp", + "Average \u2b06\ufe0f": 75.77, + "ARC": 73.04, + "HellaSwag": 88.94, + "MMLU": 64.44, + "TruthfulQA": 76.55, + "Winogrande": 83.58, + "GSM8K": 68.08, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b146ef2ff4b397d626a5945bf2caa4c2832bf9c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Capricorn-7B", + "Average \u2b06\ufe0f": 75.76, + "ARC": 72.44, + "HellaSwag": 88.41, + "MMLU": 64.9, + "TruthfulQA": 73.76, + "Winogrande": 83.27, + "GSM8K": 71.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ff7d668721b961a73a95098cf7436db0170b1db6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zhengr\/MixTAO-7Bx2-MoE-Instruct-v4.0", + "Average \u2b06\ufe0f": 75.76, + "ARC": 73.04, + "HellaSwag": 88.79, + "MMLU": 64.67, + "TruthfulQA": 68.15, + "Winogrande": 90.92, + "GSM8K": 68.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8b848fc487ec7d7d7b181400c960147af4e12b52", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "vanillaOVO\/supermario_v3", + "Average \u2b06\ufe0f": 75.75, + "ARC": 73.81, + "HellaSwag": 88.92, + "MMLU": 65.07, + "TruthfulQA": 72.01, + "Winogrande": 85.48, + "GSM8K": 69.22, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5d20941300a647c563a385ca95c963bb5f26bc69", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kquant03\/Cognito-2x7B-bf16", + "Average \u2b06\ufe0f": 75.74, + "ARC": 72.95, + "HellaSwag": 88.96, + "MMLU": 64.86, + "TruthfulQA": 71.7, + "Winogrande": 85.64, + "GSM8K": 70.36, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "b743668c7cf34e29d52adf22203850ee407b4e2e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "YKM11\/Mistral-7B-adaptv1", + "Average \u2b06\ufe0f": 75.74, + "ARC": 73.98, + "HellaSwag": 89.37, + "MMLU": 64.42, + "TruthfulQA": 74.55, + "Winogrande": 85.48, + "GSM8K": 66.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "105cb07b032ae67bcb204f873e96bab953cc3294", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yleo\/EmertonMonarch-7B", + "Average \u2b06\ufe0f": 75.74, + "ARC": 72.7, + "HellaSwag": 89.16, + "MMLU": 64.05, + "TruthfulQA": 78.09, + "Winogrande": 85.16, + "GSM8K": 65.28, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1a8a1ce0ceea0e298d9c8d5cce0b869a4a8c0514", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "macadeliccc\/OmniCorso-7B", + "Average \u2b06\ufe0f": 75.74, + "ARC": 72.7, + "HellaSwag": 88.7, + "MMLU": 64.91, + "TruthfulQA": 73.43, + "Winogrande": 83.74, + "GSM8K": 70.96, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "bb0af56aafce88413fb8c823ee7831a9a0d09e96", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AiMavenAi\/AiMaven-Prometheus", + "Average \u2b06\ufe0f": 75.74, + "ARC": 73.98, + "HellaSwag": 88.83, + "MMLU": 65.17, + "TruthfulQA": 72.22, + "Winogrande": 85.16, + "GSM8K": 69.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ee2dba5b9877b3b6d8f5b28f2900e4bfd4152a1b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kquant03\/Nanashi-2x7B-bf16", + "Average \u2b06\ufe0f": 75.72, + "ARC": 73.12, + "HellaSwag": 88.76, + "MMLU": 65.04, + "TruthfulQA": 71.31, + "Winogrande": 86.11, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a922f962cb95e4eb3d77357e82405486e64ab7b1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jefferylovely\/SuperThetaMaven", + "Average \u2b06\ufe0f": 75.71, + "ARC": 73.63, + "HellaSwag": 89.0, + "MMLU": 64.82, + "TruthfulQA": 71.77, + "Winogrande": 84.93, + "GSM8K": 70.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1344e7cb96b5c037c7bf00ed67311b582b56327f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment20-7B", + "Average \u2b06\ufe0f": 75.71, + "ARC": 73.04, + "HellaSwag": 88.62, + "MMLU": 63.23, + "TruthfulQA": 77.72, + "Winogrande": 85.0, + "GSM8K": 66.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2491f12e51d7b74fb47ef5480d4b5f547d4d19ea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "alnrg2arg\/blockchainlabs_test3_seminar", + "Average \u2b06\ufe0f": 75.7, + "ARC": 72.18, + "HellaSwag": 88.94, + "MMLU": 64.63, + "TruthfulQA": 72.47, + "Winogrande": 85.64, + "GSM8K": 70.36, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5c306a299896f682c0a392d893f258603d5d0706", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yleo\/EmertonOmniBeagle-7B-dpo", + "Average \u2b06\ufe0f": 75.67, + "ARC": 72.7, + "HellaSwag": 88.44, + "MMLU": 64.44, + "TruthfulQA": 75.62, + "Winogrande": 84.29, + "GSM8K": 68.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f484e7af54735acaa1b60d9ec95825818e74c46a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rizla\/rizla-17", + "Average \u2b06\ufe0f": 75.67, + "ARC": 73.63, + "HellaSwag": 89.72, + "MMLU": 64.4, + "TruthfulQA": 76.93, + "Winogrande": 87.85, + "GSM8K": 61.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 15.64, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "06aa2af4648aef092e914c9ae518a4ae2ec55f04", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "mlabonne\/OmniBeagle-7B", + "Average \u2b06\ufe0f": 75.66, + "ARC": 72.61, + "HellaSwag": 88.93, + "MMLU": 64.8, + "TruthfulQA": 74.45, + "Winogrande": 83.11, + "GSM8K": 70.05, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "035047bcb642b054307ae49052b2b8a6e58c7b2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/NeuralTrix-7B-dpo-relaser", + "Average \u2b06\ufe0f": 75.66, + "ARC": 71.33, + "HellaSwag": 88.41, + "MMLU": 64.01, + "TruthfulQA": 77.98, + "Winogrande": 84.06, + "GSM8K": 68.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e9e9d8a90abb9716c93ec93ec7d977527794201f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YKM11\/Mistral-7B-adaptv0.9", + "Average \u2b06\ufe0f": 75.65, + "ARC": 73.55, + "HellaSwag": 88.96, + "MMLU": 64.73, + "TruthfulQA": 73.12, + "Winogrande": 85.64, + "GSM8K": 67.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3bdfb578bb9ee94cb8b0f8c10cfaf1db3e9dc684", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Smaug-Mixtral-v0.1", + "Average \u2b06\ufe0f": 75.64, + "ARC": 74.91, + "HellaSwag": 87.79, + "MMLU": 70.08, + "TruthfulQA": 66.88, + "Winogrande": 81.69, + "GSM8K": 72.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "2f83b45077479bc3f663da50c4c40372894bf92e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "daxiongshu\/Pluto_24B_DPO_63", + "Average \u2b06\ufe0f": 75.63, + "ARC": 73.98, + "HellaSwag": 88.17, + "MMLU": 64.49, + "TruthfulQA": 79.36, + "Winogrande": 81.69, + "GSM8K": 66.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "72f6e05eddabe6f3fa8891c99c4ba02aa60158c1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "kaitchup\/Mayonnaise-4in1-022", + "Average \u2b06\ufe0f": 75.56, + "ARC": 72.87, + "HellaSwag": 88.63, + "MMLU": 64.93, + "TruthfulQA": 71.73, + "Winogrande": 84.69, + "GSM8K": 70.51, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "3b5f7ff495b82d71f4f542779435ce737811ea25", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "NeuralNovel\/Confinus-2x7B", + "Average \u2b06\ufe0f": 75.55, + "ARC": 73.89, + "HellaSwag": 88.82, + "MMLU": 65.12, + "TruthfulQA": 71.88, + "Winogrande": 84.77, + "GSM8K": 68.84, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "5eeb9b70e39db055b51811931a04481ed58c8092", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/OrcaHermes-Mistral-70B-miqu", + "Average \u2b06\ufe0f": 75.51, + "ARC": 71.33, + "HellaSwag": 87.78, + "MMLU": 75.47, + "TruthfulQA": 60.72, + "Winogrande": 84.53, + "GSM8K": 73.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d8b56411b045767511593f901179c01855e9d7e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "vanillaOVO\/supermario_v2", + "Average \u2b06\ufe0f": 75.49, + "ARC": 72.95, + "HellaSwag": 88.53, + "MMLU": 64.99, + "TruthfulQA": 71.22, + "Winogrande": 83.9, + "GSM8K": 71.34, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ae95b6254eee9bd1de68fc6f4881a7bb98d57235", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "louisbrulenaudet\/Pearl-34B-ties", + "Average \u2b06\ufe0f": 75.48, + "ARC": 70.99, + "HellaSwag": 84.83, + "MMLU": 76.63, + "TruthfulQA": 70.32, + "Winogrande": 82.64, + "GSM8K": 67.48, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "be28f8663c6f49e1df04ddd59f4475cb93575272", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Phoenix_DPO_60B", + "Average \u2b06\ufe0f": 75.48, + "ARC": 71.16, + "HellaSwag": 85.46, + "MMLU": 77.66, + "TruthfulQA": 63.84, + "Winogrande": 84.93, + "GSM8K": 69.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "bd9ac169a0d6acb8fb66d55a6471ef162271b248", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "SC56\/Mistral-7B-orca-dpo-2h", + "Average \u2b06\ufe0f": 75.48, + "ARC": 73.12, + "HellaSwag": 88.65, + "MMLU": 64.99, + "TruthfulQA": 71.31, + "Winogrande": 84.21, + "GSM8K": 70.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5b96d5e0a38d25fe6bd72939a8eb193c34e59232", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Helion-4x34B", + "Average \u2b06\ufe0f": 75.48, + "ARC": 69.71, + "HellaSwag": 85.28, + "MMLU": 77.33, + "TruthfulQA": 63.91, + "Winogrande": 84.37, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 113.66, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "583254a5a134243d7793b311c465da12b10a3ff2", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/multimaster-7b-v4", + "Average \u2b06\ufe0f": 75.47, + "ARC": 72.53, + "HellaSwag": 88.77, + "MMLU": 64.85, + "TruthfulQA": 70.74, + "Winogrande": 86.27, + "GSM8K": 69.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a89b5a4ce482c531b1cb3b8703e8eb2b9321994c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/UNA-34BeagleSimpleMath-32K-v1", + "Average \u2b06\ufe0f": 75.45, + "ARC": 74.15, + "HellaSwag": 85.98, + "MMLU": 76.52, + "TruthfulQA": 73.74, + "Winogrande": 83.27, + "GSM8K": 59.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "ead4b4aedf94b98916f30388b85620a3583375e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ShinojiResearch\/Senku-70B-Full", + "Average \u2b06\ufe0f": 75.44, + "ARC": 71.5, + "HellaSwag": 87.88, + "MMLU": 75.2, + "TruthfulQA": 61.96, + "Winogrande": 84.77, + "GSM8K": 71.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-2.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cf06159aaaadda2ca50b19ce547a52424f7d47c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC56\/Mistral-7B-sumz-dpo-3h", + "Average \u2b06\ufe0f": 75.43, + "ARC": 73.04, + "HellaSwag": 88.67, + "MMLU": 64.78, + "TruthfulQA": 71.53, + "Winogrande": 84.21, + "GSM8K": 70.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a704fa5a292b5f8667a23f2e818ae8cdcf51779b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC56\/Mistral-7B-orca-dpo-4h", + "Average \u2b06\ufe0f": 75.42, + "ARC": 73.38, + "HellaSwag": 88.73, + "MMLU": 64.97, + "TruthfulQA": 71.65, + "Winogrande": 84.29, + "GSM8K": 69.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b82e05bf781ad9be0febdb2d8aaa4efbc7ca43fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "s3nh\/SeverusWestLake-7B-DPO", + "Average \u2b06\ufe0f": 75.42, + "ARC": 72.18, + "HellaSwag": 88.94, + "MMLU": 64.65, + "TruthfulQA": 71.49, + "Winogrande": 86.11, + "GSM8K": 69.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "5d6dd3a16f0469cff432410b29ec410167b71c49", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "one-man-army\/UNA-34Beagles-32K-bf16-v1", + "Average \u2b06\ufe0f": 75.41, + "ARC": 73.55, + "HellaSwag": 85.93, + "MMLU": 76.45, + "TruthfulQA": 73.55, + "Winogrande": 82.95, + "GSM8K": 60.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "d6024b97f624e9169a63f5faccb8c5ab121eb13a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/UNA-34Beagles-32K-v1", + "Average \u2b06\ufe0f": 75.41, + "ARC": 73.55, + "HellaSwag": 85.93, + "MMLU": 76.45, + "TruthfulQA": 73.55, + "Winogrande": 82.95, + "GSM8K": 60.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e02a631564990af3d9c8b0232f979af11cd8b6f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC44\/Mistral-7B-private-spef", + "Average \u2b06\ufe0f": 75.41, + "ARC": 73.21, + "HellaSwag": 88.68, + "MMLU": 64.9, + "TruthfulQA": 71.91, + "Winogrande": 84.85, + "GSM8K": 68.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bb29794e86ff6a39f77185f547c6bb335d2f5649", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC44\/Mistral-7B-private-spnf", + "Average \u2b06\ufe0f": 75.41, + "ARC": 73.04, + "HellaSwag": 88.67, + "MMLU": 64.91, + "TruthfulQA": 71.85, + "Winogrande": 84.77, + "GSM8K": 69.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b517b17cdec49dfa1dbb1927cfcac97eec020a59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Scorpio-7B", + "Average \u2b06\ufe0f": 75.4, + "ARC": 71.33, + "HellaSwag": 88.5, + "MMLU": 64.7, + "TruthfulQA": 72.51, + "Winogrande": 83.5, + "GSM8K": 71.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ea5855b529987fde6eca87492bccbd28eef8d052", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/ConfigurableBeagle-11B", + "Average \u2b06\ufe0f": 75.4, + "ARC": 72.53, + "HellaSwag": 88.85, + "MMLU": 66.71, + "TruthfulQA": 77.13, + "Winogrande": 83.27, + "GSM8K": 63.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fbf1c9958c47062e2db30276c723867c0d019652", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Cosmosis-3x34B", + "Average \u2b06\ufe0f": 75.39, + "ARC": 69.71, + "HellaSwag": 85.18, + "MMLU": 77.25, + "TruthfulQA": 63.82, + "Winogrande": 84.14, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 87.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "644f20245c08dbbc6baad20100fcf0c8bd3181a0", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "SC99\/Mistral-7B-privatemix-ia1", + "Average \u2b06\ufe0f": 75.39, + "ARC": 72.78, + "HellaSwag": 88.59, + "MMLU": 64.5, + "TruthfulQA": 71.79, + "Winogrande": 85.08, + "GSM8K": 69.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dda79b349b53c2d4efd52a99a0ae31c28f3693cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "jsfs11\/MoEv4Config-TestWeightedTIES-7b", + "Average \u2b06\ufe0f": 75.39, + "ARC": 71.59, + "HellaSwag": 88.19, + "MMLU": 65.07, + "TruthfulQA": 70.87, + "Winogrande": 83.82, + "GSM8K": 72.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8a004ce7527c8abb6273df00cb5bcaa5a6aa2d65", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "yleo\/EmertonBeagle-7B-dpo", + "Average \u2b06\ufe0f": 75.39, + "ARC": 72.78, + "HellaSwag": 89.12, + "MMLU": 64.47, + "TruthfulQA": 75.96, + "Winogrande": 83.58, + "GSM8K": 66.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2a1ecaab96bfb99cb01cb3217d34002b059eba3f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "shadowml\/BeagSake-7B", + "Average \u2b06\ufe0f": 75.38, + "ARC": 72.44, + "HellaSwag": 88.39, + "MMLU": 65.23, + "TruthfulQA": 72.27, + "Winogrande": 82.16, + "GSM8K": 71.8, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e1ae2c1e9bea8b54f6b8bff41a4f50895625a6ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/WestLake-7B-v2-laser-truthy-dpo", + "Average \u2b06\ufe0f": 75.37, + "ARC": 73.89, + "HellaSwag": 88.85, + "MMLU": 64.84, + "TruthfulQA": 69.81, + "Winogrande": 86.66, + "GSM8K": 68.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "e01fb197b4303ba63ba2f4d68a897006ec7ec4fd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kquant03\/Azathoth-16x7B-bf16", + "Average \u2b06\ufe0f": 75.36, + "ARC": 73.81, + "HellaSwag": 88.87, + "MMLU": 64.6, + "TruthfulQA": 69.61, + "Winogrande": 85.48, + "GSM8K": 69.83, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 91.8, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "452d46da45e058c4dcaf2c14216e9832bfb994dd", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "jsfs11\/RandomMergeNoNormWEIGHTED-7B-DARETIES", + "Average \u2b06\ufe0f": 75.36, + "ARC": 73.38, + "HellaSwag": 88.5, + "MMLU": 64.94, + "TruthfulQA": 71.5, + "Winogrande": 83.58, + "GSM8K": 70.28, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "611f9e29fc041be6c915538c4883669b17d1e1e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment19-7B", + "Average \u2b06\ufe0f": 75.36, + "ARC": 72.35, + "HellaSwag": 88.61, + "MMLU": 63.08, + "TruthfulQA": 78.18, + "Winogrande": 84.53, + "GSM8K": 65.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ebc7cba80494385e29bce8b1b86a75d14666c19e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ShinojiResearch\/Senku-70B-Full", + "Average \u2b06\ufe0f": 75.36, + "ARC": 71.33, + "HellaSwag": 87.86, + "MMLU": 75.14, + "TruthfulQA": 61.95, + "Winogrande": 84.53, + "GSM8K": 71.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-2.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cf06159aaaadda2ca50b19ce547a52424f7d47c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnowMee\/Mistral-7b-instruct-v0.2-summ-dpo-ed2", + "Average \u2b06\ufe0f": 75.34, + "ARC": 74.4, + "HellaSwag": 89.29, + "MMLU": 64.23, + "TruthfulQA": 72.34, + "Winogrande": 84.14, + "GSM8K": 67.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b6c9416b0deeb567f59891db1a1dce7a59fc54e4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnowMee\/Mistral-7b-instruct-v0.2-summ-dpo-ed3", + "Average \u2b06\ufe0f": 75.34, + "ARC": 74.23, + "HellaSwag": 89.28, + "MMLU": 64.37, + "TruthfulQA": 72.31, + "Winogrande": 84.37, + "GSM8K": 67.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "23f8fc9ed8d1d5ff71695307e3e1dd43ae670549", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/Neural4gsm8k", + "Average \u2b06\ufe0f": 75.31, + "ARC": 72.27, + "HellaSwag": 88.45, + "MMLU": 64.76, + "TruthfulQA": 69.65, + "Winogrande": 83.35, + "GSM8K": 73.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "be0bb5f5203cb447f4c64a4399213ce89e8b3d3e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "jsfs11\/MixtureofMerges-MoE-4x7b-v3", + "Average \u2b06\ufe0f": 75.31, + "ARC": 74.4, + "HellaSwag": 88.62, + "MMLU": 64.82, + "TruthfulQA": 70.78, + "Winogrande": 85.0, + "GSM8K": 68.23, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0f467f3f3c2182f5798885f4166c2445ea817129", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/Wernicke-7B-dpo", + "Average \u2b06\ufe0f": 75.31, + "ARC": 71.84, + "HellaSwag": 88.63, + "MMLU": 65.22, + "TruthfulQA": 73.91, + "Winogrande": 84.61, + "GSM8K": 67.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "59ae4689046b197444514a0ec531fdb3341b33cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.2", + "Average \u2b06\ufe0f": 75.3, + "ARC": 73.81, + "HellaSwag": 88.65, + "MMLU": 64.76, + "TruthfulQA": 69.79, + "Winogrande": 84.29, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c3fa3d4679f303bce6d56357abb9069fdf8b44c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC56\/Mistral-7B-sumz-dpo-4h", + "Average \u2b06\ufe0f": 75.3, + "ARC": 72.95, + "HellaSwag": 88.81, + "MMLU": 64.8, + "TruthfulQA": 71.74, + "Winogrande": 83.98, + "GSM8K": 69.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "64895c1f9916b5299f2a94412d6cfddd4d0845a0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/kiqu-70b", + "Average \u2b06\ufe0f": 75.29, + "ARC": 72.1, + "HellaSwag": 87.94, + "MMLU": 74.93, + "TruthfulQA": 63.48, + "Winogrande": 84.85, + "GSM8K": 68.46, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "c8ad8ee000e4e042d80e4cf53fb6d0815d7743dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/WestSeverus-7B-DPO-v2", + "Average \u2b06\ufe0f": 75.29, + "ARC": 71.42, + "HellaSwag": 88.27, + "MMLU": 64.79, + "TruthfulQA": 72.37, + "Winogrande": 83.27, + "GSM8K": 71.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "50dd207ce4319397d862a91f8295d902549dbdf7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BarryFutureman\/WildMarcoroni-Variant1-7B", + "Average \u2b06\ufe0f": 75.29, + "ARC": 73.98, + "HellaSwag": 88.61, + "MMLU": 64.81, + "TruthfulQA": 69.76, + "Winogrande": 84.29, + "GSM8K": 70.28, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "288b2e327f81e6f97fe1d68e2f0f08a46cdbf6eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.21", + "Average \u2b06\ufe0f": 75.29, + "ARC": 73.98, + "HellaSwag": 88.61, + "MMLU": 64.81, + "TruthfulQA": 69.76, + "Winogrande": 84.29, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "15f7ace0735678feec75a36589ed4760bfa172bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alnrg2arg\/test2_4", + "Average \u2b06\ufe0f": 75.28, + "ARC": 73.55, + "HellaSwag": 88.87, + "MMLU": 64.63, + "TruthfulQA": 69.77, + "Winogrande": 84.45, + "GSM8K": 70.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ed17cf5af87733ffd7836ab99f27991544ba2547", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alnrg2arg\/blockchainlabs_7B_merged_test2_4", + "Average \u2b06\ufe0f": 75.28, + "ARC": 73.55, + "HellaSwag": 88.87, + "MMLU": 64.63, + "TruthfulQA": 69.77, + "Winogrande": 84.45, + "GSM8K": 70.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "eb671cc5e88553f568c17eaf0e60d1616665ed95", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alnrg2arg\/test3_sft_16bit", + "Average \u2b06\ufe0f": 75.28, + "ARC": 73.55, + "HellaSwag": 88.87, + "MMLU": 64.63, + "TruthfulQA": 69.77, + "Winogrande": 84.45, + "GSM8K": 70.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a892e9a26785d59d8bf4ccef48606664c6cbc48b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder67\/Mistral-7b-instruct-v0.2-summ-sft-dpo-e2", + "Average \u2b06\ufe0f": 75.28, + "ARC": 73.81, + "HellaSwag": 88.85, + "MMLU": 64.61, + "TruthfulQA": 72.14, + "Winogrande": 83.27, + "GSM8K": 68.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "803a3e7f24f61e8cd53ef4133ae22c3ce2568a78", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kquant03\/Buttercup-V2-bf16", + "Average \u2b06\ufe0f": 75.26, + "ARC": 73.72, + "HellaSwag": 88.54, + "MMLU": 64.68, + "TruthfulQA": 69.47, + "Winogrande": 86.5, + "GSM8K": 68.61, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "307a74cb147a9d93e20755b047e9b5be4293e017", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "AbacusResearch\/haLLawa4-7b", + "Average \u2b06\ufe0f": 75.25, + "ARC": 71.5, + "HellaSwag": 88.36, + "MMLU": 64.49, + "TruthfulQA": 74.27, + "Winogrande": 82.4, + "GSM8K": 70.51, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "246c8ccf36db945de3575f2896bfe82d17ee628f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Faraday-7B", + "Average \u2b06\ufe0f": 75.25, + "ARC": 72.27, + "HellaSwag": 88.9, + "MMLU": 64.69, + "TruthfulQA": 73.07, + "Winogrande": 85.32, + "GSM8K": 67.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "2d197f7a290d191183b86f35c3857dd15a16d9b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Astralis-4x34B", + "Average \u2b06\ufe0f": 75.24, + "ARC": 69.71, + "HellaSwag": 85.17, + "MMLU": 77.24, + "TruthfulQA": 63.55, + "Winogrande": 84.14, + "GSM8K": 71.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 113.66, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "513311818a707ccc0c7d007ddabfab19e1a2e470", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "flemmingmiguel\/MBX-7B-v2", + "Average \u2b06\ufe0f": 75.24, + "ARC": 73.55, + "HellaSwag": 88.5, + "MMLU": 64.78, + "TruthfulQA": 70.21, + "Winogrande": 83.9, + "GSM8K": 70.51, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1e8604ec6f544415814c68ef0b9666393567e7dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder67\/Mistral-7b-instruct-v0.2-summ-sft-dpo-e1", + "Average \u2b06\ufe0f": 75.24, + "ARC": 73.98, + "HellaSwag": 89.27, + "MMLU": 64.16, + "TruthfulQA": 72.79, + "Winogrande": 84.45, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9eae12f70b601824919394f486dcad3fba26ca3e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Bagel-Hermes-34B-Slerp", + "Average \u2b06\ufe0f": 75.24, + "ARC": 70.73, + "HellaSwag": 85.68, + "MMLU": 77.29, + "TruthfulQA": 67.09, + "Winogrande": 84.37, + "GSM8K": 66.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ca42d74d2b7fa947e27305e41c61784f8fe9dafa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.22", + "Average \u2b06\ufe0f": 75.23, + "ARC": 72.53, + "HellaSwag": 88.5, + "MMLU": 65.0, + "TruthfulQA": 71.26, + "Winogrande": 83.9, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5bcce7562c547b81d8bc41363e1fedb15fde429c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnwMe\/Mistral-7B-Instruct-exp-e2", + "Average \u2b06\ufe0f": 75.23, + "ARC": 72.53, + "HellaSwag": 88.5, + "MMLU": 65.0, + "TruthfulQA": 71.26, + "Winogrande": 83.9, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9e85b1810b7e4c549711b217cadde6e93c6b60d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.21", + "Average \u2b06\ufe0f": 75.23, + "ARC": 72.53, + "HellaSwag": 88.5, + "MMLU": 65.0, + "TruthfulQA": 71.26, + "Winogrande": 83.9, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "15f7ace0735678feec75a36589ed4760bfa172bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-v0.23", + "Average \u2b06\ufe0f": 75.23, + "ARC": 72.53, + "HellaSwag": 88.5, + "MMLU": 65.0, + "TruthfulQA": 71.26, + "Winogrande": 83.9, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c11553f07f16813545fe8c8eab410b164eb7cea3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnowMee\/Mistral-7b-instruct-v0.2-summ-sft-dpo-ed2", + "Average \u2b06\ufe0f": 75.23, + "ARC": 74.06, + "HellaSwag": 89.25, + "MMLU": 64.25, + "TruthfulQA": 72.73, + "Winogrande": 84.69, + "GSM8K": 66.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f0774eebdb546c237cf312fe7041abe375c88ac0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Faraday-7B", + "Average \u2b06\ufe0f": 75.22, + "ARC": 72.44, + "HellaSwag": 88.91, + "MMLU": 64.68, + "TruthfulQA": 73.03, + "Winogrande": 85.56, + "GSM8K": 66.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "2d197f7a290d191183b86f35c3857dd15a16d9b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC56\/Mistral-7B-sumz-dpo-5h", + "Average \u2b06\ufe0f": 75.22, + "ARC": 72.7, + "HellaSwag": 88.99, + "MMLU": 64.78, + "TruthfulQA": 72.36, + "Winogrande": 83.9, + "GSM8K": 68.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6a311ececab8cb8de5a3f6fd6a9afd1a4d5f7a80", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "shadowml\/WestBeagle-7B", + "Average \u2b06\ufe0f": 75.22, + "ARC": 72.27, + "HellaSwag": 88.29, + "MMLU": 65.17, + "TruthfulQA": 71.71, + "Winogrande": 82.0, + "GSM8K": 71.87, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e84cd31eaed755a286dee0c9ca2fe4308e693f64", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/Wernicke-7B-v8", + "Average \u2b06\ufe0f": 75.21, + "ARC": 72.44, + "HellaSwag": 88.7, + "MMLU": 64.62, + "TruthfulQA": 71.3, + "Winogrande": 84.85, + "GSM8K": 69.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f65b1538d77cc48cb646e0c53350b55fd03bc96c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "kaitchup\/Mayonnaise-4in1-02", + "Average \u2b06\ufe0f": 75.21, + "ARC": 73.38, + "HellaSwag": 88.51, + "MMLU": 64.89, + "TruthfulQA": 69.04, + "Winogrande": 84.37, + "GSM8K": 71.04, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9a0c4751e8cf3b766d2cf55b70ec5eca5096c522", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zhengr\/MixTAO-7Bx2-MoE-Instruct-v2.0", + "Average \u2b06\ufe0f": 75.2, + "ARC": 73.38, + "HellaSwag": 88.81, + "MMLU": 64.65, + "TruthfulQA": 69.76, + "Winogrande": 83.82, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d558d93b7f8bd8c5ca01f1d272f4a42f52b8d9ae", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnowMee\/Mistral-7b-instruct-v0.2-summ-sft-dpo-ed3", + "Average \u2b06\ufe0f": 75.2, + "ARC": 73.98, + "HellaSwag": 89.26, + "MMLU": 64.28, + "TruthfulQA": 72.76, + "Winogrande": 84.69, + "GSM8K": 66.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9e501956cd6183dd13b80f5be6eaa5d37fff8848", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jsfs11\/TurdusTrixBeagle-DARETIES-7B", + "Average \u2b06\ufe0f": 75.2, + "ARC": 73.46, + "HellaSwag": 88.61, + "MMLU": 64.89, + "TruthfulQA": 68.81, + "Winogrande": 85.16, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f2f91c82dd2ad8f3c4514a83e793cfb4a59da323", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "kaitchup\/Mayonnaise-4in1-01", + "Average \u2b06\ufe0f": 75.19, + "ARC": 73.46, + "HellaSwag": 88.47, + "MMLU": 64.95, + "TruthfulQA": 69.18, + "Winogrande": 84.14, + "GSM8K": 70.96, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ab57f82bf8eb169be3560a44cc94653e024cedf4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/CombinaTrix-7B", + "Average \u2b06\ufe0f": 75.19, + "ARC": 72.87, + "HellaSwag": 88.4, + "MMLU": 64.85, + "TruthfulQA": 70.63, + "Winogrande": 84.14, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1962b09249cb27870cef33edde88872b088f7dc7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Eric111\/CatunaMayo-DPO", + "Average \u2b06\ufe0f": 75.19, + "ARC": 72.87, + "HellaSwag": 88.3, + "MMLU": 65.24, + "TruthfulQA": 71.82, + "Winogrande": 82.72, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "54959097f175441fcb25c9eec1f4169ee7d5232f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/Wernicke-7B-v9", + "Average \u2b06\ufe0f": 75.18, + "ARC": 72.44, + "HellaSwag": 88.54, + "MMLU": 64.9, + "TruthfulQA": 71.86, + "Winogrande": 84.06, + "GSM8K": 69.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "2ad6dc3fc3551ef641c0ca6b7dbb157194d9a911", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "s3nh\/Severusectum-7B-DPO", + "Average \u2b06\ufe0f": 75.18, + "ARC": 71.5, + "HellaSwag": 88.55, + "MMLU": 64.79, + "TruthfulQA": 72.45, + "Winogrande": 83.27, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "50f69f6cddaee727bb25f23a0eb525175a2c6491", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PetroGPT\/WestSeverus-7B-DPO", + "Average \u2b06\ufe0f": 75.17, + "ARC": 70.73, + "HellaSwag": 88.01, + "MMLU": 64.93, + "TruthfulQA": 70.53, + "Winogrande": 83.5, + "GSM8K": 73.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e13a48ef1524ba35615d7f63834e7c9192fa1836", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "udkai\/Garrulus", + "Average \u2b06\ufe0f": 75.16, + "ARC": 73.29, + "HellaSwag": 88.87, + "MMLU": 64.57, + "TruthfulQA": 68.23, + "Winogrande": 91.48, + "GSM8K": 64.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "cd2fa5c2188588b903fff2070a389db3b24031a4", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/Wernicke-7B-v1", + "Average \u2b06\ufe0f": 75.15, + "ARC": 73.21, + "HellaSwag": 88.48, + "MMLU": 64.95, + "TruthfulQA": 70.95, + "Winogrande": 83.74, + "GSM8K": 69.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "752573009b7d0518958d4b98b3154678af7c2bde", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dfurman\/HermesBagel-34B-v0.1", + "Average \u2b06\ufe0f": 75.15, + "ARC": 70.56, + "HellaSwag": 85.74, + "MMLU": 77.38, + "TruthfulQA": 67.34, + "Winogrande": 84.61, + "GSM8K": 65.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7364cfc1f2c7fc56d460adc0dc90d7a6d13641fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "leveldevai\/TurdusBeagle-7B", + "Average \u2b06\ufe0f": 75.15, + "ARC": 73.63, + "HellaSwag": 88.89, + "MMLU": 64.7, + "TruthfulQA": 69.71, + "Winogrande": 83.9, + "GSM8K": 70.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "bdd2c0aa848a559c6f55c51c0abd1f3cde683909", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC56\/Mistral-7B-orca-dpo-8h", + "Average \u2b06\ufe0f": 75.14, + "ARC": 72.44, + "HellaSwag": 88.99, + "MMLU": 64.59, + "TruthfulQA": 72.96, + "Winogrande": 84.45, + "GSM8K": 67.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6ab6f2489b77ba23d0cc230ff4cbb826eb5bc6e5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Sectumsempra-7B-DPO", + "Average \u2b06\ufe0f": 75.14, + "ARC": 71.5, + "HellaSwag": 88.7, + "MMLU": 64.9, + "TruthfulQA": 72.49, + "Winogrande": 83.19, + "GSM8K": 70.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5ecc835f4137adac99198831c61c2afff4f340cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/TheTop-5x7B-Instruct-S5-v0.1", + "Average \u2b06\ufe0f": 75.14, + "ARC": 72.53, + "HellaSwag": 88.71, + "MMLU": 65.01, + "TruthfulQA": 67.58, + "Winogrande": 86.19, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "538565474e9cf94b3ab4cd0b74a3537a338831f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/OmniTrixAI", + "Average \u2b06\ufe0f": 75.13, + "ARC": 72.95, + "HellaSwag": 88.52, + "MMLU": 65.12, + "TruthfulQA": 70.12, + "Winogrande": 83.58, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "53c0bd452b1b4535d5c97bcf6405b4c3d3b260a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/MiquMaid-v1-70B", + "Average \u2b06\ufe0f": 75.12, + "ARC": 71.67, + "HellaSwag": 87.96, + "MMLU": 74.9, + "TruthfulQA": 61.79, + "Winogrande": 85.08, + "GSM8K": 69.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "0dc1f9340fac9aadf883f52e6409e49e8d286af6", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/SevereNeuralBeagleTrix-7B", + "Average \u2b06\ufe0f": 75.12, + "ARC": 72.78, + "HellaSwag": 88.33, + "MMLU": 65.09, + "TruthfulQA": 69.02, + "Winogrande": 83.82, + "GSM8K": 71.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1593a524ec3a8be887da0569cf1a2081071f67ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "louisbrulenaudet\/Pearl-7B-0211-ties", + "Average \u2b06\ufe0f": 75.11, + "ARC": 71.42, + "HellaSwag": 88.86, + "MMLU": 63.91, + "TruthfulQA": 71.46, + "Winogrande": 84.37, + "GSM8K": 70.66, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "15db1e92e1683166a32da6f54c6ee6d6c10c20cb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "leveldevai\/MarcBeagle-7B", + "Average \u2b06\ufe0f": 75.11, + "ARC": 73.12, + "HellaSwag": 88.43, + "MMLU": 64.92, + "TruthfulQA": 69.18, + "Winogrande": 83.82, + "GSM8K": 71.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9c742da68447832157389dad53be682e7d6c1d5f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "eren23\/slerp-test-turdus-beagle", + "Average \u2b06\ufe0f": 75.11, + "ARC": 73.55, + "HellaSwag": 88.85, + "MMLU": 64.62, + "TruthfulQA": 69.69, + "Winogrande": 83.9, + "GSM8K": 70.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f2aef36538bb0c7aab30ffe889e12b72f51a6816", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnwMe\/Direct-sm-private-e1", + "Average \u2b06\ufe0f": 75.1, + "ARC": 72.53, + "HellaSwag": 88.98, + "MMLU": 64.55, + "TruthfulQA": 72.81, + "Winogrande": 83.82, + "GSM8K": 67.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0465002ffc1849eee1223b57dcf180e4dbd09d34", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnwMe\/Mistral-7b-instruct-v0.2-private-eds2", + "Average \u2b06\ufe0f": 75.1, + "ARC": 72.7, + "HellaSwag": 89.05, + "MMLU": 64.21, + "TruthfulQA": 73.88, + "Winogrande": 83.98, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d4cffeadbb02eaf6273e954fc5aea4f745747705", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xDAN2099\/xDAN-L2-moe-2x-v1", + "Average \u2b06\ufe0f": 75.1, + "ARC": 68.52, + "HellaSwag": 86.31, + "MMLU": 76.76, + "TruthfulQA": 61.77, + "Winogrande": 84.29, + "GSM8K": 72.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0a137b01142b62fccfcbc81176d40f4b86405958", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Bagel-Hermes-2x34B", + "Average \u2b06\ufe0f": 75.1, + "ARC": 69.8, + "HellaSwag": 85.26, + "MMLU": 77.24, + "TruthfulQA": 64.82, + "Winogrande": 84.77, + "GSM8K": 68.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d187b7bd6757d78bf89aaad8b0b5834ddbf29392", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Bagel-Hermes-2x34b", + "Average \u2b06\ufe0f": 75.1, + "ARC": 69.8, + "HellaSwag": 85.26, + "MMLU": 77.24, + "TruthfulQA": 64.82, + "Winogrande": 84.77, + "GSM8K": 68.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d187b7bd6757d78bf89aaad8b0b5834ddbf29392", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jsfs11\/WildMBXMarconi-SLERP-7B", + "Average \u2b06\ufe0f": 75.09, + "ARC": 73.29, + "HellaSwag": 88.49, + "MMLU": 64.9, + "TruthfulQA": 68.98, + "Winogrande": 83.98, + "GSM8K": 70.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d50e66f9cfab5320ca4d3caad9e527254d923d90", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "zhengr\/MixTAO-7Bx2-MoE-Instruct-v5.0", + "Average \u2b06\ufe0f": 75.08, + "ARC": 73.63, + "HellaSwag": 88.93, + "MMLU": 64.65, + "TruthfulQA": 69.83, + "Winogrande": 83.98, + "GSM8K": 69.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e2c043dadae748feedea411e1ce2548d1b91aa80", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/Samlagast-7B-laser-bf16", + "Average \u2b06\ufe0f": 75.06, + "ARC": 72.87, + "HellaSwag": 88.96, + "MMLU": 64.35, + "TruthfulQA": 73.16, + "Winogrande": 85.4, + "GSM8K": 65.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3d2e5b5fd23cee9303ce2b8e068aa49973a3f61e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "AbacusResearch\/jaLLAbi2-7b", + "Average \u2b06\ufe0f": 75.06, + "ARC": 71.67, + "HellaSwag": 88.29, + "MMLU": 64.92, + "TruthfulQA": 70.16, + "Winogrande": 83.35, + "GSM8K": 71.95, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e51c2fd0e60ca0c20a8d9094a878f98c7880967a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarryFutureman\/WestLakeX-7B-EvoMerge-Variant2", + "Average \u2b06\ufe0f": 75.04, + "ARC": 72.53, + "HellaSwag": 88.52, + "MMLU": 64.77, + "TruthfulQA": 70.35, + "Winogrande": 85.79, + "GSM8K": 68.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2e36c528223443d6b8b5203b6a013e79f6d78d09", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Cygnus-7B", + "Average \u2b06\ufe0f": 75.04, + "ARC": 70.9, + "HellaSwag": 87.82, + "MMLU": 63.81, + "TruthfulQA": 72.61, + "Winogrande": 81.93, + "GSM8K": 73.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "12e91d9302ecdd09d37d13da79b5761727b20eb8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "flemmingmiguel\/MBX-7B", + "Average \u2b06\ufe0f": 75.04, + "ARC": 72.87, + "HellaSwag": 88.38, + "MMLU": 64.93, + "TruthfulQA": 69.11, + "Winogrande": 83.66, + "GSM8K": 71.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "2270125929da3aa44594f7d0f82ac142cbdc38c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sumo43\/Yi-34b-x2", + "Average \u2b06\ufe0f": 75.02, + "ARC": 72.87, + "HellaSwag": 85.7, + "MMLU": 76.64, + "TruthfulQA": 72.1, + "Winogrande": 82.79, + "GSM8K": 60.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "09876944a5d29e7f8e4da1347cd1d8f6f2151444", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BarryFutureman\/ChatMarc-YesAnotherMerge-7B", + "Average \u2b06\ufe0f": 75.02, + "ARC": 72.78, + "HellaSwag": 88.39, + "MMLU": 65.01, + "TruthfulQA": 70.04, + "Winogrande": 83.9, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a1cf8fff75a44a3085ef0537cc11e833979b6017", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/multimaster-7b-v5", + "Average \u2b06\ufe0f": 75.01, + "ARC": 72.18, + "HellaSwag": 88.42, + "MMLU": 65.06, + "TruthfulQA": 70.37, + "Winogrande": 86.03, + "GSM8K": 68.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "95d031f0cad065bc18387f09ce37b256756f762f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zhengr\/MixTAO-7Bx2-MoE-Instruct-v1.0", + "Average \u2b06\ufe0f": 74.99, + "ARC": 74.06, + "HellaSwag": 88.25, + "MMLU": 64.25, + "TruthfulQA": 69.61, + "Winogrande": 84.29, + "GSM8K": 69.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "02e3cacbd9a9518289f6101fbcca8f7a875c1dfc", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "alnrg2arg\/test3_sft_16bit_dpo2", + "Average \u2b06\ufe0f": 74.98, + "ARC": 73.63, + "HellaSwag": 89.03, + "MMLU": 64.63, + "TruthfulQA": 70.71, + "Winogrande": 84.37, + "GSM8K": 67.48, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8a741a32e8d1d426c408c3eeb208eccc172c655e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andrijdavid\/Macaroni-7b-Tied", + "Average \u2b06\ufe0f": 74.96, + "ARC": 72.87, + "HellaSwag": 88.14, + "MMLU": 64.73, + "TruthfulQA": 70.54, + "Winogrande": 81.93, + "GSM8K": 71.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6323cf53ed75eab25ca37b3636a0f38ee8d1ac30", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/TheTop-5x7B-Instruct-T-v0.1", + "Average \u2b06\ufe0f": 74.96, + "ARC": 73.63, + "HellaSwag": 88.85, + "MMLU": 64.22, + "TruthfulQA": 70.78, + "Winogrande": 85.79, + "GSM8K": 66.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "dd841bf2fc42cb4f872fab04a638465cb06a4b7a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ycros\/BagelMIsteryTour-v2-8x7B", + "Average \u2b06\ufe0f": 74.95, + "ARC": 72.7, + "HellaSwag": 87.36, + "MMLU": 71.16, + "TruthfulQA": 74.54, + "Winogrande": 82.64, + "GSM8K": 61.33, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "98a8b319707be3dab1659594da69a37ed8f8c148", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/CatunaMayo", + "Average \u2b06\ufe0f": 74.95, + "ARC": 71.76, + "HellaSwag": 87.9, + "MMLU": 65.21, + "TruthfulQA": 69.96, + "Winogrande": 82.56, + "GSM8K": 72.33, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9dc038fac8b37aac504e851c311bede4092afafd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "eric111\/CatunaMayo", + "Average \u2b06\ufe0f": 74.95, + "ARC": 71.76, + "HellaSwag": 87.9, + "MMLU": 65.21, + "TruthfulQA": 69.96, + "Winogrande": 82.56, + "GSM8K": 72.33, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9dc038fac8b37aac504e851c311bede4092afafd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/Buttercup-V2-laser", + "Average \u2b06\ufe0f": 74.95, + "ARC": 73.12, + "HellaSwag": 88.48, + "MMLU": 64.74, + "TruthfulQA": 69.0, + "Winogrande": 86.27, + "GSM8K": 68.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b53163f2a7b562ce0191bdadd9d1f2e77a2b5a5e", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "rwitz2\/go-bruins-v2.1.1", + "Average \u2b06\ufe0f": 74.95, + "ARC": 72.87, + "HellaSwag": 88.33, + "MMLU": 65.18, + "TruthfulQA": 69.8, + "Winogrande": 82.24, + "GSM8K": 71.27, + "Type": "", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "bd56295eab54eaacbb3af6ecb88b9434d9966d4e", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "kaitchup\/TheMayonnaise", + "Average \u2b06\ufe0f": 74.94, + "ARC": 73.46, + "HellaSwag": 88.46, + "MMLU": 64.88, + "TruthfulQA": 69.19, + "Winogrande": 84.29, + "GSM8K": 69.37, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fb9c16c8878a5d688d0999e216f6fb0bb0b31ffe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ConvexAI\/BurningBruce-004", + "Average \u2b06\ufe0f": 74.94, + "ARC": 73.29, + "HellaSwag": 88.63, + "MMLU": 64.68, + "TruthfulQA": 68.39, + "Winogrande": 84.06, + "GSM8K": 70.58, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "7a447745915fb8ede249d92a7b5f271409056ce2", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "SC99\/Mistral-7B-privatemix-ia3", + "Average \u2b06\ufe0f": 74.94, + "ARC": 73.38, + "HellaSwag": 88.69, + "MMLU": 64.14, + "TruthfulQA": 70.13, + "Winogrande": 86.66, + "GSM8K": 66.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ab0c1d60a77c2156b3b788984882a666bd6e1cfa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "leveldevai\/TurdusDareBeagle-7B", + "Average \u2b06\ufe0f": 74.94, + "ARC": 72.7, + "HellaSwag": 88.45, + "MMLU": 64.87, + "TruthfulQA": 68.9, + "Winogrande": 83.98, + "GSM8K": 70.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1ffd5776337bdf6fae0b12645112e981a6bfa914", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/TheTop-5x7B-Instruct-S4-v0.1", + "Average \u2b06\ufe0f": 74.94, + "ARC": 72.18, + "HellaSwag": 88.29, + "MMLU": 65.03, + "TruthfulQA": 65.56, + "Winogrande": 85.16, + "GSM8K": 73.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "187fbdd40f13d8e1b39982984ab9ef8ed7bff97b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "NLPinas\/yi-bagel-2x34b", + "Average \u2b06\ufe0f": 74.93, + "ARC": 72.7, + "HellaSwag": 85.44, + "MMLU": 76.6, + "TruthfulQA": 71.42, + "Winogrande": 82.72, + "GSM8K": 60.73, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ce6765e4a2a1f5914969c9fe48e2d1e8f3e3a247", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NLPinas\/yi-bagel-2x34b-moe", + "Average \u2b06\ufe0f": 74.93, + "ARC": 72.7, + "HellaSwag": 85.44, + "MMLU": 76.6, + "TruthfulQA": 71.42, + "Winogrande": 82.72, + "GSM8K": 60.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a6de6f3ccb21eeef12a354c720a9a85e5e53433d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "SC99\/Mistral-7B-privatemix-ia2", + "Average \u2b06\ufe0f": 74.92, + "ARC": 72.27, + "HellaSwag": 88.59, + "MMLU": 64.53, + "TruthfulQA": 71.33, + "Winogrande": 83.9, + "GSM8K": 68.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7c9dada69222c0bc0366422b848ca4f74f8a0fdb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nfaheem\/Marcoroni-7b-DPO-Merge", + "Average \u2b06\ufe0f": 74.9, + "ARC": 73.04, + "HellaSwag": 88.8, + "MMLU": 64.24, + "TruthfulQA": 70.47, + "Winogrande": 85.24, + "GSM8K": 67.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e3085d8aacffbf46b95e263bde509fce70577a26", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC44\/Mistral-7B-private-sia", + "Average \u2b06\ufe0f": 74.89, + "ARC": 72.53, + "HellaSwag": 89.08, + "MMLU": 64.45, + "TruthfulQA": 72.44, + "Winogrande": 84.14, + "GSM8K": 66.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "213b8ab1da8a0de0183f2fd177e95a34bc157b1c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051612\/A0126", + "Average \u2b06\ufe0f": 74.87, + "ARC": 70.39, + "HellaSwag": 85.87, + "MMLU": 84.03, + "TruthfulQA": 61.53, + "Winogrande": 81.53, + "GSM8K": 65.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c0c062b6fe4202b7aa5510bfda390da2e8b393ef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "quantumaikr\/quantum-dpo-v0.1", + "Average \u2b06\ufe0f": 74.87, + "ARC": 72.53, + "HellaSwag": 88.37, + "MMLU": 65.29, + "TruthfulQA": 69.92, + "Winogrande": 82.32, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "09cbfe6569bcdddf623e9990498e9ad07345ad6a", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "flemmingmiguel\/MDBX-7B", + "Average \u2b06\ufe0f": 74.86, + "ARC": 72.01, + "HellaSwag": 88.31, + "MMLU": 64.97, + "TruthfulQA": 68.19, + "Winogrande": 83.5, + "GSM8K": 72.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "668b959981253f45ba25e6cb21289e136844f859", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CultriX\/MergeTrix-7B-v2", + "Average \u2b06\ufe0f": 74.85, + "ARC": 72.7, + "HellaSwag": 88.48, + "MMLU": 64.89, + "TruthfulQA": 67.17, + "Winogrande": 86.74, + "GSM8K": 69.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fabb95cdb3ed48cc58ab6fdc2b460640022665f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "vanillaOVO\/supermario_v1", + "Average \u2b06\ufe0f": 74.85, + "ARC": 73.72, + "HellaSwag": 88.71, + "MMLU": 64.57, + "TruthfulQA": 68.23, + "Winogrande": 85.64, + "GSM8K": 68.23, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2329946fcdd20174c997dcd8feb8f45bedc52675", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BarryFutureman\/NeuralTurdusVariant1-7B", + "Average \u2b06\ufe0f": 74.83, + "ARC": 73.12, + "HellaSwag": 88.61, + "MMLU": 64.75, + "TruthfulQA": 69.99, + "Winogrande": 85.16, + "GSM8K": 67.32, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "90bd7c1e38eef96488aa7fb19549f1cb53d1c696", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jsfs11\/MixtureofMerges-MoE-v2", + "Average \u2b06\ufe0f": 74.82, + "ARC": 72.44, + "HellaSwag": 88.41, + "MMLU": 64.88, + "TruthfulQA": 70.92, + "Winogrande": 83.58, + "GSM8K": 68.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "689f0901cfe49bd2b87c793997d24b77371891e9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnwMe\/Mistral-7b-instruct-v0.2-private-eds2", + "Average \u2b06\ufe0f": 74.82, + "ARC": 73.12, + "HellaSwag": 89.23, + "MMLU": 64.11, + "TruthfulQA": 72.25, + "Winogrande": 84.69, + "GSM8K": 65.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d4cffeadbb02eaf6273e954fc5aea4f745747705", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BarryFutureman\/WildWest-Variant3-7B", + "Average \u2b06\ufe0f": 74.81, + "ARC": 73.21, + "HellaSwag": 88.37, + "MMLU": 64.76, + "TruthfulQA": 68.09, + "Winogrande": 84.37, + "GSM8K": 70.05, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "58b9421546f15564f6a918ebeb9627979dfdb50b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abhishekchohan\/SOLAR-10.7B-Instruct-Forest-DPO-v1", + "Average \u2b06\ufe0f": 74.8, + "ARC": 71.93, + "HellaSwag": 88.44, + "MMLU": 65.63, + "TruthfulQA": 76.13, + "Winogrande": 82.16, + "GSM8K": 64.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "543b52f9b6c96a4922dc8ed1251625b1bd919e19", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abacusai\/MetaMath-Bagel-DPO-34B", + "Average \u2b06\ufe0f": 74.8, + "ARC": 68.17, + "HellaSwag": 84.23, + "MMLU": 76.54, + "TruthfulQA": 65.44, + "Winogrande": 82.24, + "GSM8K": 72.18, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "0c670c988b61240e5f89ae9df0820db7dc572576", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jan-hq\/trinity-v1", + "Average \u2b06\ufe0f": 74.8, + "ARC": 72.27, + "HellaSwag": 88.36, + "MMLU": 65.2, + "TruthfulQA": 69.31, + "Winogrande": 82.0, + "GSM8K": 71.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "34974ae99668c381be0871778e3c42958544f70e", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "janai-hq\/trinity-v1", + "Average \u2b06\ufe0f": 74.8, + "ARC": 72.27, + "HellaSwag": 88.36, + "MMLU": 65.2, + "TruthfulQA": 69.31, + "Winogrande": 82.0, + "GSM8K": 71.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "09da1a24f84c96b8c09f2c07038986e28cc24ad5", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "222gate\/Blurred-Beagle-7b-slerp", + "Average \u2b06\ufe0f": 74.8, + "ARC": 72.78, + "HellaSwag": 88.58, + "MMLU": 64.95, + "TruthfulQA": 69.39, + "Winogrande": 83.19, + "GSM8K": 69.9, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3e328ce1ef2b1216d7e3d03a7585531c6b1b9630", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_11-7B-slerp", + "Average \u2b06\ufe0f": 74.8, + "ARC": 72.53, + "HellaSwag": 88.2, + "MMLU": 65.04, + "TruthfulQA": 69.81, + "Winogrande": 82.32, + "GSM8K": 70.89, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f8f4ff2812125da6e7654a7afc28c547e087e268", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/WestLake-7B-v2-laser", + "Average \u2b06\ufe0f": 74.78, + "ARC": 73.29, + "HellaSwag": 88.66, + "MMLU": 64.72, + "TruthfulQA": 67.04, + "Winogrande": 86.74, + "GSM8K": 68.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 30.0, + "Available on the hub": true, + "Model sha": "c3227c2b48ac6b136c074871b72088677f2adca9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rizla\/raccoon-small", + "Average \u2b06\ufe0f": 74.78, + "ARC": 74.4, + "HellaSwag": 88.73, + "MMLU": 64.55, + "TruthfulQA": 76.74, + "Winogrande": 87.37, + "GSM8K": 56.86, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "79d748d0646f11bd18a8d785000c63279a9a5cde", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_10-7B-slerp", + "Average \u2b06\ufe0f": 74.77, + "ARC": 72.35, + "HellaSwag": 88.3, + "MMLU": 64.87, + "TruthfulQA": 69.49, + "Winogrande": 83.5, + "GSM8K": 70.13, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "60a299cdcaa10a275cc79b52598b096cf1a2ad2e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Vasanth\/Beast-Soul-new", + "Average \u2b06\ufe0f": 74.76, + "ARC": 73.12, + "HellaSwag": 88.35, + "MMLU": 64.74, + "TruthfulQA": 67.38, + "Winogrande": 85.24, + "GSM8K": 69.75, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d4a6d05f84f82b0a6ad625dd2473115ca972c1db", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/Beagle14-7B", + "Average \u2b06\ufe0f": 74.76, + "ARC": 72.95, + "HellaSwag": 87.95, + "MMLU": 64.7, + "TruthfulQA": 68.88, + "Winogrande": 82.64, + "GSM8K": 71.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "a5d1b1f831efe38df3b6ac125764a87ed094e282", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alnrg2arg\/test2_3", + "Average \u2b06\ufe0f": 74.76, + "ARC": 72.95, + "HellaSwag": 88.42, + "MMLU": 64.8, + "TruthfulQA": 68.4, + "Winogrande": 84.14, + "GSM8K": 69.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e2c681fa4680ee19ca9758a2289da7d168546672", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "leveldevai\/MarcDareBeagle-7B", + "Average \u2b06\ufe0f": 74.75, + "ARC": 72.1, + "HellaSwag": 88.33, + "MMLU": 65.03, + "TruthfulQA": 68.09, + "Winogrande": 83.19, + "GSM8K": 71.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1c7d1421fad812bfcef4d3374f28bbca83e63ca6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GreenNode\/GreenNodeLM-v3olet-7B", + "Average \u2b06\ufe0f": 74.75, + "ARC": 72.27, + "HellaSwag": 88.25, + "MMLU": 65.27, + "TruthfulQA": 69.52, + "Winogrande": 82.48, + "GSM8K": 70.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "94b36a4573657d7815f55b917b204e6b73f7a634", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/60B_MoE_Coder_v3", + "Average \u2b06\ufe0f": 74.75, + "ARC": 71.16, + "HellaSwag": 85.44, + "MMLU": 75.37, + "TruthfulQA": 67.01, + "Winogrande": 82.56, + "GSM8K": 66.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ccd128942c5a6bb1672ceed21730d0e172655d77", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ignos\/LeoScorpius-GreenNode-Alpaca-7B-v1", + "Average \u2b06\ufe0f": 74.74, + "ARC": 72.35, + "HellaSwag": 88.16, + "MMLU": 65.23, + "TruthfulQA": 69.35, + "Winogrande": 82.32, + "GSM8K": 71.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "00827d42d79b7e10ddfc92c800cbb0636704e379", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mlabonne\/NeuralBeagle14-7B", + "Average \u2b06\ufe0f": 74.74, + "ARC": 72.95, + "HellaSwag": 88.34, + "MMLU": 64.55, + "TruthfulQA": 69.93, + "Winogrande": 82.4, + "GSM8K": 70.28, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 141.0, + "Available on the hub": true, + "Model sha": "33f76dd61715c8fd89f138092a8e8c7f3b3dd905", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BarryFutureman\/NeuralLake-Variant1-7B", + "Average \u2b06\ufe0f": 74.73, + "ARC": 73.12, + "HellaSwag": 88.45, + "MMLU": 64.67, + "TruthfulQA": 68.37, + "Winogrande": 84.45, + "GSM8K": 69.29, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1a243c41d78eae644a0246ce7eb3bef68c10fecf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "kaitchup\/Mayonnaise-4in1-03", + "Average \u2b06\ufe0f": 74.73, + "ARC": 72.95, + "HellaSwag": 88.29, + "MMLU": 64.76, + "TruthfulQA": 68.79, + "Winogrande": 83.58, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3cc3f5e623c2451e040e0d3e137d4f2212708936", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/aegolius-acadicus-v1-30b", + "Average \u2b06\ufe0f": 74.7, + "ARC": 72.61, + "HellaSwag": 87.99, + "MMLU": 65.11, + "TruthfulQA": 67.06, + "Winogrande": 84.85, + "GSM8K": 70.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 29.79, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fecd580eb4294525160e86b79d0f205a3a44e172", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/aegolius-acadicus-30b", + "Average \u2b06\ufe0f": 74.7, + "ARC": 72.61, + "HellaSwag": 88.01, + "MMLU": 65.07, + "TruthfulQA": 67.07, + "Winogrande": 84.93, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 29.79, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1260e0b4085ce8f6fbbe41192c5932d084706be4", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/nontoxic-bagel-34b-v0.2", + "Average \u2b06\ufe0f": 74.69, + "ARC": 72.44, + "HellaSwag": 85.64, + "MMLU": 76.41, + "TruthfulQA": 72.7, + "Winogrande": 82.48, + "GSM8K": 58.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 34.0, + "Available on the hub": true, + "Model sha": "08903c93d929829aabbde2681c7ad2465d7d4189", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/bagel-dpo-34b-v0.2", + "Average \u2b06\ufe0f": 74.69, + "ARC": 71.93, + "HellaSwag": 85.25, + "MMLU": 76.58, + "TruthfulQA": 70.05, + "Winogrande": 83.35, + "GSM8K": 60.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 81.0, + "Available on the hub": true, + "Model sha": "fcc6ada5ea6dbf2f644d26b545ac402d2202cc74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "quantumaikr\/quantum-v0.01", + "Average \u2b06\ufe0f": 74.68, + "ARC": 72.53, + "HellaSwag": 88.27, + "MMLU": 65.2, + "TruthfulQA": 69.28, + "Winogrande": 82.56, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "141a76559dace99bea213922c91cd23be8783c72", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "senseable\/WestLake-7B-v2", + "Average \u2b06\ufe0f": 74.68, + "ARC": 73.04, + "HellaSwag": 88.65, + "MMLU": 64.71, + "TruthfulQA": 67.06, + "Winogrande": 86.98, + "GSM8K": 67.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 63.0, + "Available on the hub": true, + "Model sha": "6df7bb2069432bcab0971ab105284a66b3ec1ce0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "quantumaikr\/quantum-trinity-v0.1", + "Average \u2b06\ufe0f": 74.67, + "ARC": 72.53, + "HellaSwag": 88.28, + "MMLU": 65.19, + "TruthfulQA": 69.28, + "Winogrande": 82.56, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4e3eb8c21ff1689a348cc9ffdacd675aff3dde2b", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "moreh\/MoMo-70B-LoRA-V1.4", + "Average \u2b06\ufe0f": 74.67, + "ARC": 69.2, + "HellaSwag": 85.07, + "MMLU": 77.12, + "TruthfulQA": 62.66, + "Winogrande": 83.74, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "66bf25995056155b5d0796f7c0981e243bdd48f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "moreh\/MoMo-72B-LoRA-V1.4", + "Average \u2b06\ufe0f": 74.67, + "ARC": 69.2, + "HellaSwag": 85.07, + "MMLU": 77.12, + "TruthfulQA": 62.66, + "Winogrande": 83.74, + "GSM8K": 70.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 84.0, + "Available on the hub": true, + "Model sha": "66bf25995056155b5d0796f7c0981e243bdd48f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Manolo26\/metis-chat-instruct-7b", + "Average \u2b06\ufe0f": 74.66, + "ARC": 72.87, + "HellaSwag": 88.17, + "MMLU": 64.92, + "TruthfulQA": 69.44, + "Winogrande": 81.85, + "GSM8K": 70.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "23ea322a123211879153f48d61ff906cd6398bcc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ycros\/BagelMIsteryTour-8x7B", + "Average \u2b06\ufe0f": 74.66, + "ARC": 72.44, + "HellaSwag": 87.5, + "MMLU": 71.25, + "TruthfulQA": 74.95, + "Winogrande": 82.0, + "GSM8K": 59.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "e210ea8194895c3429657556b41daaf722fd44a4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "louisbrulenaudet\/Pearl-7B-0210-ties", + "Average \u2b06\ufe0f": 74.66, + "ARC": 71.08, + "HellaSwag": 88.63, + "MMLU": 63.81, + "TruthfulQA": 70.47, + "Winogrande": 83.98, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d18d0fe9d70b8a2f4e2af33b6e771c8edef6ff97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BarryFutureman\/WildMarcoroni-Variant3-7B", + "Average \u2b06\ufe0f": 74.66, + "ARC": 72.27, + "HellaSwag": 88.96, + "MMLU": 64.38, + "TruthfulQA": 71.68, + "Winogrande": 84.53, + "GSM8K": 66.11, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "77ec3ea64cb134ae694dd72606235ef497cf46d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "udkai\/Turdus", + "Average \u2b06\ufe0f": 74.66, + "ARC": 73.38, + "HellaSwag": 88.56, + "MMLU": 64.52, + "TruthfulQA": 67.11, + "Winogrande": 86.66, + "GSM8K": 67.7, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "de8a9fbacf60f07146d7bda3455d3748e12200de", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kevin009\/llamaRAGdrama", + "Average \u2b06\ufe0f": 74.65, + "ARC": 72.01, + "HellaSwag": 88.83, + "MMLU": 64.5, + "TruthfulQA": 70.24, + "Winogrande": 86.66, + "GSM8K": 65.66, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f1d27aab09086a6e691db6892d50ba809cbe0607", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/Mixtral-7Bx2-truthy", + "Average \u2b06\ufe0f": 74.64, + "ARC": 72.18, + "HellaSwag": 87.88, + "MMLU": 65.2, + "TruthfulQA": 74.68, + "Winogrande": 80.66, + "GSM8K": 67.25, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4bfad083e96a4ab129cc202fc941994be2e3adc4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vicgalle\/CarbonBeagle-11B", + "Average \u2b06\ufe0f": 74.64, + "ARC": 71.84, + "HellaSwag": 88.93, + "MMLU": 66.62, + "TruthfulQA": 69.43, + "Winogrande": 84.06, + "GSM8K": 66.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "d774c746ac8f9df026d106f2466dbeeae3a49337", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "moreh\/MoMo-72B-LoRA-V1.4", + "Average \u2b06\ufe0f": 74.64, + "ARC": 69.11, + "HellaSwag": 85.0, + "MMLU": 77.26, + "TruthfulQA": 62.71, + "Winogrande": 83.74, + "GSM8K": 69.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 84.0, + "Available on the hub": true, + "Model sha": "e5dd511955f4ac65bb1884f07426157740ad8574", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC44\/Mistral-7B-private-oia", + "Average \u2b06\ufe0f": 74.63, + "ARC": 72.78, + "HellaSwag": 89.24, + "MMLU": 64.26, + "TruthfulQA": 73.15, + "Winogrande": 83.74, + "GSM8K": 64.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "602744dea3ddc2c1b33a6a67718dc594be3e4694", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/O0128", + "Average \u2b06\ufe0f": 74.61, + "ARC": 67.92, + "HellaSwag": 85.34, + "MMLU": 83.59, + "TruthfulQA": 60.13, + "Winogrande": 82.24, + "GSM8K": 68.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d5cc987f61f58763eb2d02a06ddd103992d9a3dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andrijdavid\/macaroni-7b", + "Average \u2b06\ufe0f": 74.6, + "ARC": 73.12, + "HellaSwag": 88.17, + "MMLU": 64.58, + "TruthfulQA": 68.76, + "Winogrande": 84.37, + "GSM8K": 68.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e1c0fe26554eb627aed9569f106e838f0333850f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/NeuralDareBeagle-7B-slerp", + "Average \u2b06\ufe0f": 74.6, + "ARC": 72.1, + "HellaSwag": 88.2, + "MMLU": 64.99, + "TruthfulQA": 69.18, + "Winogrande": 82.56, + "GSM8K": 70.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "04c39204799094776e57195cd107f0fe92bf86bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shadowml\/DareBeagle-7B", + "Average \u2b06\ufe0f": 74.58, + "ARC": 71.67, + "HellaSwag": 88.01, + "MMLU": 65.03, + "TruthfulQA": 68.98, + "Winogrande": 82.32, + "GSM8K": 71.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7d5cb3c9ef547ad297d64789b188415e0320237a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_3-7B-slerp", + "Average \u2b06\ufe0f": 74.57, + "ARC": 70.82, + "HellaSwag": 87.79, + "MMLU": 65.12, + "TruthfulQA": 68.86, + "Winogrande": 82.56, + "GSM8K": 72.25, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4adb83489d7321003e942ee60d835f8346f42951", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/iWillChangeTheNameLater", + "Average \u2b06\ufe0f": 74.56, + "ARC": 72.01, + "HellaSwag": 88.23, + "MMLU": 64.97, + "TruthfulQA": 69.41, + "Winogrande": 84.21, + "GSM8K": 68.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f997d63d5fdcf5aa69ec7ceedfc2a5c2572a14ef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jefferylovely\/ThetaMaven5", + "Average \u2b06\ufe0f": 74.56, + "ARC": 72.01, + "HellaSwag": 88.38, + "MMLU": 64.77, + "TruthfulQA": 69.67, + "Winogrande": 82.64, + "GSM8K": 69.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a344b7d30e8d4afc55b1326f5fb71ca03a76b7a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/TheTop-5x7B-Instruct-D-v0.1", + "Average \u2b06\ufe0f": 74.54, + "ARC": 71.76, + "HellaSwag": 88.21, + "MMLU": 64.86, + "TruthfulQA": 66.32, + "Winogrande": 84.37, + "GSM8K": 71.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d7a439cbd47cb966778bf35e3e8efde20d5cfe7f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/Prokaryote-8x7B-bf16", + "Average \u2b06\ufe0f": 74.53, + "ARC": 73.72, + "HellaSwag": 88.18, + "MMLU": 64.97, + "TruthfulQA": 67.79, + "Winogrande": 83.03, + "GSM8K": 69.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "20496cb52b98e33cf4442c14cf464fcf7c4b27c1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "ConvexAI\/BurningBruce-005", + "Average \u2b06\ufe0f": 74.53, + "ARC": 72.01, + "HellaSwag": 88.31, + "MMLU": 64.76, + "TruthfulQA": 67.27, + "Winogrande": 83.35, + "GSM8K": 71.49, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "e61d2cc6475548244b9ab180e508246e3e577b66", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "mncai\/mistral-7b-dpo-merge-v1.1", + "Average \u2b06\ufe0f": 74.53, + "ARC": 72.53, + "HellaSwag": 88.15, + "MMLU": 64.83, + "TruthfulQA": 68.48, + "Winogrande": 82.32, + "GSM8K": 70.89, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7fc6c09477cc606e91025c38b9963bc47dd396da", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jsfs11\/WestOrcaNeural-V2-DARETIES-7B", + "Average \u2b06\ufe0f": 74.53, + "ARC": 72.1, + "HellaSwag": 88.21, + "MMLU": 64.64, + "TruthfulQA": 67.81, + "Winogrande": 83.74, + "GSM8K": 70.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cd28876def531a2db88f123782d39e91fec0317b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jeonsworld\/CarbonVillain-en-10.7B-v4", + "Average \u2b06\ufe0f": 74.52, + "ARC": 71.25, + "HellaSwag": 88.48, + "MMLU": 66.27, + "TruthfulQA": 71.95, + "Winogrande": 83.58, + "GSM8K": 65.58, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "904ffe8106a3facbea0d0e61d9a53a525675871e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rwitz2\/go-bruins-v2.1", + "Average \u2b06\ufe0f": 74.5, + "ARC": 71.93, + "HellaSwag": 88.33, + "MMLU": 65.0, + "TruthfulQA": 69.16, + "Winogrande": 82.16, + "GSM8K": 70.43, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1e785d545369d201262bcc740ff127bb120d7a6b", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/bagel-dpo-34b-v0.2", + "Average \u2b06\ufe0f": 74.5, + "ARC": 72.01, + "HellaSwag": 85.24, + "MMLU": 76.58, + "TruthfulQA": 70.16, + "Winogrande": 83.03, + "GSM8K": 59.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 81.0, + "Available on the hub": true, + "Model sha": "fcc6ada5ea6dbf2f644d26b545ac402d2202cc74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mncai\/mistral-7b-dpo-v6", + "Average \u2b06\ufe0f": 74.5, + "ARC": 72.53, + "HellaSwag": 88.1, + "MMLU": 64.68, + "TruthfulQA": 68.24, + "Winogrande": 82.56, + "GSM8K": 70.89, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "206be3fd589dd62817343c53525ab7fb1b752faf", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "RatanRohith\/NeuralPizza-WestSeverus-7B-Merge-slerp", + "Average \u2b06\ufe0f": 74.5, + "ARC": 71.42, + "HellaSwag": 88.25, + "MMLU": 64.74, + "TruthfulQA": 70.4, + "Winogrande": 83.11, + "GSM8K": 69.07, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1b1e5870d1f08eb09c9891d1737a105cdb5aa52c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "logicker\/SkkuDataScienceGlobal-10.7b", + "Average \u2b06\ufe0f": 74.5, + "ARC": 71.25, + "HellaSwag": 88.41, + "MMLU": 66.31, + "TruthfulQA": 71.92, + "Winogrande": 83.35, + "GSM8K": 65.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4f5e40b38099084b86fb18b294e4e61e7d20cc7c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shadowml\/DareBeagel-2x7B", + "Average \u2b06\ufe0f": 74.49, + "ARC": 72.01, + "HellaSwag": 88.12, + "MMLU": 64.51, + "TruthfulQA": 69.09, + "Winogrande": 82.72, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5cecd5e1f9723e3f7d287cbc9fd6d42056f73405", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "senseable\/Westlake-7B", + "Average \u2b06\ufe0f": 74.48, + "ARC": 73.21, + "HellaSwag": 88.49, + "MMLU": 64.64, + "TruthfulQA": 67.36, + "Winogrande": 86.03, + "GSM8K": 67.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "645fa936256811f53f0c33f1e5298f6ad1095dce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rizla\/trrapi-16b", + "Average \u2b06\ufe0f": 74.48, + "ARC": 72.1, + "HellaSwag": 88.88, + "MMLU": 64.26, + "TruthfulQA": 74.13, + "Winogrande": 86.35, + "GSM8K": 61.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 18.79, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "96b27c4205881920289b29ac3d83ba5edf5cf672", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abacusai\/MM-OV-bagel-DPO-34b-c1000-250", + "Average \u2b06\ufe0f": 74.47, + "ARC": 68.17, + "HellaSwag": 83.97, + "MMLU": 76.33, + "TruthfulQA": 63.67, + "Winogrande": 82.4, + "GSM8K": 72.25, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1d697d32ba4f6ed471cd2857669029f425b827bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "paulml\/NeuralOmniWestBeaglake-7B", + "Average \u2b06\ufe0f": 74.43, + "ARC": 73.72, + "HellaSwag": 89.69, + "MMLU": 63.96, + "TruthfulQA": 75.1, + "Winogrande": 84.93, + "GSM8K": 59.21, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b02cba26616d558094f7dca72419367c56937a47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FusionNet_linear", + "Average \u2b06\ufe0f": 74.43, + "ARC": 71.25, + "HellaSwag": 88.44, + "MMLU": 66.35, + "TruthfulQA": 71.94, + "Winogrande": 83.27, + "GSM8K": 65.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "a6eba075d53fc4bdbcded071f9bdeb287d1ac260", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "gagan3012\/MetaModel_moe", + "Average \u2b06\ufe0f": 74.42, + "ARC": 71.25, + "HellaSwag": 88.4, + "MMLU": 66.26, + "TruthfulQA": 71.86, + "Winogrande": 83.35, + "GSM8K": 65.43, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "015dae67b68e6e5007b7b13a448886eb5f6bfea8", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "jeonsworld\/CarbonVillain-en-10.7B-v2", + "Average \u2b06\ufe0f": 74.42, + "ARC": 71.25, + "HellaSwag": 88.4, + "MMLU": 66.31, + "TruthfulQA": 71.94, + "Winogrande": 83.35, + "GSM8K": 65.28, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "70b507c12dfe6ce8a7d050be5475fc9684a4929f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nbeerbower\/bruphin-epsilon", + "Average \u2b06\ufe0f": 74.42, + "ARC": 72.1, + "HellaSwag": 88.09, + "MMLU": 65.04, + "TruthfulQA": 66.95, + "Winogrande": 83.82, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "75d6c2cee8666b9f25631a796f35563147264045", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DopeorNope\/SOLARC-M-10.7B", + "Average \u2b06\ufe0f": 74.42, + "ARC": 71.16, + "HellaSwag": 88.41, + "MMLU": 66.31, + "TruthfulQA": 71.85, + "Winogrande": 83.35, + "GSM8K": 65.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "fa95c376fdad1670d4125e833322dbf6aeb8f410", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cloudyu\/Mixtral_11Bx2_MoE_19B", + "Average \u2b06\ufe0f": 74.41, + "ARC": 71.16, + "HellaSwag": 88.47, + "MMLU": 66.31, + "TruthfulQA": 72.0, + "Winogrande": 83.27, + "GSM8K": 65.28, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": true, + "Model sha": "092208b5bfab866b301545149a6b14fde48a0dd6", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "kekmodel\/StopCarbon-10.7B-v5", + "Average \u2b06\ufe0f": 74.41, + "ARC": 70.99, + "HellaSwag": 88.48, + "MMLU": 66.34, + "TruthfulQA": 71.84, + "Winogrande": 83.58, + "GSM8K": 65.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "57966bc616a9db7756488661f4ed16b40ee23780", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jeonsworld\/CarbonVillain-en-10.7B-v3", + "Average \u2b06\ufe0f": 74.41, + "ARC": 70.99, + "HellaSwag": 88.48, + "MMLU": 66.34, + "TruthfulQA": 71.84, + "Winogrande": 83.58, + "GSM8K": 65.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "285436a72c10e0f2b8eb897549350fe40c2e8bbe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gagan3012\/MetaModel", + "Average \u2b06\ufe0f": 74.4, + "ARC": 71.08, + "HellaSwag": 88.45, + "MMLU": 66.26, + "TruthfulQA": 71.84, + "Winogrande": 83.43, + "GSM8K": 65.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06308e54585a49a01a93c99caa2fb34daf4e7619", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kyujinpy\/Sakura-SOLAR-Instruct", + "Average \u2b06\ufe0f": 74.4, + "ARC": 70.99, + "HellaSwag": 88.42, + "MMLU": 66.33, + "TruthfulQA": 71.79, + "Winogrande": 83.66, + "GSM8K": 65.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "cc4531a25fff7cbb146c0e12f2cf4e19189c37a2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Xenon1\/MetaModel_moex8", + "Average \u2b06\ufe0f": 74.39, + "ARC": 71.16, + "HellaSwag": 88.38, + "MMLU": 66.29, + "TruthfulQA": 71.91, + "Winogrande": 83.27, + "GSM8K": 65.35, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 69.92, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "333524a8c6ed8415fd48f852e53c405cac82733d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "gagan3012\/MetaModelv3", + "Average \u2b06\ufe0f": 74.39, + "ARC": 71.16, + "HellaSwag": 88.39, + "MMLU": 66.32, + "TruthfulQA": 71.86, + "Winogrande": 83.35, + "GSM8K": 65.28, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "862f5ca5e66a0b053c14e40c8f16f2c2807b6d92", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FusionNet", + "Average \u2b06\ufe0f": 74.38, + "ARC": 71.25, + "HellaSwag": 88.42, + "MMLU": 66.36, + "TruthfulQA": 71.95, + "Winogrande": 83.27, + "GSM8K": 65.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "34421f146e5eb3306a86dd8b67ec938e800ee52e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Vasanth\/Beast-Soul", + "Average \u2b06\ufe0f": 74.37, + "ARC": 72.53, + "HellaSwag": 88.15, + "MMLU": 64.76, + "TruthfulQA": 66.76, + "Winogrande": 83.43, + "GSM8K": 70.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "700aacf29bde13dfef2a5f15c5a5d6627c73d80d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarryFutureman\/WestLakeX-7B-EvoMerge", + "Average \u2b06\ufe0f": 74.37, + "ARC": 71.42, + "HellaSwag": 88.08, + "MMLU": 64.84, + "TruthfulQA": 67.5, + "Winogrande": 84.77, + "GSM8K": 69.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6bf661cdade79d96c4def4f09c27ad5ca1bae11a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "flemmingmiguel\/DareBeagle-7B", + "Average \u2b06\ufe0f": 74.35, + "ARC": 71.59, + "HellaSwag": 87.98, + "MMLU": 65.21, + "TruthfulQA": 68.3, + "Winogrande": 81.93, + "GSM8K": 71.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "53e5b634de4ae9ef8a127c1d7a0c543acfba1b47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "222gate\/Blurdus-7b-v0.1", + "Average \u2b06\ufe0f": 74.35, + "ARC": 72.27, + "HellaSwag": 88.5, + "MMLU": 64.82, + "TruthfulQA": 69.72, + "Winogrande": 82.95, + "GSM8K": 67.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "339e5802231bda900d71d8d04db88021d1dd8903", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ConvexAI\/Solutus-3x7B", + "Average \u2b06\ufe0f": 74.35, + "ARC": 72.01, + "HellaSwag": 88.31, + "MMLU": 64.77, + "TruthfulQA": 67.52, + "Winogrande": 83.66, + "GSM8K": 69.83, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "7c604d7adedd864f6ff3db10500a499e5dd8f8ff", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "kodonho\/Solar-OrcaDPO-Solar-Instruct-SLERP", + "Average \u2b06\ufe0f": 74.35, + "ARC": 70.99, + "HellaSwag": 88.22, + "MMLU": 66.22, + "TruthfulQA": 71.95, + "Winogrande": 83.43, + "GSM8K": 65.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ea7a7a1c14c4b67bad56dbd08245dbb79dc71ec3", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DopeorNope\/SOLARC-MOE-10.7Bx6", + "Average \u2b06\ufe0f": 74.35, + "ARC": 70.9, + "HellaSwag": 88.4, + "MMLU": 66.36, + "TruthfulQA": 71.85, + "Winogrande": 83.66, + "GSM8K": 64.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 53.01, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "64c8ef9fa6d9b54b68261d839b656b0dc8717374", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "CultriX\/MergeTrix-7B", + "Average \u2b06\ufe0f": 74.33, + "ARC": 72.27, + "HellaSwag": 87.84, + "MMLU": 64.88, + "TruthfulQA": 66.27, + "Winogrande": 83.5, + "GSM8K": 71.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "d11bd6b388581d2a44c1431a9985e8fc77addd33", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "invalid-coder\/SOLAR-10.7B-Instruct-SOLARC-M-10.7B-slerp", + "Average \u2b06\ufe0f": 74.32, + "ARC": 71.08, + "HellaSwag": 88.34, + "MMLU": 66.29, + "TruthfulQA": 71.73, + "Winogrande": 83.74, + "GSM8K": 64.75, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "656f2be86e3f30067e62e61cedf78b0697ce0a97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kekmodel\/StopCarbon-10.7B-v6", + "Average \u2b06\ufe0f": 74.31, + "ARC": 71.16, + "HellaSwag": 88.5, + "MMLU": 66.31, + "TruthfulQA": 71.96, + "Winogrande": 83.43, + "GSM8K": 64.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8953a705c909ef98fe3b0ea524c5816a57f1954c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jeonsworld\/CarbonVillain-en-10.7B-v5", + "Average \u2b06\ufe0f": 74.31, + "ARC": 71.16, + "HellaSwag": 88.51, + "MMLU": 66.44, + "TruthfulQA": 71.97, + "Winogrande": 83.35, + "GSM8K": 64.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "941b5a690781dd412eb435446b65e92048992abe", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yunconglong\/Truthful_DPO_MOE_19B", + "Average \u2b06\ufe0f": 74.3, + "ARC": 71.08, + "HellaSwag": 88.46, + "MMLU": 66.13, + "TruthfulQA": 72.29, + "Winogrande": 83.35, + "GSM8K": 64.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "de574b57d45cfea00748c464af17f1c1ca53e548", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/BurningBruce-003", + "Average \u2b06\ufe0f": 74.3, + "ARC": 71.25, + "HellaSwag": 88.22, + "MMLU": 64.48, + "TruthfulQA": 66.39, + "Winogrande": 83.19, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "bbcf8079aa4a50393036e53b89f4f4fb20afbd1f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "222gate\/Blur-4x7b-MOE-v0.1", + "Average \u2b06\ufe0f": 74.29, + "ARC": 72.27, + "HellaSwag": 88.14, + "MMLU": 65.05, + "TruthfulQA": 68.82, + "Winogrande": 82.56, + "GSM8K": 68.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1690def0c82469870a8b0b649eea948f8940151b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "kodonho\/SolarM-SakuraSolar-SLERP", + "Average \u2b06\ufe0f": 74.29, + "ARC": 71.16, + "HellaSwag": 88.47, + "MMLU": 66.24, + "TruthfulQA": 72.1, + "Winogrande": 83.11, + "GSM8K": 64.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c54dbc0da9e028cfaf92114206c6b84c0198d2b0", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kekmodel\/StopCarbon-10.7B-v4", + "Average \u2b06\ufe0f": 74.29, + "ARC": 71.25, + "HellaSwag": 88.5, + "MMLU": 66.24, + "TruthfulQA": 71.89, + "Winogrande": 83.43, + "GSM8K": 64.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c8d98bb8c6b23b3c3b7462df7eb02a3b05622612", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "gagan3012\/MetaModel_moe", + "Average \u2b06\ufe0f": 74.28, + "ARC": 71.08, + "HellaSwag": 88.39, + "MMLU": 66.31, + "TruthfulQA": 71.82, + "Winogrande": 83.5, + "GSM8K": 64.59, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "015dae67b68e6e5007b7b13a448886eb5f6bfea8", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "jeonsworld\/CarbonVillain-en-13B-v1", + "Average \u2b06\ufe0f": 74.28, + "ARC": 71.25, + "HellaSwag": 88.46, + "MMLU": 66.42, + "TruthfulQA": 71.98, + "Winogrande": 83.27, + "GSM8K": 64.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a797e7e81f7929a31ca232858318d72b93b6abe0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jeonsworld\/CarbonVillain-en-10.7B-v1", + "Average \u2b06\ufe0f": 74.28, + "ARC": 71.25, + "HellaSwag": 88.46, + "MMLU": 66.42, + "TruthfulQA": 71.98, + "Winogrande": 83.27, + "GSM8K": 64.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "a797e7e81f7929a31ca232858318d72b93b6abe0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Patronum-7B", + "Average \u2b06\ufe0f": 74.27, + "ARC": 71.67, + "HellaSwag": 88.33, + "MMLU": 64.84, + "TruthfulQA": 70.41, + "Winogrande": 81.85, + "GSM8K": 68.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "78da696445e50002d29bf5610af059fd3f00f51b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DopeorNope\/SOLARC-MOE-10.7Bx4", + "Average \u2b06\ufe0f": 74.27, + "ARC": 70.99, + "HellaSwag": 88.43, + "MMLU": 66.34, + "TruthfulQA": 71.91, + "Winogrande": 83.58, + "GSM8K": 64.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "07cee5a25fd8d85486f888893d5bee532e5f5cd8", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "bhavinjawade\/SOLAR-10B-OrcaDPO-Jawade", + "Average \u2b06\ufe0f": 74.27, + "ARC": 71.16, + "HellaSwag": 88.27, + "MMLU": 66.12, + "TruthfulQA": 71.57, + "Winogrande": 83.66, + "GSM8K": 64.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "02a497125bbf85fe0355eb22424315c920d1aec4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/SauerkrautLM-UNA-SOLAR-Instruct", + "Average \u2b06\ufe0f": 74.26, + "ARC": 70.9, + "HellaSwag": 88.3, + "MMLU": 66.15, + "TruthfulQA": 71.8, + "Winogrande": 83.74, + "GSM8K": 64.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "564c02554a8b1f91c0860096bdb830dc15ac7805", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/SauerkrautLM-UNA-SOLAR-Instruct-test", + "Average \u2b06\ufe0f": 74.26, + "ARC": 70.9, + "HellaSwag": 88.3, + "MMLU": 66.15, + "TruthfulQA": 71.8, + "Winogrande": 83.74, + "GSM8K": 64.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ae0cab05b071dcde2e89e80ab511fa1bc0f53f1c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "macadeliccc\/SOLAR-math-2x10.7b-v0.2", + "Average \u2b06\ufe0f": 74.25, + "ARC": 70.9, + "HellaSwag": 88.29, + "MMLU": 66.25, + "TruthfulQA": 71.68, + "Winogrande": 83.5, + "GSM8K": 64.9, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1aa7540c34d4dad02ec2b9bcc991bdcd12d3134d", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/testtest", + "Average \u2b06\ufe0f": 74.24, + "ARC": 70.82, + "HellaSwag": 84.88, + "MMLU": 76.66, + "TruthfulQA": 69.9, + "Winogrande": 82.08, + "GSM8K": 61.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e9be60931d3abdf3b08a55f13e4c7586918b2be8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "222gate\/BrurryDog-7b-v0.1", + "Average \u2b06\ufe0f": 74.24, + "ARC": 72.53, + "HellaSwag": 88.37, + "MMLU": 64.74, + "TruthfulQA": 70.05, + "Winogrande": 82.87, + "GSM8K": 66.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d3cac1bb6dfc362656320a881b4fc91d3974d6ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gagan3012\/MetaModelv2", + "Average \u2b06\ufe0f": 74.24, + "ARC": 71.08, + "HellaSwag": 88.56, + "MMLU": 66.29, + "TruthfulQA": 71.94, + "Winogrande": 83.11, + "GSM8K": 64.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2cb9c69984ee3e5506f055238fd1aa5fe4ea91bd", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abideen\/MonarchCoder-MoE-2x7B", + "Average \u2b06\ufe0f": 74.23, + "ARC": 70.99, + "HellaSwag": 87.99, + "MMLU": 65.11, + "TruthfulQA": 71.25, + "Winogrande": 80.66, + "GSM8K": 69.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1d71eacdbfa5d4fe546bcc57d40e642dbac57cb7", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "BryanSwk\/LaserPipe-7B-SLERP", + "Average \u2b06\ufe0f": 74.22, + "ARC": 71.08, + "HellaSwag": 87.89, + "MMLU": 64.86, + "TruthfulQA": 65.38, + "Winogrande": 83.35, + "GSM8K": 72.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0c27fcb6770f2225e4dcc2277b8618e03810427e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Valor-7B-v0.1", + "Average \u2b06\ufe0f": 74.21, + "ARC": 72.27, + "HellaSwag": 86.59, + "MMLU": 64.09, + "TruthfulQA": 69.84, + "Winogrande": 83.35, + "GSM8K": 69.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "875319a815400bdb73c309601c175d72997a4fa0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "naseerfaheem\/SOLAR-10.7B-Instruct-ties", + "Average \u2b06\ufe0f": 74.21, + "ARC": 70.9, + "HellaSwag": 88.58, + "MMLU": 66.34, + "TruthfulQA": 71.88, + "Winogrande": 83.5, + "GSM8K": 64.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "333fbc56f7406a47435ad9afbde01c4f8116287e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kekmodel\/StopCarbon-10.7B-v2", + "Average \u2b06\ufe0f": 74.21, + "ARC": 71.08, + "HellaSwag": 88.6, + "MMLU": 66.23, + "TruthfulQA": 72.01, + "Winogrande": 83.5, + "GSM8K": 63.84, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7b49c998e2a32006e27d3e826d19240ed6bdd697", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "VAGOsolutions\/SauerkrautLM-SOLAR-Instruct", + "Average \u2b06\ufe0f": 74.21, + "ARC": 70.82, + "HellaSwag": 88.63, + "MMLU": 66.2, + "TruthfulQA": 71.95, + "Winogrande": 83.5, + "GSM8K": 64.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "8b9615124a0bcadd7fa984eaadd066da0fb4fbae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dfurman\/GarrulusMarcoro-7B-v0.1", + "Average \u2b06\ufe0f": 74.2, + "ARC": 72.35, + "HellaSwag": 88.0, + "MMLU": 64.65, + "TruthfulQA": 67.05, + "Winogrande": 87.21, + "GSM8K": 65.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c53e0d67f4684a46d35ded045c21e19e380f5e91", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kekmodel\/StopCarbon-10.7B-v1", + "Average \u2b06\ufe0f": 74.2, + "ARC": 70.9, + "HellaSwag": 88.41, + "MMLU": 66.32, + "TruthfulQA": 71.71, + "Winogrande": 83.74, + "GSM8K": 64.14, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1681ef65f3d06b421969199ae07b8d32feecf9a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "upstage\/SOLAR-10.7B-Instruct-v1.0", + "Average \u2b06\ufe0f": 74.2, + "ARC": 71.08, + "HellaSwag": 88.16, + "MMLU": 66.21, + "TruthfulQA": 71.43, + "Winogrande": 83.58, + "GSM8K": 64.75, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 519.0, + "Available on the hub": true, + "Model sha": "d3167df97a44b8632538b32ee8cd887893ea1435", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/UNA-SOLAR-10.7B-Instruct-v1.0", + "Average \u2b06\ufe0f": 74.2, + "ARC": 70.56, + "HellaSwag": 88.18, + "MMLU": 66.08, + "TruthfulQA": 72.05, + "Winogrande": 83.66, + "GSM8K": 64.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "08d3f07da7160e9657630ba98531850905619def", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "cloudyu\/Venus_DPO_50", + "Average \u2b06\ufe0f": 74.2, + "ARC": 70.73, + "HellaSwag": 88.47, + "MMLU": 66.3, + "TruthfulQA": 72.63, + "Winogrande": 83.43, + "GSM8K": 63.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "750695fe8e57714551d261b8c101a594c634d5b9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bhavinjawade\/SOLAR-10B-Nector-DPO-Jawade", + "Average \u2b06\ufe0f": 74.19, + "ARC": 71.33, + "HellaSwag": 88.62, + "MMLU": 66.22, + "TruthfulQA": 70.92, + "Winogrande": 83.43, + "GSM8K": 64.59, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "669f8f726fac4a588ced06a4da3959eb8ca20f9f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shadowml\/Mixolar-4x7b", + "Average \u2b06\ufe0f": 74.18, + "ARC": 71.08, + "HellaSwag": 88.44, + "MMLU": 66.29, + "TruthfulQA": 71.81, + "Winogrande": 83.58, + "GSM8K": 63.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "5a1b8a9c8df923c7c0e38fe9e534f73968603030", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "GreenNode\/GreenNodeLM-7B-v4leo", + "Average \u2b06\ufe0f": 74.18, + "ARC": 71.25, + "HellaSwag": 88.24, + "MMLU": 65.01, + "TruthfulQA": 69.65, + "Winogrande": 82.32, + "GSM8K": 68.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9286f6fac1df497203e110070322c93dab33fdd2", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "liminerity\/Blur-7b-v1.21", + "Average \u2b06\ufe0f": 74.18, + "ARC": 70.82, + "HellaSwag": 88.07, + "MMLU": 64.85, + "TruthfulQA": 67.99, + "Winogrande": 83.82, + "GSM8K": 69.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eaaab73b3cf4860b589a86c32b5e5865a6dc1f13", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/una-xaberius-34b-v1beta", + "Average \u2b06\ufe0f": 74.18, + "ARC": 70.39, + "HellaSwag": 86.77, + "MMLU": 78.15, + "TruthfulQA": 61.45, + "Winogrande": 84.93, + "GSM8K": 63.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 82.0, + "Available on the hub": true, + "Model sha": "233b63015f389d0023cfa21727632b340cadbdb5", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/Sakura-SOLRCA-Math-Instruct-DPO-v2", + "Average \u2b06\ufe0f": 74.17, + "ARC": 71.25, + "HellaSwag": 88.52, + "MMLU": 66.13, + "TruthfulQA": 72.16, + "Winogrande": 83.03, + "GSM8K": 63.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c994171eefa80df644e31ac01c1ee2d9e5546d99", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/Sakura-SOLAR-Instruct-DPO-v2", + "Average \u2b06\ufe0f": 74.14, + "ARC": 70.9, + "HellaSwag": 88.41, + "MMLU": 66.48, + "TruthfulQA": 71.86, + "Winogrande": 83.43, + "GSM8K": 63.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7f45a1ed9ca0f88b9ec23aa9b6202e8783ab35ac", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Seraphim-8x10.7B-bf16", + "Average \u2b06\ufe0f": 74.13, + "ARC": 71.16, + "HellaSwag": 88.68, + "MMLU": 66.26, + "TruthfulQA": 70.66, + "Winogrande": 83.5, + "GSM8K": 64.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 69.92, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "24a09bb2a8addae43f82106d405b6dc39072759c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/Sakura-SOLRCA-Math-Instruct-DPO-v1", + "Average \u2b06\ufe0f": 74.13, + "ARC": 71.25, + "HellaSwag": 88.48, + "MMLU": 66.21, + "TruthfulQA": 72.12, + "Winogrande": 82.87, + "GSM8K": 63.84, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "60e68b717f30144757b2e51d1db879c0c628f128", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Seraphim-8x10.7B-bf16", + "Average \u2b06\ufe0f": 74.12, + "ARC": 70.99, + "HellaSwag": 88.72, + "MMLU": 66.16, + "TruthfulQA": 70.77, + "Winogrande": 83.74, + "GSM8K": 64.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 69.92, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "24a09bb2a8addae43f82106d405b6dc39072759c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "mlabonne\/NeuralDaredevil-7B", + "Average \u2b06\ufe0f": 74.12, + "ARC": 69.88, + "HellaSwag": 87.62, + "MMLU": 65.12, + "TruthfulQA": 66.85, + "Winogrande": 82.08, + "GSM8K": 73.16, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "f03ff71ca0b07edccda0d2f407049dcf18edfb4d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dddsaty\/SOLAR-Instruct-ko-Adapter-Attach", + "Average \u2b06\ufe0f": 74.11, + "ARC": 71.08, + "HellaSwag": 88.2, + "MMLU": 66.09, + "TruthfulQA": 71.51, + "Winogrande": 83.5, + "GSM8K": 64.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c2519bf48d73f5751cfecfe2c4c796fbcb73c390", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/SOLAR-10.7b-Instruct-truthy-dpo", + "Average \u2b06\ufe0f": 74.11, + "ARC": 72.1, + "HellaSwag": 88.44, + "MMLU": 65.45, + "TruthfulQA": 76.75, + "Winogrande": 82.72, + "GSM8K": 59.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "31bbd3c348400c942a33c1f952dca8e7125996b7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/19B_MATH_DPO", + "Average \u2b06\ufe0f": 74.1, + "ARC": 71.08, + "HellaSwag": 88.43, + "MMLU": 66.25, + "TruthfulQA": 72.11, + "Winogrande": 82.95, + "GSM8K": 63.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0a25a243957b41c7ac8d59af50294547151ae621", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/Neural-Cosmic-Boy-7B-slerp", + "Average \u2b06\ufe0f": 74.08, + "ARC": 70.48, + "HellaSwag": 87.65, + "MMLU": 64.92, + "TruthfulQA": 67.1, + "Winogrande": 82.0, + "GSM8K": 72.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2335ab666bac2723188a3b35fc27be9306a3057c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BryanSwk\/LaserPipe-7B-SLERP", + "Average \u2b06\ufe0f": 74.08, + "ARC": 70.82, + "HellaSwag": 87.88, + "MMLU": 64.77, + "TruthfulQA": 65.34, + "Winogrande": 83.27, + "GSM8K": 72.4, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0c27fcb6770f2225e4dcc2277b8618e03810427e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhanushreddy29\/BrokenKeyboard", + "Average \u2b06\ufe0f": 74.08, + "ARC": 71.25, + "HellaSwag": 88.34, + "MMLU": 66.04, + "TruthfulQA": 71.36, + "Winogrande": 83.19, + "GSM8K": 64.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c03dfcda5d45ea4c518bd14641d9604726e00477", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "brucethemoose\/SUS-Bagel-200K-DARE-Test", + "Average \u2b06\ufe0f": 74.07, + "ARC": 68.09, + "HellaSwag": 85.38, + "MMLU": 76.98, + "TruthfulQA": 61.2, + "Winogrande": 83.5, + "GSM8K": 69.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "063c5412143468d6408b6b8122ec925c0baa0add", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "fblgit\/UNA-SOLAR-10.7B-Instruct-v1.0", + "Average \u2b06\ufe0f": 74.07, + "ARC": 70.73, + "HellaSwag": 88.32, + "MMLU": 66.1, + "TruthfulQA": 72.52, + "Winogrande": 83.35, + "GSM8K": 63.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "c63d06344214886094d7ab6c7fd5692cc59fdf0d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/UNA-POLAR-10.7B-InstructMath-v2", + "Average \u2b06\ufe0f": 74.07, + "ARC": 70.73, + "HellaSwag": 88.2, + "MMLU": 66.03, + "TruthfulQA": 71.73, + "Winogrande": 82.95, + "GSM8K": 64.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "b47d17b0df02e38e97f565784bb3cf948b29a6ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Nous-Hermes-2-SUS-Chat-34B-Slerp", + "Average \u2b06\ufe0f": 74.06, + "ARC": 66.72, + "HellaSwag": 84.97, + "MMLU": 77.0, + "TruthfulQA": 59.23, + "Winogrande": 83.58, + "GSM8K": 72.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "511cc63b3efca6f036fdbbe15f312d0e2b7e5cf5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yhyu13\/LMCocktail-10.7B-v1", + "Average \u2b06\ufe0f": 74.06, + "ARC": 70.65, + "HellaSwag": 88.13, + "MMLU": 66.21, + "TruthfulQA": 71.03, + "Winogrande": 83.35, + "GSM8K": 64.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "79ec3a42118f0715666b86bacab2688b62e1433b", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yhyu13\/LMCocktail-10.7B-v1", + "Average \u2b06\ufe0f": 74.06, + "ARC": 70.65, + "HellaSwag": 88.13, + "MMLU": 66.21, + "TruthfulQA": 71.03, + "Winogrande": 83.35, + "GSM8K": 64.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "79ec3a42118f0715666b86bacab2688b62e1433b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/Sakura-SOLRCA-Instruct-DPO", + "Average \u2b06\ufe0f": 74.05, + "ARC": 71.16, + "HellaSwag": 88.49, + "MMLU": 66.17, + "TruthfulQA": 72.1, + "Winogrande": 82.95, + "GSM8K": 63.46, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "48977e38731685ad9a45eef6ff94d5d6f60471f2", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/UNAversal-2x7B-v1", + "Average \u2b06\ufe0f": 74.05, + "ARC": 73.38, + "HellaSwag": 87.87, + "MMLU": 63.49, + "TruthfulQA": 69.93, + "Winogrande": 82.08, + "GSM8K": 67.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "514783cefac2b142adb50ee5f61dd724d62910cf", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/TheTop-5x7B-Instruct-S3-v0.1", + "Average \u2b06\ufe0f": 74.03, + "ARC": 70.9, + "HellaSwag": 88.0, + "MMLU": 65.13, + "TruthfulQA": 64.47, + "Winogrande": 83.66, + "GSM8K": 72.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cce7c94dc1d178234c3616730b203c2e52f80ed2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "dddsaty\/Merge_Sakura_Solar", + "Average \u2b06\ufe0f": 74.03, + "ARC": 70.73, + "HellaSwag": 88.51, + "MMLU": 66.03, + "TruthfulQA": 72.21, + "Winogrande": 82.72, + "GSM8K": 63.99, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0cce8842b179e19e6faac936a8c44ea1ba05b6b9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/Westest-7B", + "Average \u2b06\ufe0f": 74.03, + "ARC": 72.18, + "HellaSwag": 88.52, + "MMLU": 64.43, + "TruthfulQA": 66.72, + "Winogrande": 86.58, + "GSM8K": 65.73, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9250ae984d3a3051fb4767451a7c548b34f96445", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/una-cybertron-7b-v3-OMA", + "Average \u2b06\ufe0f": 74.01, + "ARC": 73.04, + "HellaSwag": 87.94, + "MMLU": 63.44, + "TruthfulQA": 69.85, + "Winogrande": 82.08, + "GSM8K": 67.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "29c9ff0a9f5daa5adc797a34508bcca50205f34f", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kekmodel\/StopCarbon-10.7B-v3", + "Average \u2b06\ufe0f": 74.01, + "ARC": 70.99, + "HellaSwag": 88.57, + "MMLU": 66.13, + "TruthfulQA": 71.94, + "Winogrande": 83.19, + "GSM8K": 63.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4cf314aa78f585376918a1be8b5a246edf9f4e71", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "h2m\/mhm-8x7B-FrankenMoE-v1.0", + "Average \u2b06\ufe0f": 74.01, + "ARC": 70.9, + "HellaSwag": 87.75, + "MMLU": 64.7, + "TruthfulQA": 67.1, + "Winogrande": 82.0, + "GSM8K": 71.57, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5aeee76977588d88d3faca8340c582c82cc598ce", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "macadeliccc\/Laser-WestLake-2x7b", + "Average \u2b06\ufe0f": 74.0, + "ARC": 72.27, + "HellaSwag": 88.44, + "MMLU": 64.71, + "TruthfulQA": 69.25, + "Winogrande": 85.79, + "GSM8K": 63.53, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "0fa0bee4e763f5d9c12d414bc7e3e22a1f7f4981", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jsfs11\/WestOrcaNeuralMarco-DPO-v2-DARETIES-7B", + "Average \u2b06\ufe0f": 73.98, + "ARC": 71.93, + "HellaSwag": 88.06, + "MMLU": 64.99, + "TruthfulQA": 65.96, + "Winogrande": 82.79, + "GSM8K": 70.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e06b5a01d769ab898ed9b3e9052567d34d325552", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/WhyAreWeStillHere-7B-slerp", + "Average \u2b06\ufe0f": 73.96, + "ARC": 71.67, + "HellaSwag": 88.25, + "MMLU": 64.92, + "TruthfulQA": 68.12, + "Winogrande": 85.48, + "GSM8K": 65.35, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e973ef8cbbd0728edfe25b3999abc24a5b50e81d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/Mayoroya", + "Average \u2b06\ufe0f": 73.96, + "ARC": 71.08, + "HellaSwag": 87.52, + "MMLU": 65.28, + "TruthfulQA": 64.79, + "Winogrande": 83.43, + "GSM8K": 71.65, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "782a4064641e79573aa6bf5fd11ffb09baafbe6a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zhengr\/MixTAO-7Bx2-MoE-DPO", + "Average \u2b06\ufe0f": 73.94, + "ARC": 70.9, + "HellaSwag": 87.12, + "MMLU": 64.72, + "TruthfulQA": 69.34, + "Winogrande": 81.22, + "GSM8K": 70.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "911149cad645ccb189cb403c16bbed98df18dfd6", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "rishiraj\/meow", + "Average \u2b06\ufe0f": 73.94, + "ARC": 70.48, + "HellaSwag": 88.08, + "MMLU": 66.25, + "TruthfulQA": 70.49, + "Winogrande": 83.43, + "GSM8K": 64.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d933dcd7cbb19916f4732ae7e3892a656a8c3d27", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "viethq188\/LeoScorpius-7B-Chat-DPO", + "Average \u2b06\ufe0f": 73.92, + "ARC": 70.48, + "HellaSwag": 87.97, + "MMLU": 65.08, + "TruthfulQA": 68.83, + "Winogrande": 82.08, + "GSM8K": 69.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "6e6e0a6e5c309acbe124a8055138ea5a4f2e56d1", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/Buttercup-4x7B-bf16", + "Average \u2b06\ufe0f": 73.9, + "ARC": 72.1, + "HellaSwag": 87.74, + "MMLU": 64.58, + "TruthfulQA": 67.2, + "Winogrande": 81.93, + "GSM8K": 69.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "2513232abc84b071b83d0241e8decc69d18d721d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_5-7B-ties", + "Average \u2b06\ufe0f": 73.89, + "ARC": 71.67, + "HellaSwag": 87.88, + "MMLU": 64.91, + "TruthfulQA": 66.37, + "Winogrande": 83.66, + "GSM8K": 68.84, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1ca994e2d628d98ba725b128c3a87201bd434603", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "222gate\/bleagle-7b-v0.1-test", + "Average \u2b06\ufe0f": 73.89, + "ARC": 72.27, + "HellaSwag": 88.24, + "MMLU": 64.37, + "TruthfulQA": 67.83, + "Winogrande": 85.48, + "GSM8K": 65.13, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "176a7ae5754de18b852c5018c7cee41925fe05b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "fblgit\/UNA-TheBeagle-7b-v1", + "Average \u2b06\ufe0f": 73.87, + "ARC": 73.04, + "HellaSwag": 88.0, + "MMLU": 63.48, + "TruthfulQA": 69.85, + "Winogrande": 82.16, + "GSM8K": 66.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "72084679bda2e7679259e9c0fa2fdcd48ecb158c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mncai\/mistral-7b-dpo-v5", + "Average \u2b06\ufe0f": 73.87, + "ARC": 72.01, + "HellaSwag": 87.57, + "MMLU": 63.85, + "TruthfulQA": 66.86, + "Winogrande": 82.24, + "GSM8K": 70.66, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8108f313d878ce848ceceeaf55ce8b3ecaaee792", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nlpguy\/Westgate", + "Average \u2b06\ufe0f": 73.84, + "ARC": 71.42, + "HellaSwag": 88.14, + "MMLU": 65.11, + "TruthfulQA": 62.59, + "Winogrande": 85.71, + "GSM8K": 70.05, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c1bec7b7f725e02cde8c87a20f5928a535e4fa75", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Gony_v3", + "Average \u2b06\ufe0f": 73.83, + "ARC": 71.33, + "HellaSwag": 88.71, + "MMLU": 71.07, + "TruthfulQA": 73.33, + "Winogrande": 81.22, + "GSM8K": 57.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "73b5302f1efc7ba87e123cfed0c9c998e098c16a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "yunconglong\/10.7Bx2_DPO_200", + "Average \u2b06\ufe0f": 73.83, + "ARC": 70.22, + "HellaSwag": 88.23, + "MMLU": 66.25, + "TruthfulQA": 75.38, + "Winogrande": 81.93, + "GSM8K": 60.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e6e9534becf65017d359db8704e6bcc9caf3ff60", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Nous-Hermes-2-SUS-Chat-2x34B", + "Average \u2b06\ufe0f": 73.82, + "ARC": 66.81, + "HellaSwag": 85.22, + "MMLU": 76.65, + "TruthfulQA": 57.42, + "Winogrande": 83.74, + "GSM8K": 73.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "fd230896bc3a1cfabdf37f8d8389cd670ea72faa", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "flemmingmiguel\/MarcMistral-7B", + "Average \u2b06\ufe0f": 73.81, + "ARC": 71.16, + "HellaSwag": 87.78, + "MMLU": 65.38, + "TruthfulQA": 64.92, + "Winogrande": 81.69, + "GSM8K": 71.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4571c6a5382eedacb74a51d1dfb0a6f378becc86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/LUNA-SOLARkrautLM-Instruct", + "Average \u2b06\ufe0f": 73.79, + "ARC": 71.16, + "HellaSwag": 88.28, + "MMLU": 66.11, + "TruthfulQA": 73.37, + "Winogrande": 82.95, + "GSM8K": 60.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "3b6604be8133f311d0719acb95d1a3a1f62a7d67", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "antiven0m\/finch", + "Average \u2b06\ufe0f": 73.78, + "ARC": 71.59, + "HellaSwag": 87.87, + "MMLU": 64.81, + "TruthfulQA": 67.96, + "Winogrande": 84.14, + "GSM8K": 66.34, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8dbf40c7be17ddb1b2a07e49c60c180fed741172", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/UNAversal-8x7B-v1beta", + "Average \u2b06\ufe0f": 73.78, + "ARC": 69.8, + "HellaSwag": 86.9, + "MMLU": 70.39, + "TruthfulQA": 71.97, + "Winogrande": 82.0, + "GSM8K": 61.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "db160d4bc5bd9f2e66a764aeb44dcd18fb8afa6d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Grafted-Llama2-2x70B", + "Average \u2b06\ufe0f": 73.77, + "ARC": 72.61, + "HellaSwag": 89.57, + "MMLU": 71.67, + "TruthfulQA": 66.49, + "Winogrande": 84.37, + "GSM8K": 57.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 125.35, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "68b4f64541479fb6f6691de1fb2f4db07e1634e2", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "sophosympatheia\/Aurora-Nights-70B-v1.0", + "Average \u2b06\ufe0f": 73.77, + "ARC": 71.33, + "HellaSwag": 88.33, + "MMLU": 70.47, + "TruthfulQA": 62.81, + "Winogrande": 83.35, + "GSM8K": 66.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "e4b4ee3d952b1e8360a82d2b3506fd5b4ab68df9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "allenai\/tulu-2-dpo-70b", + "Average \u2b06\ufe0f": 73.77, + "ARC": 72.1, + "HellaSwag": 88.99, + "MMLU": 69.84, + "TruthfulQA": 65.78, + "Winogrande": 83.27, + "GSM8K": 62.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 137.0, + "Available on the hub": true, + "Model sha": "0ab5c875f0070d5aee8d36bc55f41de440a13f02", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Steelskull\/Lumosia-v2-MoE-4x10.7", + "Average \u2b06\ufe0f": 73.75, + "ARC": 70.39, + "HellaSwag": 87.87, + "MMLU": 66.45, + "TruthfulQA": 68.48, + "Winogrande": 84.21, + "GSM8K": 65.13, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "479d3907a5bce4f3edb476d3ae05fe4b38a0a6e4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "nbeerbower\/SuperBruphin-3x7B", + "Average \u2b06\ufe0f": 73.75, + "ARC": 71.16, + "HellaSwag": 87.74, + "MMLU": 64.58, + "TruthfulQA": 66.85, + "Winogrande": 81.53, + "GSM8K": 70.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fedc78faef524786860027123f90609f402430b2", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "leveldevai\/BeagleMist-7B", + "Average \u2b06\ufe0f": 73.74, + "ARC": 71.08, + "HellaSwag": 87.47, + "MMLU": 65.29, + "TruthfulQA": 64.83, + "Winogrande": 81.93, + "GSM8K": 71.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "33c3fd1152072dfefe60b4c2c9247539b0a161ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Nous-Hermes-2-Yi-34B", + "Average \u2b06\ufe0f": 73.74, + "ARC": 66.89, + "HellaSwag": 85.49, + "MMLU": 76.7, + "TruthfulQA": 60.37, + "Winogrande": 82.95, + "GSM8K": 70.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 183.0, + "Available on the hub": true, + "Model sha": "deb99d98742ec9691ef593418bea71a4437745a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC56\/Mistral-7B-orca-dpo-12h", + "Average \u2b06\ufe0f": 73.73, + "ARC": 71.59, + "HellaSwag": 89.01, + "MMLU": 64.23, + "TruthfulQA": 72.15, + "Winogrande": 84.53, + "GSM8K": 60.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7453b717ab9010c3c5cfa5d38af4b174529bc457", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "decruz07\/kellemar-DPO-Orca-Distilled-7B-SLERP", + "Average \u2b06\ufe0f": 73.71, + "ARC": 70.48, + "HellaSwag": 87.56, + "MMLU": 65.33, + "TruthfulQA": 64.97, + "Winogrande": 81.93, + "GSM8K": 72.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "efb6caff9804383600563a658ba18720ec3b2d11", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "louisbrulenaudet\/Pearl-34B-dare", + "Average \u2b06\ufe0f": 73.71, + "ARC": 68.43, + "HellaSwag": 83.61, + "MMLU": 76.4, + "TruthfulQA": 68.5, + "Winogrande": 81.77, + "GSM8K": 63.53, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8c37fc9bad0de353a597b133a1570b556211c01b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Nous-Hermes-2-SUS-Chat-34B-Linear", + "Average \u2b06\ufe0f": 73.69, + "ARC": 66.38, + "HellaSwag": 84.94, + "MMLU": 76.82, + "TruthfulQA": 59.19, + "Winogrande": 82.79, + "GSM8K": 72.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "91673157803a869009e04e588c15914f132fb46b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "v1olet\/v1olet_merged_dpo_7B_v3", + "Average \u2b06\ufe0f": 73.68, + "ARC": 72.61, + "HellaSwag": 87.7, + "MMLU": 63.51, + "TruthfulQA": 69.07, + "Winogrande": 82.32, + "GSM8K": 66.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "63b69bf2588f3b108d3427389d3c707f6b50d2ba", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "GreenNode\/GreenNodeLM-7B-v1olet", + "Average \u2b06\ufe0f": 73.68, + "ARC": 72.61, + "HellaSwag": 87.7, + "MMLU": 63.51, + "TruthfulQA": 69.07, + "Winogrande": 82.32, + "GSM8K": 66.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4f0d53e65814390b8a260dd23fe5a30ced239176", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/MM-Orc-Vic-bagel-34b-c1000", + "Average \u2b06\ufe0f": 73.68, + "ARC": 67.32, + "HellaSwag": 83.52, + "MMLU": 76.09, + "TruthfulQA": 60.57, + "Winogrande": 82.32, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dc7dfbece1b31665b0456476f67ef97a17bd2323", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AiMavenAi\/MavenWest", + "Average \u2b06\ufe0f": 73.68, + "ARC": 71.59, + "HellaSwag": 88.44, + "MMLU": 64.63, + "TruthfulQA": 65.29, + "Winogrande": 83.27, + "GSM8K": 68.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "91075cfad3fe5a4bf08475e2b45fd9399a8ad368", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jsfs11\/West-Dare-7B", + "Average \u2b06\ufe0f": 73.65, + "ARC": 71.42, + "HellaSwag": 87.57, + "MMLU": 64.29, + "TruthfulQA": 66.25, + "Winogrande": 84.53, + "GSM8K": 67.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "78a01b25cb36f806ad1b25132595ccfaa376466a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "FelixChao\/WestSeverus-10.7B", + "Average \u2b06\ufe0f": 73.65, + "ARC": 72.18, + "HellaSwag": 87.47, + "MMLU": 65.06, + "TruthfulQA": 72.3, + "Winogrande": 82.72, + "GSM8K": 62.17, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "22fbfded4e563a0b1e0a750ff24e742ee19831b1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "flemmingmiguel\/NeuDist-Ro-7B", + "Average \u2b06\ufe0f": 73.64, + "ARC": 71.25, + "HellaSwag": 87.48, + "MMLU": 65.13, + "TruthfulQA": 64.93, + "Winogrande": 82.08, + "GSM8K": 70.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c48a29d5543deb8ab9afb4dec0eb0c1a47f2c222", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "argilla\/distilabeled-Marcoro14-7B-slerp", + "Average \u2b06\ufe0f": 73.63, + "ARC": 70.73, + "HellaSwag": 87.47, + "MMLU": 65.22, + "TruthfulQA": 65.1, + "Winogrande": 82.08, + "GSM8K": 71.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "baa14c82695e595b5d39f35068898feb6fdceb34", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051612\/A0125", + "Average \u2b06\ufe0f": 73.63, + "ARC": 69.71, + "HellaSwag": 85.0, + "MMLU": 86.64, + "TruthfulQA": 60.27, + "Winogrande": 80.51, + "GSM8K": 59.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "194a9c07a60f6064fe77adb0daf378d0ded7ac43", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Asura_v2", + "Average \u2b06\ufe0f": 73.62, + "ARC": 70.82, + "HellaSwag": 88.09, + "MMLU": 74.72, + "TruthfulQA": 56.97, + "Winogrande": 85.24, + "GSM8K": 65.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "515d7d948b4274c7451fdef61eae9e76eac93a38", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnowMee\/Mistral-7b-instruct-v0.2-summ-sft-ed2", + "Average \u2b06\ufe0f": 73.62, + "ARC": 71.42, + "HellaSwag": 87.42, + "MMLU": 64.32, + "TruthfulQA": 64.49, + "Winogrande": 82.87, + "GSM8K": 71.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7b7531cc63b452b67e4eefc45d89792af6a88e2f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen-72B", + "Average \u2b06\ufe0f": 73.6, + "ARC": 65.19, + "HellaSwag": 85.94, + "MMLU": 77.37, + "TruthfulQA": 60.19, + "Winogrande": 82.48, + "GSM8K": 70.43, + "Type": "pretrained", + "Architecture": "QWenLMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 308.0, + "Available on the hub": true, + "Model sha": "f62c59844a8de3c27cf22735218d77e9fa9f6b17", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "saishf\/West-Hermes-7B", + "Average \u2b06\ufe0f": 73.6, + "ARC": 71.67, + "HellaSwag": 87.6, + "MMLU": 64.83, + "TruthfulQA": 64.26, + "Winogrande": 84.69, + "GSM8K": 68.54, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "9cd172b853949228761dfa65dfec57746475d703", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rombodawg\/Open_Gpt4_8x7B_v0.2", + "Average \u2b06\ufe0f": 73.59, + "ARC": 68.69, + "HellaSwag": 86.16, + "MMLU": 72.07, + "TruthfulQA": 71.92, + "Winogrande": 83.58, + "GSM8K": 59.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "3aba335d2131a014494a9df7c8a3d0783f50bad8", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Steelskull\/Umbra-v2.1-MoE-4x10.7", + "Average \u2b06\ufe0f": 73.59, + "ARC": 69.11, + "HellaSwag": 87.57, + "MMLU": 66.48, + "TruthfulQA": 66.57, + "Winogrande": 83.11, + "GSM8K": 68.69, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "740d59fb617da265662a6bddd092226b5503eda4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "CultriX\/MistralTrix-SLERP", + "Average \u2b06\ufe0f": 73.58, + "ARC": 70.82, + "HellaSwag": 87.54, + "MMLU": 64.98, + "TruthfulQA": 65.35, + "Winogrande": 81.69, + "GSM8K": 71.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ebc368fef4f5f6d3bef7d7839e58afd1c4dd3bfc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC44\/Mistral-7B-private-spef", + "Average \u2b06\ufe0f": 73.58, + "ARC": 69.88, + "HellaSwag": 87.34, + "MMLU": 63.27, + "TruthfulQA": 69.01, + "Winogrande": 83.98, + "GSM8K": 68.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bb29794e86ff6a39f77185f547c6bb335d2f5649", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mlabonne\/NeuralMarcoro14-7B", + "Average \u2b06\ufe0f": 73.57, + "ARC": 71.42, + "HellaSwag": 87.59, + "MMLU": 64.84, + "TruthfulQA": 65.64, + "Winogrande": 81.22, + "GSM8K": 70.74, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 37.0, + "Available on the hub": true, + "Model sha": "df267682dbafe08a877602e6588bf461b6607d74", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "saishf\/Kuno-Lake-7B", + "Average \u2b06\ufe0f": 73.56, + "ARC": 71.84, + "HellaSwag": 88.15, + "MMLU": 64.76, + "TruthfulQA": 66.83, + "Winogrande": 84.45, + "GSM8K": 65.35, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ee6af302f1aa7b49a89f79ae2ae15e3a357099f0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment7-7B", + "Average \u2b06\ufe0f": 73.55, + "ARC": 71.84, + "HellaSwag": 88.04, + "MMLU": 65.25, + "TruthfulQA": 70.59, + "Winogrande": 80.82, + "GSM8K": 64.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fff356f1e506e6801c5a60c165636e84a4bd302c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/Konstanta-7B", + "Average \u2b06\ufe0f": 73.54, + "ARC": 70.05, + "HellaSwag": 87.5, + "MMLU": 65.06, + "TruthfulQA": 65.43, + "Winogrande": 82.16, + "GSM8K": 71.04, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5a80b72967360cf997687b9d2b5d2ed8f167ed79", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/SOLAR-10.7b-Instruct-dpo", + "Average \u2b06\ufe0f": 73.54, + "ARC": 71.76, + "HellaSwag": 88.08, + "MMLU": 66.06, + "TruthfulQA": 71.98, + "Winogrande": 82.32, + "GSM8K": 61.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0219ef0ce5c8aaa6abe5e6c30f287edb777c7e8c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abideen\/NexoNimbus-7B", + "Average \u2b06\ufe0f": 73.5, + "ARC": 70.82, + "HellaSwag": 87.86, + "MMLU": 64.69, + "TruthfulQA": 62.43, + "Winogrande": 84.85, + "GSM8K": 70.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "12f194df2152bd4b9431b25e06fff9e47713d03d", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/A0127", + "Average \u2b06\ufe0f": 73.49, + "ARC": 68.6, + "HellaSwag": 84.51, + "MMLU": 84.9, + "TruthfulQA": 58.38, + "Winogrande": 79.87, + "GSM8K": 64.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "68ea5286e3925a8dce3d791ab35dd978c1245ec7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment15-7B", + "Average \u2b06\ufe0f": 73.48, + "ARC": 72.18, + "HellaSwag": 88.68, + "MMLU": 60.01, + "TruthfulQA": 77.05, + "Winogrande": 84.21, + "GSM8K": 58.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "45b93bfc4297b0bc1ef0b7316cbae11d2bb527d1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment10-7B", + "Average \u2b06\ufe0f": 73.47, + "ARC": 72.18, + "HellaSwag": 87.96, + "MMLU": 65.32, + "TruthfulQA": 71.1, + "Winogrande": 80.74, + "GSM8K": 63.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b79854d1c29b5caae403c29d484f969b31734a5e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment8-7B", + "Average \u2b06\ufe0f": 73.47, + "ARC": 72.1, + "HellaSwag": 88.13, + "MMLU": 65.25, + "TruthfulQA": 70.25, + "Winogrande": 80.66, + "GSM8K": 64.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e17d301fb143b20ac943c99f34aa8b118f14e1e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "louisbrulenaudet\/Pearl-7B-0210-dare", + "Average \u2b06\ufe0f": 73.46, + "ARC": 70.9, + "HellaSwag": 88.8, + "MMLU": 61.69, + "TruthfulQA": 71.46, + "Winogrande": 84.53, + "GSM8K": 63.38, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b29298bbe30bba7c6aef25ef21cb9f4d470a10e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Neuronovo\/neuronovo-7B-v0.2", + "Average \u2b06\ufe0f": 73.44, + "ARC": 73.04, + "HellaSwag": 88.32, + "MMLU": 65.15, + "TruthfulQA": 71.02, + "Winogrande": 80.66, + "GSM8K": 62.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "72b49b8390caf1413a4bc33a759c147525510482", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "cloudyu\/Mixtral-8x7B-Instruct-v0.1-DPO", + "Average \u2b06\ufe0f": 73.44, + "ARC": 69.8, + "HellaSwag": 87.83, + "MMLU": 71.05, + "TruthfulQA": 69.18, + "Winogrande": 81.37, + "GSM8K": 61.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "9311a4300f61f4cba381ba8347b73f0f2977a8f9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "cloudyu\/Mixtral_7Bx2_MoE", + "Average \u2b06\ufe0f": 73.43, + "ARC": 71.25, + "HellaSwag": 87.45, + "MMLU": 64.98, + "TruthfulQA": 67.23, + "Winogrande": 81.22, + "GSM8K": 68.46, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 34.0, + "Available on the hub": true, + "Model sha": "4295fae8ef44f19f38f5391dc0c7194db096c4b2", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "Neuronovo\/neuronovo-9B-v0.4", + "Average \u2b06\ufe0f": 73.42, + "ARC": 72.44, + "HellaSwag": 88.33, + "MMLU": 65.24, + "TruthfulQA": 71.07, + "Winogrande": 80.66, + "GSM8K": 62.77, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "f4bfa8b298cbd0acc236117231d5b00de5f43240", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/BruinHermes", + "Average \u2b06\ufe0f": 73.42, + "ARC": 70.14, + "HellaSwag": 87.07, + "MMLU": 65.22, + "TruthfulQA": 65.6, + "Winogrande": 81.29, + "GSM8K": 71.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "unknown", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "59db3aa4f37411d5c97a6182dcf5ecfe1757ee4a", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "argilla\/distilabeled-Marcoro14-7B-slerp-full", + "Average \u2b06\ufe0f": 73.4, + "ARC": 70.65, + "HellaSwag": 87.55, + "MMLU": 65.33, + "TruthfulQA": 64.21, + "Winogrande": 82.0, + "GSM8K": 70.66, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8a4b63ce6161a85d53a5ac9504a758e95ac052dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Steelskull\/Umbra-MoE-4x10.7", + "Average \u2b06\ufe0f": 73.4, + "ARC": 70.31, + "HellaSwag": 87.81, + "MMLU": 66.42, + "TruthfulQA": 67.82, + "Winogrande": 83.27, + "GSM8K": 64.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "6a1e1b81e4d99755604be0b84798e56058d6ec37", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "CultriX\/MistralTrix-v1", + "Average \u2b06\ufe0f": 73.39, + "ARC": 72.27, + "HellaSwag": 88.33, + "MMLU": 65.24, + "TruthfulQA": 70.73, + "Winogrande": 80.98, + "GSM8K": 62.77, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 104.0, + "Available on the hub": true, + "Model sha": "e09045608b2d68a6412185817306f4bb0cf3530c", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Mixtral_7Bx5_MoE_30B", + "Average \u2b06\ufe0f": 73.39, + "ARC": 69.97, + "HellaSwag": 86.82, + "MMLU": 64.42, + "TruthfulQA": 65.97, + "Winogrande": 80.98, + "GSM8K": 72.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 29.79, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "323fba03ac21b03df8d04ab575741429cc509d7b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment9-7B", + "Average \u2b06\ufe0f": 73.39, + "ARC": 72.01, + "HellaSwag": 88.06, + "MMLU": 65.32, + "TruthfulQA": 70.42, + "Winogrande": 80.74, + "GSM8K": 63.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a3798e202aaa326b1027c0ee0a61ac78dc175e63", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment1-7B", + "Average \u2b06\ufe0f": 73.39, + "ARC": 72.53, + "HellaSwag": 88.17, + "MMLU": 65.28, + "TruthfulQA": 69.98, + "Winogrande": 80.82, + "GSM8K": 63.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aedfd66841e39a8db181d8549a42f4d2ee248b0a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment2-7B", + "Average \u2b06\ufe0f": 73.38, + "ARC": 72.18, + "HellaSwag": 88.15, + "MMLU": 65.1, + "TruthfulQA": 69.97, + "Winogrande": 81.22, + "GSM8K": 63.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "689dbca3e4bd977fa08b7a933e4e709277cd1394", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yam-peleg\/Experiment4-7B", + "Average \u2b06\ufe0f": 73.38, + "ARC": 72.18, + "HellaSwag": 88.09, + "MMLU": 65.03, + "TruthfulQA": 70.39, + "Winogrande": 81.14, + "GSM8K": 63.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fa406117c67fc86cc8171f57b12184eecb8069be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/caTUNABeagle", + "Average \u2b06\ufe0f": 73.38, + "ARC": 70.05, + "HellaSwag": 87.35, + "MMLU": 65.02, + "TruthfulQA": 65.31, + "Winogrande": 81.22, + "GSM8K": 71.34, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "21b7d3925fb53249f3aaaa268a18106e0cc7ae0d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "macadeliccc\/SOLAR-math-2x10.7b", + "Average \u2b06\ufe0f": 73.37, + "ARC": 68.43, + "HellaSwag": 86.31, + "MMLU": 66.9, + "TruthfulQA": 64.21, + "Winogrande": 83.35, + "GSM8K": 71.04, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "10953f7a3d411b148dcbb4363b1508d0efc303a2", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/Daredevil-7B", + "Average \u2b06\ufe0f": 73.36, + "ARC": 69.37, + "HellaSwag": 87.17, + "MMLU": 65.3, + "TruthfulQA": 64.09, + "Winogrande": 81.29, + "GSM8K": 72.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "015a362ee09e6370ad5b1b70fad8a7ebfcdc9e74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shadowml\/Daredevil-7B", + "Average \u2b06\ufe0f": 73.36, + "ARC": 69.37, + "HellaSwag": 87.17, + "MMLU": 65.3, + "TruthfulQA": 64.09, + "Winogrande": 81.29, + "GSM8K": 72.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "015a362ee09e6370ad5b1b70fad8a7ebfcdc9e74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Nous-Hermes-2-Mixtral-8x7B-DPO", + "Average \u2b06\ufe0f": 73.35, + "ARC": 71.08, + "HellaSwag": 87.29, + "MMLU": 72.17, + "TruthfulQA": 54.83, + "Winogrande": 83.11, + "GSM8K": 71.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 244.0, + "Available on the hub": true, + "Model sha": "566cdea53950f86eb51dae62812c29e79405cffe", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/MoE-StrangeMerges-2x7B", + "Average \u2b06\ufe0f": 73.34, + "ARC": 70.82, + "HellaSwag": 87.83, + "MMLU": 65.04, + "TruthfulQA": 65.86, + "Winogrande": 82.79, + "GSM8K": 67.7, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5a97a5e729502a8065ecc045ca569c3840fe58e3", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "ryandt\/MusingCaterpillar", + "Average \u2b06\ufe0f": 73.33, + "ARC": 72.53, + "HellaSwag": 88.34, + "MMLU": 65.26, + "TruthfulQA": 70.93, + "Winogrande": 80.66, + "GSM8K": 62.24, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "83c266f92d51adb87ed2c259f2c151f05fb10cc2", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/multimaster-7b-v2", + "Average \u2b06\ufe0f": 73.33, + "ARC": 70.48, + "HellaSwag": 87.59, + "MMLU": 65.09, + "TruthfulQA": 60.63, + "Winogrande": 84.29, + "GSM8K": 71.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "777deaba78991d3786f3db6a513a63695170f52d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cloudyu\/Mixtral_7Bx6_MoE_35B", + "Average \u2b06\ufe0f": 73.32, + "ARC": 70.14, + "HellaSwag": 86.77, + "MMLU": 64.74, + "TruthfulQA": 65.79, + "Winogrande": 81.06, + "GSM8K": 71.42, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e1b7ae70975e235240f8a6b998eab635f37eb342", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_9-7B-dare_ties", + "Average \u2b06\ufe0f": 73.32, + "ARC": 70.31, + "HellaSwag": 87.46, + "MMLU": 65.08, + "TruthfulQA": 65.08, + "Winogrande": 81.37, + "GSM8K": 70.58, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a9b18f357c2df94b5fa2c5b36c42aa6bf43acf8b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Mixtral_7Bx6_MoE_35B", + "Average \u2b06\ufe0f": 73.31, + "ARC": 69.97, + "HellaSwag": 86.82, + "MMLU": 64.91, + "TruthfulQA": 65.77, + "Winogrande": 81.14, + "GSM8K": 71.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e1b7ae70975e235240f8a6b998eab635f37eb342", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ibndias\/Nous-Hermes-2-MoE-2x34B", + "Average \u2b06\ufe0f": 73.3, + "ARC": 66.64, + "HellaSwag": 85.73, + "MMLU": 76.49, + "TruthfulQA": 58.08, + "Winogrande": 83.35, + "GSM8K": 69.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 60.81, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "af9757f0420e27e2a332cc16cbe1eeefe99cb5f1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/FrankenBeagle-SmallOverlap-test", + "Average \u2b06\ufe0f": 73.3, + "ARC": 72.01, + "HellaSwag": 88.16, + "MMLU": 64.71, + "TruthfulQA": 69.69, + "Winogrande": 81.85, + "GSM8K": 63.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.55, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c4adb38943819daae3dc92af41801c6e97c09805", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zyh3826\/GML-Mistral-merged-v1", + "Average \u2b06\ufe0f": 73.3, + "ARC": 71.25, + "HellaSwag": 87.88, + "MMLU": 65.42, + "TruthfulQA": 69.28, + "Winogrande": 80.98, + "GSM8K": 64.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "17a3d5eb5dc23b8a7c29d33cfcd07140a083aa1f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "GreenNode\/GreenNodeLM-7B-v2leo", + "Average \u2b06\ufe0f": 73.29, + "ARC": 69.8, + "HellaSwag": 88.02, + "MMLU": 65.0, + "TruthfulQA": 67.83, + "Winogrande": 82.0, + "GSM8K": 67.1, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e5a0955eb36568aa850cd73debbe9815a9d1e60a", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Neuronovo\/neuronovo-7B-v0.3", + "Average \u2b06\ufe0f": 73.29, + "ARC": 72.7, + "HellaSwag": 88.26, + "MMLU": 65.1, + "TruthfulQA": 71.35, + "Winogrande": 80.9, + "GSM8K": 61.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6f5c9f242610ade5940a6e04d367ef9398409b73", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "gradientai\/v-alpha-tross", + "Average \u2b06\ufe0f": 73.28, + "ARC": 71.93, + "HellaSwag": 86.82, + "MMLU": 70.38, + "TruthfulQA": 65.21, + "Winogrande": 83.58, + "GSM8K": 61.79, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "6188e34517a82298b0216c141ec728a5d9861658", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnwMe\/Mistral-7b-instruct-v0.2-private-edw2", + "Average \u2b06\ufe0f": 73.28, + "ARC": 69.88, + "HellaSwag": 87.33, + "MMLU": 64.85, + "TruthfulQA": 63.89, + "Winogrande": 80.66, + "GSM8K": 73.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d4cffeadbb02eaf6273e954fc5aea4f745747705", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Eric111\/NeuralBeagleOpenChat", + "Average \u2b06\ufe0f": 73.26, + "ARC": 70.31, + "HellaSwag": 86.26, + "MMLU": 65.62, + "TruthfulQA": 60.91, + "Winogrande": 82.08, + "GSM8K": 74.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "27f19157ab816247b969cafa84642f37fe841913", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "occultml\/CatMarcoro14-7B-slerp", + "Average \u2b06\ufe0f": 73.25, + "ARC": 69.37, + "HellaSwag": 86.92, + "MMLU": 65.27, + "TruthfulQA": 63.24, + "Winogrande": 81.69, + "GSM8K": 73.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "07d9e69a880d1c31c29c932f4fae6c36ceda01ea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/Eukaryote-8x7B-bf16", + "Average \u2b06\ufe0f": 73.23, + "ARC": 69.45, + "HellaSwag": 87.29, + "MMLU": 65.15, + "TruthfulQA": 63.17, + "Winogrande": 82.4, + "GSM8K": 71.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5ccee182c62fcbadfe91f66b74590aea40b181e5", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "ZoidBB\/MultiKory-0.1-4x11b-pre1", + "Average \u2b06\ufe0f": 73.23, + "ARC": 72.87, + "HellaSwag": 87.9, + "MMLU": 64.6, + "TruthfulQA": 67.67, + "Winogrande": 85.4, + "GSM8K": 60.96, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "894dacf37534e90519b4f29ce618922e19adf934", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ZoidBB\/Kory-0.1-11b-pre1", + "Average \u2b06\ufe0f": 73.23, + "ARC": 72.87, + "HellaSwag": 87.9, + "MMLU": 64.59, + "TruthfulQA": 67.68, + "Winogrande": 85.4, + "GSM8K": 60.96, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e485b974a73b0b280d974713392e90afd9e51e38", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/WinterGoddess-1.4x-70B-L2", + "Average \u2b06\ufe0f": 73.23, + "ARC": 72.78, + "HellaSwag": 90.11, + "MMLU": 71.12, + "TruthfulQA": 65.76, + "Winogrande": 85.0, + "GSM8K": 54.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "5197257333076dd80821a5055abae7d21a7dc844", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/BurningBruce-SOLAR-8x10.7B-bf16", + "Average \u2b06\ufe0f": 73.23, + "ARC": 69.11, + "HellaSwag": 87.81, + "MMLU": 66.27, + "TruthfulQA": 68.67, + "Winogrande": 83.35, + "GSM8K": 64.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 69.92, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "fd0cfae8ce78770857d415291ea23b77c7b52705", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "SUSTech\/SUS-Chat-34B", + "Average \u2b06\ufe0f": 73.22, + "ARC": 66.3, + "HellaSwag": 83.91, + "MMLU": 76.41, + "TruthfulQA": 57.04, + "Winogrande": 83.5, + "GSM8K": 72.18, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 107.0, + "Available on the hub": true, + "Model sha": "01f1a7861667c4869bb03251dfd10526bf846e9c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/SOLAR-10.7B-NahIdWin", + "Average \u2b06\ufe0f": 73.21, + "ARC": 64.51, + "HellaSwag": 85.67, + "MMLU": 64.17, + "TruthfulQA": 76.73, + "Winogrande": 80.51, + "GSM8K": 67.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "94bad5a6b469d84f556d6cc52c44fd88c07476f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dillfrescott\/trinity-medium", + "Average \u2b06\ufe0f": 73.21, + "ARC": 71.5, + "HellaSwag": 86.99, + "MMLU": 65.04, + "TruthfulQA": 69.54, + "Winogrande": 81.14, + "GSM8K": 65.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e0d20c61e1bcd8e305da40e20219edf7649d2952", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Vasanth\/Valor_Macaroni_moe", + "Average \u2b06\ufe0f": 73.2, + "ARC": 70.31, + "HellaSwag": 86.62, + "MMLU": 64.57, + "TruthfulQA": 64.65, + "Winogrande": 82.24, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dbd8fcc7b2987cc3a1802561f63e483e8871aadb", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "yunconglong\/7Bx4_DPO", + "Average \u2b06\ufe0f": 73.2, + "ARC": 69.37, + "HellaSwag": 86.89, + "MMLU": 64.73, + "TruthfulQA": 65.66, + "Winogrande": 80.58, + "GSM8K": 71.95, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d26e345f256b8a8210637258a5973fd36227d8ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "argilla\/notus-8x7b-experiment", + "Average \u2b06\ufe0f": 73.18, + "ARC": 70.99, + "HellaSwag": 87.73, + "MMLU": 71.33, + "TruthfulQA": 65.79, + "Winogrande": 81.61, + "GSM8K": 61.64, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "86c89d182babd29521a41a54528e5bf8331ed4cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "CultriX\/MistralTrixTest", + "Average \u2b06\ufe0f": 73.17, + "ARC": 72.53, + "HellaSwag": 88.4, + "MMLU": 65.22, + "TruthfulQA": 70.77, + "Winogrande": 81.37, + "GSM8K": 60.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4e6a6b8022ce4b3b71b332c3389067613bd7f850", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "macadeliccc\/Orca-SOLAR-4x10.7b", + "Average \u2b06\ufe0f": 73.17, + "ARC": 68.52, + "HellaSwag": 86.78, + "MMLU": 67.03, + "TruthfulQA": 64.54, + "Winogrande": 83.9, + "GSM8K": 68.23, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "620ed061bad27da7c0e4d1342ec431986d01477f", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YouKnwMe\/Mistral-7b-instruct-v0.2-private-edw2", + "Average \u2b06\ufe0f": 73.17, + "ARC": 69.8, + "HellaSwag": 87.32, + "MMLU": 64.9, + "TruthfulQA": 63.83, + "Winogrande": 80.9, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d4cffeadbb02eaf6273e954fc5aea4f745747705", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/WestSeverus-7B", + "Average \u2b06\ufe0f": 73.16, + "ARC": 70.31, + "HellaSwag": 87.46, + "MMLU": 64.98, + "TruthfulQA": 62.89, + "Winogrande": 83.58, + "GSM8K": 69.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "309fb3fd2e71c9a93f9840fecfa754c7e82c346e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gradientai\/v-alpha-tross", + "Average \u2b06\ufe0f": 73.16, + "ARC": 71.84, + "HellaSwag": 86.84, + "MMLU": 70.44, + "TruthfulQA": 65.22, + "Winogrande": 83.11, + "GSM8K": 61.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "2d5b9af81408ebc5e45c944cc24c9bab85b7ae1f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "AA051615\/A0204", + "Average \u2b06\ufe0f": 73.14, + "ARC": 70.31, + "HellaSwag": 84.42, + "MMLU": 86.86, + "TruthfulQA": 57.94, + "Winogrande": 80.82, + "GSM8K": 58.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5f2395801bf236bb5d6a0b5ca48122b261f7a2cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "brucethemoose\/Yi-34B-200K-DARE-merge-v7", + "Average \u2b06\ufe0f": 73.12, + "ARC": 68.09, + "HellaSwag": 85.99, + "MMLU": 77.3, + "TruthfulQA": 58.9, + "Winogrande": 83.11, + "GSM8K": 65.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "9a6bfe30e2ab9eab807787bb0f3b7e91241d1ce0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NousResearch\/Nous-Hermes-2-Mixtral-8x7B-DPO", + "Average \u2b06\ufe0f": 73.12, + "ARC": 71.42, + "HellaSwag": 87.21, + "MMLU": 72.28, + "TruthfulQA": 54.53, + "Winogrande": 82.64, + "GSM8K": 70.66, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 244.0, + "Available on the hub": true, + "Model sha": "6ba531f1aec62375bf94ad9c7bb064953c4e9868", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "samir-fama\/SamirGPT-v1", + "Average \u2b06\ufe0f": 73.11, + "ARC": 69.54, + "HellaSwag": 87.04, + "MMLU": 65.3, + "TruthfulQA": 63.37, + "Winogrande": 81.69, + "GSM8K": 71.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8e8abca2d9703dff2d60de78b013360a9a3f4d5e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rombodawg\/Open_Gpt4_8x7B", + "Average \u2b06\ufe0f": 73.1, + "ARC": 69.28, + "HellaSwag": 86.77, + "MMLU": 71.2, + "TruthfulQA": 70.39, + "Winogrande": 81.77, + "GSM8K": 59.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fa90ffb7fb57cb609d9d47719b3731693d23b312", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Slerp-CM-mist-dpo", + "Average \u2b06\ufe0f": 73.1, + "ARC": 69.62, + "HellaSwag": 87.09, + "MMLU": 64.81, + "TruthfulQA": 62.82, + "Winogrande": 81.45, + "GSM8K": 72.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "ea3b28f8b829e08dfd0c7310da78bd483ab29bbe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Lelantos-DPO-7B", + "Average \u2b06\ufe0f": 73.09, + "ARC": 71.08, + "HellaSwag": 87.22, + "MMLU": 64.0, + "TruthfulQA": 67.77, + "Winogrande": 80.03, + "GSM8K": 68.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a14226753e81928ca1aa97a5457bf8313e06ba6d", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ChaoticNeutrals\/Prima-LelantaclesV5-7b", + "Average \u2b06\ufe0f": 73.09, + "ARC": 70.65, + "HellaSwag": 87.87, + "MMLU": 64.52, + "TruthfulQA": 68.26, + "Winogrande": 82.4, + "GSM8K": 64.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9d87945f984ee530cb1e062018906110e92dc470", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/Mayo", + "Average \u2b06\ufe0f": 73.08, + "ARC": 70.14, + "HellaSwag": 86.27, + "MMLU": 65.58, + "TruthfulQA": 60.93, + "Winogrande": 82.16, + "GSM8K": 73.39, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c9e75f7275ae8f8f8db94fea1d24a4855db96060", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/multimaster-7b-v3", + "Average \u2b06\ufe0f": 73.07, + "ARC": 70.39, + "HellaSwag": 87.65, + "MMLU": 65.07, + "TruthfulQA": 59.7, + "Winogrande": 84.06, + "GSM8K": 71.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6ee0b7c59743c3047f307643c7c1f13ada56fdd1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Pasta-Lake-7b", + "Average \u2b06\ufe0f": 73.07, + "ARC": 70.82, + "HellaSwag": 87.91, + "MMLU": 64.41, + "TruthfulQA": 68.28, + "Winogrande": 82.64, + "GSM8K": 64.37, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "4c0ea3e14e45c5f6aa0d8b409ccd9017501dee42", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "argilla\/notux-8x7b-v1-epoch-2", + "Average \u2b06\ufe0f": 73.05, + "ARC": 70.65, + "HellaSwag": 87.8, + "MMLU": 71.43, + "TruthfulQA": 65.97, + "Winogrande": 82.08, + "GSM8K": 60.35, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bd3924498c3ae041334be5018cd912b6537a633c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/34b-beta", + "Average \u2b06\ufe0f": 73.04, + "ARC": 70.56, + "HellaSwag": 84.2, + "MMLU": 85.6, + "TruthfulQA": 58.38, + "Winogrande": 81.29, + "GSM8K": 58.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "1a68e2717bd4b42dc9860695c3a192845e388cf7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jsfs11\/SnorkelWestBeagle-DARETIES-7B", + "Average \u2b06\ufe0f": 73.03, + "ARC": 71.16, + "HellaSwag": 87.35, + "MMLU": 64.35, + "TruthfulQA": 70.05, + "Winogrande": 83.19, + "GSM8K": 62.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "39d9c0d5c5bd1d46834a54c388fe6cb55554995f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/Marcoro14-7B-slerp", + "Average \u2b06\ufe0f": 73.01, + "ARC": 69.8, + "HellaSwag": 87.13, + "MMLU": 65.11, + "TruthfulQA": 63.54, + "Winogrande": 81.61, + "GSM8K": 70.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "25f7e124456a5ad5c8c032088eb573d3e520d411", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shadowml\/Marcoro14-7B-ties", + "Average \u2b06\ufe0f": 73.01, + "ARC": 69.8, + "HellaSwag": 87.13, + "MMLU": 65.11, + "TruthfulQA": 63.54, + "Winogrande": 81.61, + "GSM8K": 70.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "060737a4e7e8619b8d7c1180a6cc5b1a7c1d87fa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yunconglong\/7Bx4_DPO_2e", + "Average \u2b06\ufe0f": 72.99, + "ARC": 68.94, + "HellaSwag": 86.8, + "MMLU": 64.5, + "TruthfulQA": 65.6, + "Winogrande": 80.74, + "GSM8K": 71.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b2535b271d83f892de2fb3a790b298618565dcff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "argilla\/notux-8x7b-v1", + "Average \u2b06\ufe0f": 72.97, + "ARC": 70.65, + "HellaSwag": 87.72, + "MMLU": 71.39, + "TruthfulQA": 66.21, + "Winogrande": 80.74, + "GSM8K": 61.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 157.0, + "Available on the hub": true, + "Model sha": "1f8562051647d5537dc950315e74534b363a0812", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Test-Instruct-Solar-v1", + "Average \u2b06\ufe0f": 72.97, + "ARC": 70.39, + "HellaSwag": 87.76, + "MMLU": 66.33, + "TruthfulQA": 62.64, + "Winogrande": 83.9, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ff1f0d2ad57618ad9bcf526d74d8304605ffd567", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/whattest", + "Average \u2b06\ufe0f": 72.96, + "ARC": 66.81, + "HellaSwag": 84.43, + "MMLU": 76.59, + "TruthfulQA": 58.04, + "Winogrande": 82.48, + "GSM8K": 69.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "598102a9a810986c05b9aa216507be57d93de4fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/NeuralBeagle-11B", + "Average \u2b06\ufe0f": 72.95, + "ARC": 73.29, + "HellaSwag": 87.61, + "MMLU": 63.8, + "TruthfulQA": 71.36, + "Winogrande": 82.64, + "GSM8K": 58.98, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "ef081ad768776d8f6fe7b15b832c66fa6f86ffdc", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "jan-ai\/Pandora-10.7B-v1", + "Average \u2b06\ufe0f": 72.93, + "ARC": 71.08, + "HellaSwag": 87.06, + "MMLU": 64.95, + "TruthfulQA": 70.67, + "Winogrande": 81.37, + "GSM8K": 62.47, + "Type": "", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0e06af9adc32a44f307f96c387b4e803a1868291", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "The-Face-Of-Goonery\/HuginnV5.5-12.6B", + "Average \u2b06\ufe0f": 72.93, + "ARC": 72.01, + "HellaSwag": 86.7, + "MMLU": 64.5, + "TruthfulQA": 70.45, + "Winogrande": 81.29, + "GSM8K": 62.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 12.91, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "9cb2d09228ac87d761d23a1284c79b55f9f285d9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kukedlc\/NeuralKukedlc-7B-Labonned", + "Average \u2b06\ufe0f": 72.92, + "ARC": 70.82, + "HellaSwag": 86.99, + "MMLU": 64.49, + "TruthfulQA": 64.1, + "Winogrande": 80.98, + "GSM8K": 70.13, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "241c8f778b910c202ad6b80a536d7a43e41803f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bardsai\/jaskier-7b-dpo", + "Average \u2b06\ufe0f": 72.91, + "ARC": 70.82, + "HellaSwag": 87.02, + "MMLU": 64.67, + "TruthfulQA": 64.41, + "Winogrande": 80.19, + "GSM8K": 70.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ddc14e22152cc16d6ba01cd6c4facc833e98e6b5", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen2-beta-72B", + "Average \u2b06\ufe0f": 72.91, + "ARC": 65.87, + "HellaSwag": 85.99, + "MMLU": 77.2, + "TruthfulQA": 59.61, + "Winogrande": 83.03, + "GSM8K": 65.73, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "77914b9e49a63ebca7c06ecebe00215a79723f75", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen1.5-72B", + "Average \u2b06\ufe0f": 72.91, + "ARC": 65.87, + "HellaSwag": 85.99, + "MMLU": 77.2, + "TruthfulQA": 59.61, + "Winogrande": 83.03, + "GSM8K": 65.73, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "cc2f19f5bc9ad693d4447e42e9844d9931ab8e81", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "logicker\/SkkuDS-DPO-72B-v1", + "Average \u2b06\ufe0f": 72.89, + "ARC": 65.96, + "HellaSwag": 86.0, + "MMLU": 77.33, + "TruthfulQA": 59.54, + "Winogrande": 82.64, + "GSM8K": 65.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5e194e1e44c6c2ebe294f854733f5c5532de5688", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "VAGOsolutions\/SauerkrautLM-Mixtral-8x7B-Instruct", + "Average \u2b06\ufe0f": 72.89, + "ARC": 70.48, + "HellaSwag": 87.75, + "MMLU": 71.37, + "TruthfulQA": 65.71, + "Winogrande": 81.22, + "GSM8K": 60.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "330eb185920d6a470b265a4b31217c60e810fb3e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "EmbeddedLLM\/Mistral-7B-Merge-14-v0.2", + "Average \u2b06\ufe0f": 72.88, + "ARC": 68.86, + "HellaSwag": 87.01, + "MMLU": 65.05, + "TruthfulQA": 64.19, + "Winogrande": 81.69, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "819c48aa6cf2b1f722a824027ceab8247e957e79", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "samir-fama\/FernandoGPT-v1", + "Average \u2b06\ufe0f": 72.87, + "ARC": 69.45, + "HellaSwag": 86.94, + "MMLU": 65.19, + "TruthfulQA": 61.18, + "Winogrande": 81.14, + "GSM8K": 73.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a26fbae35874a6aafb02e39fd8a623022b9e2a95", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Kukedlc\/NeuralKukedlc-7B-Labonned", + "Average \u2b06\ufe0f": 72.84, + "ARC": 70.73, + "HellaSwag": 86.9, + "MMLU": 64.58, + "TruthfulQA": 64.09, + "Winogrande": 81.22, + "GSM8K": 69.52, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "241c8f778b910c202ad6b80a536d7a43e41803f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Sirius-10B", + "Average \u2b06\ufe0f": 72.83, + "ARC": 71.93, + "HellaSwag": 87.32, + "MMLU": 64.73, + "TruthfulQA": 68.1, + "Winogrande": 82.79, + "GSM8K": 62.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9f230348c854288c328f1fada6e6887c11709151", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Himitsui\/Kaiju-11B", + "Average \u2b06\ufe0f": 72.82, + "ARC": 69.97, + "HellaSwag": 87.72, + "MMLU": 66.79, + "TruthfulQA": 62.15, + "Winogrande": 83.5, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "cb9c9b0fb1d49b085069617bd8dc9cdddfdba7fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/CM-14", + "Average \u2b06\ufe0f": 72.82, + "ARC": 69.37, + "HellaSwag": 86.97, + "MMLU": 65.37, + "TruthfulQA": 61.9, + "Winogrande": 81.06, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7ab2f7eedca7ec6a6463ba4b2f822a06e47b4cd4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/O0201", + "Average \u2b06\ufe0f": 72.81, + "ARC": 67.83, + "HellaSwag": 84.49, + "MMLU": 89.35, + "TruthfulQA": 58.63, + "Winogrande": 79.79, + "GSM8K": 56.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a198e7afd29087237d6346114e75482deaf99fe4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PetroGPT\/Severus-7B-DPO", + "Average \u2b06\ufe0f": 72.81, + "ARC": 70.22, + "HellaSwag": 87.09, + "MMLU": 64.93, + "TruthfulQA": 64.41, + "Winogrande": 80.66, + "GSM8K": 69.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9893dc24b32bc83ca63e7d06cfa296d66be3fb3d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "v1olet\/v1olet_marcoroni-go-bruins-merge-7B", + "Average \u2b06\ufe0f": 72.81, + "ARC": 70.05, + "HellaSwag": 87.17, + "MMLU": 65.17, + "TruthfulQA": 61.42, + "Winogrande": 81.45, + "GSM8K": 71.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "aca5d9df596ac1f9ddffbec3de282ecbe3b32d68", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_16-7B-slerp", + "Average \u2b06\ufe0f": 72.8, + "ARC": 69.03, + "HellaSwag": 87.15, + "MMLU": 65.65, + "TruthfulQA": 62.97, + "Winogrande": 81.29, + "GSM8K": 70.74, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "04c11fb1df83af9a52139e45fc2fc34b3386a37f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PSanni\/MPOMixtral-8x7B-Instruct-v0.1", + "Average \u2b06\ufe0f": 72.8, + "ARC": 70.99, + "HellaSwag": 87.95, + "MMLU": 70.26, + "TruthfulQA": 66.52, + "Winogrande": 82.56, + "GSM8K": 58.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a4400d021e29279c8676d5c46cf76c4b36d748f6", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "macadeliccc\/piccolo-8x7b", + "Average \u2b06\ufe0f": 72.8, + "ARC": 69.62, + "HellaSwag": 86.98, + "MMLU": 64.13, + "TruthfulQA": 64.17, + "Winogrande": 79.87, + "GSM8K": 72.02, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "08440f35fb0fe0334942fe59dc116c901d55b0a0", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/19B_TRUTH_DPO", + "Average \u2b06\ufe0f": 72.8, + "ARC": 71.67, + "HellaSwag": 88.63, + "MMLU": 65.78, + "TruthfulQA": 72.23, + "Winogrande": 82.16, + "GSM8K": 56.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a388bd7af444f632e5e9370bedaeb69572f861af", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "AA051612\/A0124", + "Average \u2b06\ufe0f": 72.79, + "ARC": 67.83, + "HellaSwag": 84.71, + "MMLU": 83.7, + "TruthfulQA": 56.52, + "Winogrande": 80.74, + "GSM8K": 63.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1ff7135939ad6f5e4931703cf251134fa87b3432", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Lelantos-7B", + "Average \u2b06\ufe0f": 72.78, + "ARC": 69.03, + "HellaSwag": 86.9, + "MMLU": 64.1, + "TruthfulQA": 65.18, + "Winogrande": 80.66, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "ec060c6a4f5e45370cf2e2d65ecb388b048b0fdb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Gony_v3.3", + "Average \u2b06\ufe0f": 72.76, + "ARC": 70.39, + "HellaSwag": 87.88, + "MMLU": 71.43, + "TruthfulQA": 67.41, + "Winogrande": 81.22, + "GSM8K": 58.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cbf9c2350f24d9d10ebb1961965e7fbb4361cafb", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/OpenCM-14", + "Average \u2b06\ufe0f": 72.75, + "ARC": 69.28, + "HellaSwag": 86.89, + "MMLU": 65.01, + "TruthfulQA": 61.07, + "Winogrande": 81.29, + "GSM8K": 72.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "744228e768a6d117952ead1d981c410dd0d3ce4d", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "louisbrulenaudet\/Pearl-7B-slerp", + "Average \u2b06\ufe0f": 72.75, + "ARC": 68.0, + "HellaSwag": 87.16, + "MMLU": 64.04, + "TruthfulQA": 62.35, + "Winogrande": 81.29, + "GSM8K": 73.62, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b4fef0d4a79ed1e5441d6a0d8fb06e0eda223d9e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/CatMacaroni-Slerp", + "Average \u2b06\ufe0f": 72.74, + "ARC": 69.28, + "HellaSwag": 86.88, + "MMLU": 65.02, + "TruthfulQA": 61.02, + "Winogrande": 81.14, + "GSM8K": 73.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "6045552b7283e50378fb5c3e31f75072c1bc91f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "damerajee\/Oot-v2_lll", + "Average \u2b06\ufe0f": 72.73, + "ARC": 69.28, + "HellaSwag": 86.6, + "MMLU": 64.96, + "TruthfulQA": 62.57, + "Winogrande": 80.82, + "GSM8K": 72.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3d4a013ad5763822280ca13e804d52c432e4fc0f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "VAGOsolutions\/SauerkrautLM-Mixtral-8x7B-Instruct", + "Average \u2b06\ufe0f": 72.73, + "ARC": 70.56, + "HellaSwag": 87.74, + "MMLU": 71.08, + "TruthfulQA": 65.72, + "Winogrande": 81.45, + "GSM8K": 59.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "330eb185920d6a470b265a4b31217c60e810fb3e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "saishf\/Fimbulvetr-Kuro-Lotus-10.7B", + "Average \u2b06\ufe0f": 72.73, + "ARC": 69.54, + "HellaSwag": 87.87, + "MMLU": 66.99, + "TruthfulQA": 60.95, + "Winogrande": 84.14, + "GSM8K": 66.87, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b41d174c2041e8661086e4eb939480641a5c66dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tenyx\/TenyxChat-8x7B-v1", + "Average \u2b06\ufe0f": 72.72, + "ARC": 69.71, + "HellaSwag": 87.76, + "MMLU": 71.12, + "TruthfulQA": 65.42, + "Winogrande": 81.22, + "GSM8K": 61.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "86fd0b7d132126be49c02e061ebec02e1d3a4e38", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "mistralai\/Mixtral-8x7B-Instruct-v0.1", + "Average \u2b06\ufe0f": 72.7, + "ARC": 70.14, + "HellaSwag": 87.55, + "MMLU": 71.4, + "TruthfulQA": 64.98, + "Winogrande": 81.06, + "GSM8K": 61.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 3069.0, + "Available on the hub": true, + "Model sha": "125c431e2ff41a156b9f9076f744d2f35dd6e67a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/CatMacaroni14", + "Average \u2b06\ufe0f": 72.68, + "ARC": 69.11, + "HellaSwag": 86.92, + "MMLU": 65.07, + "TruthfulQA": 61.58, + "Winogrande": 81.06, + "GSM8K": 72.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "66f6d076cf5396d4cecc08696addf12567c55a85", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "SJ-Donald\/SJ-SOLAR-10.7b-DPO", + "Average \u2b06\ufe0f": 72.67, + "ARC": 68.26, + "HellaSwag": 86.95, + "MMLU": 66.73, + "TruthfulQA": 67.74, + "Winogrande": 84.21, + "GSM8K": 62.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "618e5aedf02d58358d6fda7d9fa67c169b7156d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "senseable\/garten2-7b", + "Average \u2b06\ufe0f": 72.65, + "ARC": 69.37, + "HellaSwag": 87.54, + "MMLU": 65.44, + "TruthfulQA": 59.5, + "Winogrande": 84.69, + "GSM8K": 69.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "96e7c78544d7eca96e3ae60ff80c728f3109e8ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Fimbulvetr-11B-v2-Test-14", + "Average \u2b06\ufe0f": 72.64, + "ARC": 70.05, + "HellaSwag": 87.79, + "MMLU": 66.78, + "TruthfulQA": 63.43, + "Winogrande": 82.95, + "GSM8K": 64.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4095b989123d28da44717f4ec8d4bd01055f4650", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_4-7B-slerp", + "Average \u2b06\ufe0f": 72.63, + "ARC": 69.45, + "HellaSwag": 87.01, + "MMLU": 65.33, + "TruthfulQA": 62.4, + "Winogrande": 82.95, + "GSM8K": 68.61, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "716875bb40a5f526cdcb33c629866175e220db55", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mistralai\/Mixtral-8x7B-Instruct-v0.1", + "Average \u2b06\ufe0f": 72.62, + "ARC": 70.22, + "HellaSwag": 87.63, + "MMLU": 71.16, + "TruthfulQA": 64.58, + "Winogrande": 81.37, + "GSM8K": 60.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 3069.0, + "Available on the hub": true, + "Model sha": "3de0408ae8b591d9ac516a2384925dd98ebc66f4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "CultriX\/CultriX-MoE-BF16", + "Average \u2b06\ufe0f": 72.6, + "ARC": 68.94, + "HellaSwag": 86.96, + "MMLU": 65.2, + "TruthfulQA": 63.47, + "Winogrande": 81.06, + "GSM8K": 69.98, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "76e3315cc3294e86ca4f348a473f5c232e50600d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Severus-7B", + "Average \u2b06\ufe0f": 72.58, + "ARC": 68.43, + "HellaSwag": 86.89, + "MMLU": 65.2, + "TruthfulQA": 61.36, + "Winogrande": 80.9, + "GSM8K": 72.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "adf7c513e9cadbe25cc2be61c43f3f36f1b488e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "SJ-Donald\/SOLAR-10.7B-slerp", + "Average \u2b06\ufe0f": 72.58, + "ARC": 68.17, + "HellaSwag": 86.91, + "MMLU": 66.73, + "TruthfulQA": 67.42, + "Winogrande": 84.06, + "GSM8K": 62.17, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6a31eeb4fe10b727da8f01f693de0afafb7695fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Himitsui\/KuroMitsu-11B", + "Average \u2b06\ufe0f": 72.58, + "ARC": 70.31, + "HellaSwag": 88.07, + "MMLU": 66.66, + "TruthfulQA": 61.36, + "Winogrande": 84.69, + "GSM8K": 64.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 11.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "7bd8487fc3a5c3bac022bfe8c34d2f630c123d40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/PiVoT-SUS-RP", + "Average \u2b06\ufe0f": 72.57, + "ARC": 66.55, + "HellaSwag": 84.23, + "MMLU": 76.23, + "TruthfulQA": 54.57, + "Winogrande": 83.35, + "GSM8K": 70.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1b3a5c98381f37a2ec97ce80d1d88d472a7d1802", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/TheTop-5x7B-Instruct-S2-v0.1", + "Average \u2b06\ufe0f": 72.57, + "ARC": 69.45, + "HellaSwag": 87.15, + "MMLU": 64.98, + "TruthfulQA": 62.18, + "Winogrande": 79.64, + "GSM8K": 72.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "db8fde5fb86be6414c42d71ff6d8bf44ae4275ad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "brucethemoose\/Yi-34B-200K-DARE-megamerge-v8", + "Average \u2b06\ufe0f": 72.56, + "ARC": 67.75, + "HellaSwag": 86.06, + "MMLU": 77.03, + "TruthfulQA": 56.31, + "Winogrande": 82.79, + "GSM8K": 65.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "0823229057d02acb1c9dda173d6fb2ea3b46b0af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Harmony-4x7B-bf16", + "Average \u2b06\ufe0f": 72.56, + "ARC": 68.34, + "HellaSwag": 86.75, + "MMLU": 64.73, + "TruthfulQA": 62.06, + "Winogrande": 81.37, + "GSM8K": 72.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "6e7b75c5f5941d2745c2ba1d85e0617107280f3d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/EveryNight-7B-slerp", + "Average \u2b06\ufe0f": 72.54, + "ARC": 70.05, + "HellaSwag": 87.7, + "MMLU": 64.88, + "TruthfulQA": 66.07, + "Winogrande": 82.87, + "GSM8K": 63.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d9a0f3fc9f72dfe8f5a97084f512d6ace39f9b9f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "fhai50032\/RolePlayLake-7B", + "Average \u2b06\ufe0f": 72.54, + "ARC": 70.56, + "HellaSwag": 87.42, + "MMLU": 64.55, + "TruthfulQA": 64.38, + "Winogrande": 83.27, + "GSM8K": 65.05, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "067200540bfab02c1aad895e709075f1416279f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIDC-ai-business\/Marcoroni-7B-v3", + "Average \u2b06\ufe0f": 72.53, + "ARC": 69.45, + "HellaSwag": 86.78, + "MMLU": 65.0, + "TruthfulQA": 60.4, + "Winogrande": 81.45, + "GSM8K": 72.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6ec546141522aef9b42d1a014f1a539fcc485c45", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bardsai\/jaskier-7b-dpo-v2", + "Average \u2b06\ufe0f": 72.53, + "ARC": 69.28, + "HellaSwag": 86.8, + "MMLU": 64.92, + "TruthfulQA": 61.64, + "Winogrande": 80.74, + "GSM8K": 71.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a0c0f4f9d4fbfe0a688d1d58b98b30f0ca6fc9bd", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "leveldevai\/MBA-7B", + "Average \u2b06\ufe0f": 72.52, + "ARC": 69.45, + "HellaSwag": 87.22, + "MMLU": 65.16, + "TruthfulQA": 62.71, + "Winogrande": 81.53, + "GSM8K": 69.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b5b539f244c5f2fae4eff2095c5d75e60707fcc0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Toten5\/Marcoroni-v3-neural-chat-v3-3-Slerp", + "Average \u2b06\ufe0f": 72.51, + "ARC": 68.77, + "HellaSwag": 86.55, + "MMLU": 64.51, + "TruthfulQA": 62.7, + "Winogrande": 80.74, + "GSM8K": 71.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0223ffb3f70272009d0d76923f40cb31f3d2347e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rwitz2\/pee", + "Average \u2b06\ufe0f": 72.5, + "ARC": 69.88, + "HellaSwag": 86.89, + "MMLU": 64.95, + "TruthfulQA": 60.56, + "Winogrande": 81.77, + "GSM8K": 70.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "eb3b3b6b25c31a7805d672059e06d4eace586a28", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Toten5\/Marcoroni-neural-chat-7B-v2", + "Average \u2b06\ufe0f": 72.5, + "ARC": 68.6, + "HellaSwag": 86.33, + "MMLU": 64.65, + "TruthfulQA": 61.84, + "Winogrande": 80.43, + "GSM8K": 73.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "15808c683e8e1125d54498a16a620b0e8520ed2b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/bagel-dpo-8x7b-v0.2", + "Average \u2b06\ufe0f": 72.49, + "ARC": 72.1, + "HellaSwag": 86.41, + "MMLU": 70.27, + "TruthfulQA": 72.83, + "Winogrande": 83.27, + "GSM8K": 50.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "61822ea65b8a4c56d2b5622e2adf69e430fac29a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ignos\/Mistral-T5-7B-v1", + "Average \u2b06\ufe0f": 72.47, + "ARC": 68.6, + "HellaSwag": 86.3, + "MMLU": 64.62, + "TruthfulQA": 61.86, + "Winogrande": 80.27, + "GSM8K": 73.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "e91dcc46d28fc0aa5553fb73c4eac5e28abfd3ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Kunoichi-DPO-v2-7B", + "Average \u2b06\ufe0f": 72.46, + "ARC": 69.62, + "HellaSwag": 87.44, + "MMLU": 64.94, + "TruthfulQA": 66.06, + "Winogrande": 80.82, + "GSM8K": 65.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 32.0, + "Available on the hub": true, + "Model sha": "f55aef05f6632a1407fcddcbc6729613b07e87e2", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Marcoroni-8x7B-v3-MoE", + "Average \u2b06\ufe0f": 72.45, + "ARC": 69.37, + "HellaSwag": 86.78, + "MMLU": 65.01, + "TruthfulQA": 60.4, + "Winogrande": 81.45, + "GSM8K": 71.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "901a733d1c01035bcbe69afd25dd9b4f982cb216", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/RPLakeCoder-TxC", + "Average \u2b06\ufe0f": 72.45, + "ARC": 70.39, + "HellaSwag": 87.36, + "MMLU": 64.48, + "TruthfulQA": 64.37, + "Winogrande": 83.11, + "GSM8K": 64.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f4e336066a1410547ebcf603f09c15071e646d8f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Brillibits\/Instruct_Mixtral-8x7B-v0.1_Dolly15K", + "Average \u2b06\ufe0f": 72.44, + "ARC": 69.28, + "HellaSwag": 87.59, + "MMLU": 70.96, + "TruthfulQA": 64.83, + "Winogrande": 82.56, + "GSM8K": 59.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e593de223b662cfda40aa96163c6a42d6b32de5e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/RPLakeCoder-TxC", + "Average \u2b06\ufe0f": 72.43, + "ARC": 70.39, + "HellaSwag": 87.35, + "MMLU": 64.5, + "TruthfulQA": 64.34, + "Winogrande": 83.43, + "GSM8K": 64.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f4e336066a1410547ebcf603f09c15071e646d8f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChuckMcSneed\/PMaxxxer-v1-70b", + "Average \u2b06\ufe0f": 72.41, + "ARC": 71.08, + "HellaSwag": 87.88, + "MMLU": 70.39, + "TruthfulQA": 59.77, + "Winogrande": 82.64, + "GSM8K": 62.7, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "00a78d52d1e5c97fb0a277818c1245dfec61ab0f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "liminerity\/Blur-7B-slerp-v0.1", + "Average \u2b06\ufe0f": 72.4, + "ARC": 68.77, + "HellaSwag": 86.58, + "MMLU": 65.18, + "TruthfulQA": 60.64, + "Winogrande": 81.14, + "GSM8K": 72.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "03d64dadac0ac71cc5d62e325103cb9b9f279d43", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Kunoichi-DPO-v2-7B", + "Average \u2b06\ufe0f": 72.4, + "ARC": 69.37, + "HellaSwag": 87.42, + "MMLU": 64.83, + "TruthfulQA": 66.0, + "Winogrande": 80.74, + "GSM8K": 66.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 32.0, + "Available on the hub": true, + "Model sha": "d7d33a1517c57b596162a71a48bc29c87d29d9aa", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Kukedlc\/neuronal-7b-Mlab", + "Average \u2b06\ufe0f": 72.4, + "ARC": 69.97, + "HellaSwag": 86.79, + "MMLU": 64.51, + "TruthfulQA": 63.36, + "Winogrande": 81.06, + "GSM8K": 68.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "91a49d4c156ecb21e8477529e6b957242ba3829e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EmbeddedLLM\/Mistral-7B-Merge-14-v0.1", + "Average \u2b06\ufe0f": 72.39, + "ARC": 69.11, + "HellaSwag": 86.7, + "MMLU": 65.34, + "TruthfulQA": 63.43, + "Winogrande": 80.19, + "GSM8K": 69.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "3ddae31382dd3f7e654c1fc0e9b37f2e7f4ede92", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/IamSoTired-7B-slerp", + "Average \u2b06\ufe0f": 72.37, + "ARC": 69.88, + "HellaSwag": 87.15, + "MMLU": 64.85, + "TruthfulQA": 63.75, + "Winogrande": 82.4, + "GSM8K": 66.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a389a96d4bf973529d47564b0fe44685422e23cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "cognitivecomputations\/mixtral-instruct-0.1-laser", + "Average \u2b06\ufe0f": 72.36, + "ARC": 70.48, + "HellaSwag": 87.28, + "MMLU": 71.07, + "TruthfulQA": 65.83, + "Winogrande": 80.82, + "GSM8K": 58.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "5dbc14842c16f1fa315e682e7e5bdb0248a2b05e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/Konstanta-Alpha-V2-7B", + "Average \u2b06\ufe0f": 72.35, + "ARC": 69.62, + "HellaSwag": 87.14, + "MMLU": 65.11, + "TruthfulQA": 61.08, + "Winogrande": 81.22, + "GSM8K": 69.9, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8ee5b2131f391940dd7e09c107c02a4bfca0d7bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/laserxtral", + "Average \u2b06\ufe0f": 72.34, + "ARC": 69.03, + "HellaSwag": 86.76, + "MMLU": 64.68, + "TruthfulQA": 63.8, + "Winogrande": 80.03, + "GSM8K": 69.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 73.0, + "Available on the hub": true, + "Model sha": "91e0a33fd2cb0a77401831e96536b91c5b7817e4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "fhai50032\/BeagleLake-7B", + "Average \u2b06\ufe0f": 72.34, + "ARC": 70.39, + "HellaSwag": 87.38, + "MMLU": 64.25, + "TruthfulQA": 64.92, + "Winogrande": 83.19, + "GSM8K": 63.91, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "09289bf975106972d7e5b690c8891cf203660ddb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mindy-labs\/mindy-7b", + "Average \u2b06\ufe0f": 72.34, + "ARC": 69.11, + "HellaSwag": 86.57, + "MMLU": 64.69, + "TruthfulQA": 60.89, + "Winogrande": 81.06, + "GSM8K": 71.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ce0d461a6de81d5b8ec4d338fb0c6e7991d0b1ff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "janhq\/supermario-v2", + "Average \u2b06\ufe0f": 72.34, + "ARC": 68.52, + "HellaSwag": 86.51, + "MMLU": 64.88, + "TruthfulQA": 60.58, + "Winogrande": 81.37, + "GSM8K": 72.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d66c7d87fc3670c9292177e4cfc59e8a9d71322d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/FrankenDPO-4x7B-bf16", + "Average \u2b06\ufe0f": 72.34, + "ARC": 68.69, + "HellaSwag": 86.07, + "MMLU": 64.93, + "TruthfulQA": 63.14, + "Winogrande": 83.5, + "GSM8K": 67.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "547eac8651e32eb9a59019696faf19c372b25016", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-deepseek-67b-v15.2", + "Average \u2b06\ufe0f": 72.33, + "ARC": 68.6, + "HellaSwag": 86.37, + "MMLU": 71.5, + "TruthfulQA": 56.2, + "Winogrande": 84.45, + "GSM8K": 66.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 67.42, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "c3caef28f8402d52d6a646a7e1e00a971db1c507", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/Beyonder-4x7B-v2", + "Average \u2b06\ufe0f": 72.33, + "ARC": 68.77, + "HellaSwag": 86.8, + "MMLU": 65.1, + "TruthfulQA": 60.68, + "Winogrande": 80.9, + "GSM8K": 71.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 113.0, + "Available on the hub": true, + "Model sha": "f44d94a8a0ccfa98e5173da9d88a5ed09efad30e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "janhq\/supermario-slerp", + "Average \u2b06\ufe0f": 72.32, + "ARC": 68.94, + "HellaSwag": 86.58, + "MMLU": 64.93, + "TruthfulQA": 60.11, + "Winogrande": 81.29, + "GSM8K": 72.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "83bcf51c709bcb4fcb3c8f0f91de22f458a07ee4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "macadeliccc\/piccolo-math-2x7b", + "Average \u2b06\ufe0f": 72.32, + "ARC": 69.11, + "HellaSwag": 87.27, + "MMLU": 63.69, + "TruthfulQA": 63.86, + "Winogrande": 79.87, + "GSM8K": 70.13, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b7cd9398c8797b4e90cdd90ec9f64300e6334e6a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "chasedreaminf\/Dream-7B-slerp", + "Average \u2b06\ufe0f": 72.32, + "ARC": 68.52, + "HellaSwag": 86.35, + "MMLU": 64.6, + "TruthfulQA": 61.85, + "Winogrande": 80.35, + "GSM8K": 72.25, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c9a78a8006cd0b07d0f944621f85baf8f203d18c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Gony_v0.1", + "Average \u2b06\ufe0f": 72.32, + "ARC": 70.05, + "HellaSwag": 87.27, + "MMLU": 71.21, + "TruthfulQA": 63.23, + "Winogrande": 80.35, + "GSM8K": 61.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5aeed89b3b0eba74cea863b59a43c63c81be5989", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "rishiraj\/CatPPT", + "Average \u2b06\ufe0f": 72.32, + "ARC": 68.09, + "HellaSwag": 86.69, + "MMLU": 65.16, + "TruthfulQA": 61.55, + "Winogrande": 81.61, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "65d316ec5f213b7d9abbe2116372e0e90b579319", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jan-ai\/Solar-10.7B-SLERP", + "Average \u2b06\ufe0f": 72.31, + "ARC": 70.73, + "HellaSwag": 87.87, + "MMLU": 65.77, + "TruthfulQA": 65.72, + "Winogrande": 82.48, + "GSM8K": 61.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "786e6492919d0d1eb07b5988f67e0ee61aa05c21", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mncai\/yi-34B-v3", + "Average \u2b06\ufe0f": 72.26, + "ARC": 67.06, + "HellaSwag": 85.11, + "MMLU": 75.8, + "TruthfulQA": 57.54, + "Winogrande": 83.5, + "GSM8K": 64.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "f7605af56f29b42e72f9c2cbbd4ad8e443a8dae0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Fimbulvetr-10.7B-v1", + "Average \u2b06\ufe0f": 72.25, + "ARC": 68.94, + "HellaSwag": 87.27, + "MMLU": 66.59, + "TruthfulQA": 60.54, + "Winogrande": 83.5, + "GSM8K": 66.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "bff7146aafe1a5b84631bd279112c8c5b95d2802", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "jan-hq\/supermario-v2", + "Average \u2b06\ufe0f": 72.25, + "ARC": 68.43, + "HellaSwag": 86.51, + "MMLU": 64.96, + "TruthfulQA": 60.61, + "Winogrande": 80.74, + "GSM8K": 72.25, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "bddc0dbbe2ce89336f2f1ff9db9211b2f28e7694", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "rishiraj\/CatPPT-base", + "Average \u2b06\ufe0f": 72.25, + "ARC": 67.92, + "HellaSwag": 86.64, + "MMLU": 65.26, + "TruthfulQA": 61.72, + "Winogrande": 81.29, + "GSM8K": 70.66, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": true, + "Model sha": "7b041695f3ac19052f8c8be1918822bba8f73f74", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Kunoichi-DPO-7B", + "Average \u2b06\ufe0f": 72.24, + "ARC": 69.62, + "HellaSwag": 87.14, + "MMLU": 64.79, + "TruthfulQA": 67.31, + "Winogrande": 80.58, + "GSM8K": 63.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "4e21eea3c32d00b2fcfc5bcfd16d8dc9d0d8874d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "ChuckMcSneed\/SMaxxxer-v1-70b", + "Average \u2b06\ufe0f": 72.23, + "ARC": 70.65, + "HellaSwag": 88.02, + "MMLU": 70.55, + "TruthfulQA": 60.7, + "Winogrande": 82.87, + "GSM8K": 60.58, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e3f325626684c533dd3ce7f3c328c9a962bcbb21", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "jan-hq\/supermario-slerp-v3", + "Average \u2b06\ufe0f": 72.22, + "ARC": 69.28, + "HellaSwag": 86.71, + "MMLU": 65.11, + "TruthfulQA": 61.77, + "Winogrande": 80.51, + "GSM8K": 69.98, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9bfa05ff62ddd960cb9fb3e9dff70d800ea1c0a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "CultriX\/CultriX-MoE-Model", + "Average \u2b06\ufe0f": 72.21, + "ARC": 70.05, + "HellaSwag": 87.22, + "MMLU": 64.95, + "TruthfulQA": 68.04, + "Winogrande": 80.9, + "GSM8K": 62.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9043ce95d7311086417164cc84c6eb1d4ab7fe13", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "viethq188\/LeoScorpius-7B", + "Average \u2b06\ufe0f": 72.21, + "ARC": 69.28, + "HellaSwag": 87.01, + "MMLU": 65.04, + "TruthfulQA": 63.95, + "Winogrande": 81.53, + "GSM8K": 66.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "02e11fa83d18975f95c5d5047d0439897308c73b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Gony_v3.1", + "Average \u2b06\ufe0f": 72.2, + "ARC": 69.62, + "HellaSwag": 87.45, + "MMLU": 71.2, + "TruthfulQA": 64.17, + "Winogrande": 81.14, + "GSM8K": 59.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dfc889db0d02cebaadacc6726a8622a40f45eb5e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "AA051612\/A0123", + "Average \u2b06\ufe0f": 72.19, + "ARC": 67.66, + "HellaSwag": 84.87, + "MMLU": 78.45, + "TruthfulQA": 58.42, + "Winogrande": 80.35, + "GSM8K": 63.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "61f74b991f1a2ae4dd7ca294051ce19bed90cc56", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rwitz2\/grindin", + "Average \u2b06\ufe0f": 72.18, + "ARC": 69.88, + "HellaSwag": 87.02, + "MMLU": 64.98, + "TruthfulQA": 59.34, + "Winogrande": 80.9, + "GSM8K": 70.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9bdce071e0f87fe047cd2446be42edf91175c3be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "adonlee\/Mistral_7B_SFT_DPO_v0", + "Average \u2b06\ufe0f": 72.17, + "ARC": 66.3, + "HellaSwag": 84.9, + "MMLU": 64.53, + "TruthfulQA": 69.72, + "Winogrande": 81.77, + "GSM8K": 65.81, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "03955e2748064dcfac121e35e4e060cf6f48e259", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "brucethemoose\/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity", + "Average \u2b06\ufe0f": 72.15, + "ARC": 67.41, + "HellaSwag": 85.77, + "MMLU": 77.44, + "TruthfulQA": 57.84, + "Winogrande": 83.11, + "GSM8K": 61.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "17fe477d833b16aab50bef843bc8bf196a2710ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Kunoichi-7B", + "Average \u2b06\ufe0f": 72.13, + "ARC": 68.69, + "HellaSwag": 87.1, + "MMLU": 64.9, + "TruthfulQA": 64.04, + "Winogrande": 81.06, + "GSM8K": 67.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 62.0, + "Available on the hub": true, + "Model sha": "cb731f23e65b8638143d88055e1db57b84fdd546", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "mncai\/yi-34B-v2", + "Average \u2b06\ufe0f": 72.12, + "ARC": 66.13, + "HellaSwag": 85.0, + "MMLU": 75.64, + "TruthfulQA": 57.34, + "Winogrande": 83.66, + "GSM8K": 64.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "bf7696c10077e73d06752c564ea35cc7e5e336ca", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/72B-preview", + "Average \u2b06\ufe0f": 72.12, + "ARC": 65.19, + "HellaSwag": 83.23, + "MMLU": 77.14, + "TruthfulQA": 52.58, + "Winogrande": 82.48, + "GSM8K": 72.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "508ee8ddfd8b823fcd4b0366a72c7981c8b447d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/A0120", + "Average \u2b06\ufe0f": 72.11, + "ARC": 67.06, + "HellaSwag": 85.15, + "MMLU": 74.49, + "TruthfulQA": 57.48, + "Winogrande": 81.37, + "GSM8K": 67.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5416fc460666cec3cd10c4798f58765e03e67b42", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mindy-labs\/mindy-7b-v2", + "Average \u2b06\ufe0f": 72.11, + "ARC": 68.69, + "HellaSwag": 86.59, + "MMLU": 65.18, + "TruthfulQA": 60.16, + "Winogrande": 81.06, + "GSM8K": 70.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "b859eae30d69b065060e268b4e918601dabcc36c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rwitz\/go-bruins-v2", + "Average \u2b06\ufe0f": 72.07, + "ARC": 69.8, + "HellaSwag": 87.05, + "MMLU": 64.75, + "TruthfulQA": 59.7, + "Winogrande": 81.45, + "GSM8K": 69.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "24f8ce81d25c433bc6be147928779fb2d00ae0e7", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NousResearch\/Nous-Hermes-2-Mixtral-8x7B-SFT", + "Average \u2b06\ufe0f": 72.07, + "ARC": 69.71, + "HellaSwag": 86.74, + "MMLU": 72.21, + "TruthfulQA": 51.22, + "Winogrande": 82.95, + "GSM8K": 69.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 51.0, + "Available on the hub": true, + "Model sha": "6011e2ef7791738f3b78fa9e122360029df7c9ed", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "AA051615\/A0221", + "Average \u2b06\ufe0f": 72.07, + "ARC": 68.52, + "HellaSwag": 85.13, + "MMLU": 84.48, + "TruthfulQA": 55.13, + "Winogrande": 81.29, + "GSM8K": 57.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5faa6fd16b30b975ec7d18dea9203c186511d910", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/72B-preview", + "Average \u2b06\ufe0f": 72.06, + "ARC": 64.85, + "HellaSwag": 83.28, + "MMLU": 77.21, + "TruthfulQA": 52.51, + "Winogrande": 82.48, + "GSM8K": 72.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "508ee8ddfd8b823fcd4b0366a72c7981c8b447d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/NeuralBeagle-11B-truthy", + "Average \u2b06\ufe0f": 72.06, + "ARC": 73.63, + "HellaSwag": 87.86, + "MMLU": 63.11, + "TruthfulQA": 75.92, + "Winogrande": 82.08, + "GSM8K": 49.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e02f5cdd529677c97fb2c8e7a1ccaec378ba60df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/ToppyLake-7B-slerp", + "Average \u2b06\ufe0f": 72.05, + "ARC": 69.2, + "HellaSwag": 86.98, + "MMLU": 64.85, + "TruthfulQA": 62.54, + "Winogrande": 82.79, + "GSM8K": 65.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6d083dd5e571749ad0c574897abf473600142b16", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/DonutLM-v1", + "Average \u2b06\ufe0f": 72.05, + "ARC": 69.11, + "HellaSwag": 85.91, + "MMLU": 65.45, + "TruthfulQA": 63.36, + "Winogrande": 81.69, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "710e480608d7f9bd42bbc1d90046580f1ffdbe04", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rwitz\/dec10", + "Average \u2b06\ufe0f": 72.05, + "ARC": 69.11, + "HellaSwag": 86.46, + "MMLU": 64.98, + "TruthfulQA": 60.42, + "Winogrande": 80.74, + "GSM8K": 70.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d12ade4c823d9f42949c7902d0f01b2e996a7d7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ChaoticNeutrals\/This_is_fine_7B", + "Average \u2b06\ufe0f": 72.05, + "ARC": 70.31, + "HellaSwag": 87.28, + "MMLU": 64.51, + "TruthfulQA": 65.79, + "Winogrande": 81.61, + "GSM8K": 62.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "75c6be75cd8eeea4bc06f0d46bfeeb803b19ff26", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "llmixer\/BigWeave-v16-103b", + "Average \u2b06\ufe0f": 72.02, + "ARC": 65.87, + "HellaSwag": 87.61, + "MMLU": 73.22, + "TruthfulQA": 63.81, + "Winogrande": 80.43, + "GSM8K": 61.18, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 103.2, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1f70cd042fc8b4c5767f597edbb0054e7cb14f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rwitz\/dec10", + "Average \u2b06\ufe0f": 72.01, + "ARC": 69.2, + "HellaSwag": 86.48, + "MMLU": 64.91, + "TruthfulQA": 60.52, + "Winogrande": 80.43, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d12ade4c823d9f42949c7902d0f01b2e996a7d7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/72B-preview-llamafied-qwen-llamafy", + "Average \u2b06\ufe0f": 72.0, + "ARC": 65.19, + "HellaSwag": 83.24, + "MMLU": 77.04, + "TruthfulQA": 52.55, + "Winogrande": 82.4, + "GSM8K": 71.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 71.0, + "Available on the hub": true, + "Model sha": "f16df07e24654858a6b04c3ecb0670dcfc42337d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "brucethemoose\/Yi-34B-200K-DARE-merge-v5", + "Average \u2b06\ufe0f": 71.98, + "ARC": 66.47, + "HellaSwag": 85.54, + "MMLU": 77.22, + "TruthfulQA": 57.46, + "Winogrande": 82.24, + "GSM8K": 62.93, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "72d2469926f0277d31b13ce2db78e454b24a91b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EmbeddedLLM\/Mistral-7B-Merge-14-v0.5", + "Average \u2b06\ufe0f": 71.96, + "ARC": 68.69, + "HellaSwag": 86.45, + "MMLU": 65.65, + "TruthfulQA": 59.12, + "Winogrande": 80.66, + "GSM8K": 71.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fe9f9e52f1b48112d1c4349abbc0f104e56303ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rwitz\/go-bruins-v2", + "Average \u2b06\ufe0f": 71.95, + "ARC": 69.8, + "HellaSwag": 87.06, + "MMLU": 64.95, + "TruthfulQA": 59.68, + "Winogrande": 81.22, + "GSM8K": 68.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "49c730c9e00299eaefeb5ada30a9ec53659729a5", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenPipe\/mistral-ft-optimized-1218", + "Average \u2b06\ufe0f": 71.94, + "ARC": 67.92, + "HellaSwag": 86.26, + "MMLU": 64.99, + "TruthfulQA": 59.48, + "Winogrande": 80.74, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 146.0, + "Available on the hub": true, + "Model sha": "f4f3f6144dd143d6ec43ece9ab0fdd740ed610f1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/Valkyrie-V1", + "Average \u2b06\ufe0f": 71.92, + "ARC": 67.24, + "HellaSwag": 86.27, + "MMLU": 64.82, + "TruthfulQA": 60.4, + "Winogrande": 81.45, + "GSM8K": 71.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "78917a93a47ea6d401458d0e283a2c6db6c68a47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "saishf\/Kuro-Lotus-10.7B", + "Average \u2b06\ufe0f": 71.9, + "ARC": 68.69, + "HellaSwag": 87.51, + "MMLU": 66.64, + "TruthfulQA": 58.27, + "Winogrande": 84.21, + "GSM8K": 66.11, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ec748dade16858ef2fb3c712c78de748d165a21c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/A0110", + "Average \u2b06\ufe0f": 71.89, + "ARC": 66.38, + "HellaSwag": 84.73, + "MMLU": 74.48, + "TruthfulQA": 58.6, + "Winogrande": 82.32, + "GSM8K": 64.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1a15b9aa4acf1327164672edd16ee966b8bc3691", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Karko\/Proctora", + "Average \u2b06\ufe0f": 71.88, + "ARC": 67.83, + "HellaSwag": 86.68, + "MMLU": 65.49, + "TruthfulQA": 59.55, + "Winogrande": 79.79, + "GSM8K": 71.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "9e338a5f1650cf15850e53046fdf0c4cb25acad1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Pluto_24B_DPO_200", + "Average \u2b06\ufe0f": 71.88, + "ARC": 65.61, + "HellaSwag": 86.38, + "MMLU": 64.59, + "TruthfulQA": 69.86, + "Winogrande": 78.93, + "GSM8K": 65.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3e6ced019d4cab13bd0ca2cefbf91bc7bba31375", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/Darewin-7B", + "Average \u2b06\ufe0f": 71.87, + "ARC": 68.6, + "HellaSwag": 86.22, + "MMLU": 65.21, + "TruthfulQA": 60.38, + "Winogrande": 79.79, + "GSM8K": 71.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "04a49e7c37033714a42a22c834e0c0179cfb90c6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jeiku\/Cookie_7B", + "Average \u2b06\ufe0f": 71.87, + "ARC": 69.71, + "HellaSwag": 87.57, + "MMLU": 64.51, + "TruthfulQA": 66.88, + "Winogrande": 81.37, + "GSM8K": 61.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "026955076c0744e1257cef9b4edc25d6389fd413", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Cookie_7B", + "Average \u2b06\ufe0f": 71.87, + "ARC": 69.71, + "HellaSwag": 87.57, + "MMLU": 64.51, + "TruthfulQA": 66.88, + "Winogrande": 81.37, + "GSM8K": 61.18, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "bb106b2f29819c4e4a173cefaa62fa9b6a4a0d2e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DopeorNope\/COKAL-v1-70B", + "Average \u2b06\ufe0f": 71.87, + "ARC": 87.46, + "HellaSwag": 83.29, + "MMLU": 68.13, + "TruthfulQA": 72.79, + "Winogrande": 80.27, + "GSM8K": 39.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 69.44, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "6898ebe887fd7debab6b26aa650f2876c1e2f4cf", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Seraph-7B", + "Average \u2b06\ufe0f": 71.86, + "ARC": 67.83, + "HellaSwag": 86.22, + "MMLU": 65.07, + "TruthfulQA": 59.49, + "Winogrande": 80.66, + "GSM8K": 71.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "2c6ea500b4b33bc9231b56ee6a495cd96e63064a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bn22\/Nous-Hermes-2-SOLAR-10.7B-MISALIGNED", + "Average \u2b06\ufe0f": 71.83, + "ARC": 68.26, + "HellaSwag": 86.11, + "MMLU": 66.26, + "TruthfulQA": 57.79, + "Winogrande": 83.43, + "GSM8K": 69.14, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e402c5ea1ba23d776062f18306690296a708d469", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/A0109", + "Average \u2b06\ufe0f": 71.83, + "ARC": 66.55, + "HellaSwag": 84.7, + "MMLU": 74.44, + "TruthfulQA": 58.75, + "Winogrande": 82.16, + "GSM8K": 64.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2a9cd40c67e0b17d94a0eedafd3d116245613709", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/openchat-3.5-1210-Seraph-Slerp", + "Average \u2b06\ufe0f": 71.82, + "ARC": 68.09, + "HellaSwag": 86.48, + "MMLU": 65.33, + "TruthfulQA": 57.77, + "Winogrande": 80.82, + "GSM8K": 72.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fdcc497bcf5e9ba62a9617617ff8f4e2965104e1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "arlineka\/Brunhilde-2x7b-MOE-DPO-v.01.5", + "Average \u2b06\ufe0f": 71.81, + "ARC": 69.54, + "HellaSwag": 87.02, + "MMLU": 64.93, + "TruthfulQA": 65.47, + "Winogrande": 80.9, + "GSM8K": 63.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d9bb402315f47764bf0f6002e513cd7e89c7c804", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "rwitz\/go-bruins", + "Average \u2b06\ufe0f": 71.81, + "ARC": 69.11, + "HellaSwag": 86.73, + "MMLU": 64.94, + "TruthfulQA": 58.71, + "Winogrande": 81.45, + "GSM8K": 69.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "a544f70a290738787bf3edc167f0bc95999e5702", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-deepseek-67b-v18.1-4k", + "Average \u2b06\ufe0f": 71.8, + "ARC": 67.75, + "HellaSwag": 84.65, + "MMLU": 70.58, + "TruthfulQA": 55.66, + "Winogrande": 82.95, + "GSM8K": 69.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 67.42, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e4ba7abdb25b00308f67589458cb9380a2ccd5e6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "deepseek-ai\/deepseek-llm-67b-chat", + "Average \u2b06\ufe0f": 71.79, + "ARC": 67.75, + "HellaSwag": 86.82, + "MMLU": 72.42, + "TruthfulQA": 55.85, + "Winogrande": 84.21, + "GSM8K": 63.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 67.0, + "Hub \u2764\ufe0f": 150.0, + "Available on the hub": true, + "Model sha": "79648bef7658bb824e4630740f6e1484c1b0620b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rwitz\/go-bruins", + "Average \u2b06\ufe0f": 71.79, + "ARC": 69.11, + "HellaSwag": 86.68, + "MMLU": 64.96, + "TruthfulQA": 58.72, + "Winogrande": 81.37, + "GSM8K": 69.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "a544f70a290738787bf3edc167f0bc95999e5702", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mlabonne\/NeuralDarewin-7B", + "Average \u2b06\ufe0f": 71.79, + "ARC": 70.14, + "HellaSwag": 86.4, + "MMLU": 64.85, + "TruthfulQA": 62.92, + "Winogrande": 79.72, + "GSM8K": 66.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "72267d131001da8cdf253105c367fd913db79523", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-deepseek-67b-v15.1", + "Average \u2b06\ufe0f": 71.76, + "ARC": 67.66, + "HellaSwag": 86.49, + "MMLU": 70.3, + "TruthfulQA": 54.42, + "Winogrande": 84.77, + "GSM8K": 66.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 67.42, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3120e204e1b4928fd784ae78fa754bc937352c98", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/openchat-3.5-1210-Seraph-Slerp", + "Average \u2b06\ufe0f": 71.74, + "ARC": 67.92, + "HellaSwag": 86.43, + "MMLU": 65.26, + "TruthfulQA": 57.75, + "Winogrande": 80.82, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "46bb19fb19ff3673bdde3b38ee8e3f3884df8113", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-M-Creative-v1.0", + "Average \u2b06\ufe0f": 71.73, + "ARC": 66.81, + "HellaSwag": 85.14, + "MMLU": 75.54, + "TruthfulQA": 57.68, + "Winogrande": 83.11, + "GSM8K": 62.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 32.0, + "Available on the hub": true, + "Model sha": "26923a2648b9864e2ec6f0cc66b8b6fcfbbdd491", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "VitalContribution\/Evangelion-7B", + "Average \u2b06\ufe0f": 71.71, + "ARC": 68.94, + "HellaSwag": 86.45, + "MMLU": 63.97, + "TruthfulQA": 64.01, + "Winogrande": 79.95, + "GSM8K": 66.94, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7e3fdb60969ef0f7219cbcb9b05f7d1537af1c8d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bhenrym14\/platypus-yi-34b", + "Average \u2b06\ufe0f": 71.69, + "ARC": 68.43, + "HellaSwag": 85.21, + "MMLU": 78.13, + "TruthfulQA": 54.48, + "Winogrande": 84.06, + "GSM8K": 59.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "66abec7cba89b35c7b6cab2140c3532049de0157", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "RatanRohith\/NeuralPizza-7B-V0.3", + "Average \u2b06\ufe0f": 71.68, + "ARC": 71.08, + "HellaSwag": 87.38, + "MMLU": 64.29, + "TruthfulQA": 67.93, + "Winogrande": 80.51, + "GSM8K": 58.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "04cd413008c353ca558ab901c0d88132c25772c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PracticeLLM\/SOLAR-tail-10.7B-Merge-v1.0", + "Average \u2b06\ufe0f": 71.68, + "ARC": 66.13, + "HellaSwag": 86.54, + "MMLU": 66.52, + "TruthfulQA": 60.57, + "Winogrande": 84.77, + "GSM8K": 65.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "957474e32057f19ef863c1c8ba3d16389cf58eed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Loyal-Macaroni-Maid-7B", + "Average \u2b06\ufe0f": 71.68, + "ARC": 68.0, + "HellaSwag": 86.39, + "MMLU": 64.87, + "TruthfulQA": 62.5, + "Winogrande": 79.87, + "GSM8K": 68.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "3fc12ef0089d55509552d1569f3107fd6a24b90f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v4-yi-34b", + "Average \u2b06\ufe0f": 71.67, + "ARC": 66.81, + "HellaSwag": 84.44, + "MMLU": 74.34, + "TruthfulQA": 57.89, + "Winogrande": 82.4, + "GSM8K": 64.14, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "d1bdf5a5ea942b8236e48c17c3c07e3bd49ae5c8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "llmixer\/BigWeave-v15-103b", + "Average \u2b06\ufe0f": 71.67, + "ARC": 69.71, + "HellaSwag": 86.41, + "MMLU": 71.25, + "TruthfulQA": 66.1, + "Winogrande": 80.35, + "GSM8K": 56.18, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 103.2, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "59004f5610548e626ad27cd4a7b92daa3ccfc9c8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051612\/B0121", + "Average \u2b06\ufe0f": 71.61, + "ARC": 68.34, + "HellaSwag": 85.3, + "MMLU": 85.63, + "TruthfulQA": 58.63, + "Winogrande": 80.19, + "GSM8K": 51.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7be68dd360bea0171316ccc646261532599f14dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Samee-ur\/NeuralPipe-7B-slerp-DPO", + "Average \u2b06\ufe0f": 71.6, + "ARC": 69.28, + "HellaSwag": 86.34, + "MMLU": 63.7, + "TruthfulQA": 63.53, + "Winogrande": 80.51, + "GSM8K": 66.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "17af425d904f21f8500bf965b16d07603e01d125", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "RatanRohith\/NeuralPizza-7B-V0.2", + "Average \u2b06\ufe0f": 71.59, + "ARC": 68.77, + "HellaSwag": 86.11, + "MMLU": 64.32, + "TruthfulQA": 61.38, + "Winogrande": 80.35, + "GSM8K": 68.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e2164a4cce391e1f4228e2e89689793ec037135e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "saishf\/Top-Western-Maid-7B", + "Average \u2b06\ufe0f": 71.57, + "ARC": 69.37, + "HellaSwag": 87.4, + "MMLU": 64.63, + "TruthfulQA": 58.79, + "Winogrande": 83.27, + "GSM8K": 65.96, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2973b0902468b765a9d6452ae3ba116a3e1ceba0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "scaledown\/ScaleDown-7B-slerp-v0.1", + "Average \u2b06\ufe0f": 71.57, + "ARC": 68.0, + "HellaSwag": 85.7, + "MMLU": 65.26, + "TruthfulQA": 61.9, + "Winogrande": 81.37, + "GSM8K": 67.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9bddd33f58ddbbaa9ecf8c5a4b79dfd8e49155e5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "mayacinka\/NeuralZephyr-Beagle-7B", + "Average \u2b06\ufe0f": 71.57, + "ARC": 68.6, + "HellaSwag": 86.38, + "MMLU": 64.67, + "TruthfulQA": 65.17, + "Winogrande": 81.14, + "GSM8K": 63.46, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "91fb2de32d29aec936e54c6edeea4ae778259b00", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "brucethemoose\/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-ExtremeDensity", + "Average \u2b06\ufe0f": 71.57, + "ARC": 66.89, + "HellaSwag": 85.69, + "MMLU": 77.35, + "TruthfulQA": 57.63, + "Winogrande": 82.0, + "GSM8K": 59.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "71c95f1971c4a47adc331859b91502bd0b790ce0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Stopwolf\/DistilabelCerberus-7B-slerp", + "Average \u2b06\ufe0f": 71.56, + "ARC": 68.17, + "HellaSwag": 86.78, + "MMLU": 64.2, + "TruthfulQA": 60.93, + "Winogrande": 79.48, + "GSM8K": 69.83, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f7267cb2b0151acddd84a88c2981e73880d97634", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/NeuralPipe-7B-ties", + "Average \u2b06\ufe0f": 71.55, + "ARC": 67.92, + "HellaSwag": 86.04, + "MMLU": 64.24, + "TruthfulQA": 61.37, + "Winogrande": 80.19, + "GSM8K": 69.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "5b4a878a938954d87183d1d903923c100b2c724f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "RatanRohith\/NeuralPizza-7B-V0.1", + "Average \u2b06\ufe0f": 71.53, + "ARC": 70.48, + "HellaSwag": 87.3, + "MMLU": 64.42, + "TruthfulQA": 67.22, + "Winogrande": 80.35, + "GSM8K": 59.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "fb53c42ba7d5719e730f67c5356766d84e5f3619", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/A0106", + "Average \u2b06\ufe0f": 71.53, + "ARC": 66.38, + "HellaSwag": 85.05, + "MMLU": 74.0, + "TruthfulQA": 57.88, + "Winogrande": 82.87, + "GSM8K": 63.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "215cbefbc69d22c28181651b5b964c329ca09f59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "deepseek-ai\/deepseek-llm-67b-chat", + "Average \u2b06\ufe0f": 71.52, + "ARC": 67.75, + "HellaSwag": 86.8, + "MMLU": 72.19, + "TruthfulQA": 55.83, + "Winogrande": 84.21, + "GSM8K": 62.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 67.0, + "Hub \u2764\ufe0f": 150.0, + "Available on the hub": true, + "Model sha": "79648bef7658bb824e4630740f6e1484c1b0620b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "sethuiyer\/Nandine-7b", + "Average \u2b06\ufe0f": 71.47, + "ARC": 69.28, + "HellaSwag": 87.01, + "MMLU": 64.83, + "TruthfulQA": 62.1, + "Winogrande": 83.19, + "GSM8K": 62.4, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6fe9ea49efd6024e45e352c63815efdb7d0fe35d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Yuna-7b-Merge", + "Average \u2b06\ufe0f": 71.46, + "ARC": 67.49, + "HellaSwag": 86.84, + "MMLU": 64.86, + "TruthfulQA": 61.2, + "Winogrande": 80.74, + "GSM8K": 67.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d5cde262c73c9ee44c1ec85b1fb48f226ae99a77", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luqmanxyz\/LelaStarling-7B", + "Average \u2b06\ufe0f": 71.45, + "ARC": 67.58, + "HellaSwag": 86.33, + "MMLU": 64.98, + "TruthfulQA": 57.73, + "Winogrande": 80.98, + "GSM8K": 71.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "249b4fed97bfddc8f69e28274a2f4211296de246", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "jan-hq\/supermario-slerp-v2", + "Average \u2b06\ufe0f": 71.45, + "ARC": 69.71, + "HellaSwag": 86.54, + "MMLU": 64.82, + "TruthfulQA": 63.06, + "Winogrande": 80.74, + "GSM8K": 63.84, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dd27a200fd3dd5500a0b5bbfc0e4a9289af486e5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/A0106", + "Average \u2b06\ufe0f": 71.44, + "ARC": 66.47, + "HellaSwag": 85.05, + "MMLU": 74.03, + "TruthfulQA": 57.82, + "Winogrande": 82.72, + "GSM8K": 62.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "215cbefbc69d22c28181651b5b964c329ca09f59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dillfrescott\/amadeus-v0.1", + "Average \u2b06\ufe0f": 71.42, + "ARC": 68.94, + "HellaSwag": 86.98, + "MMLU": 64.69, + "TruthfulQA": 63.82, + "Winogrande": 79.95, + "GSM8K": 64.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "wtfpl", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "2d6dcf8bf9f1a758f135929de4a6fd81e26a38da", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051615\/L0223", + "Average \u2b06\ufe0f": 71.42, + "ARC": 67.92, + "HellaSwag": 82.99, + "MMLU": 82.59, + "TruthfulQA": 53.59, + "Winogrande": 79.79, + "GSM8K": 61.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e2819a059ca4f349f9034f2e2096c2d2208875c6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-deepseek-67b-v15.3-4k", + "Average \u2b06\ufe0f": 71.42, + "ARC": 67.58, + "HellaSwag": 85.15, + "MMLU": 70.38, + "TruthfulQA": 54.88, + "Winogrande": 83.35, + "GSM8K": 67.17, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 67.42, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7152f2dc8e0aceb0412e802653271cd9e59bf23e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KnutJaegersberg\/Deita-20b", + "Average \u2b06\ufe0f": 71.4, + "ARC": 63.91, + "HellaSwag": 83.11, + "MMLU": 67.4, + "TruthfulQA": 57.29, + "Winogrande": 84.61, + "GSM8K": 72.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "855035b23011e2a09182025a63a9252e19033163", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LDCC\/LDCC-SOLAR-10.7B", + "Average \u2b06\ufe0f": 71.4, + "ARC": 67.32, + "HellaSwag": 88.11, + "MMLU": 66.83, + "TruthfulQA": 68.85, + "Winogrande": 83.66, + "GSM8K": 53.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.86, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "1055563879363d9ee2fba1d9fd1628eca6bcbb4e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LDCC\/LDCC-SOLAR-10.7B", + "Average \u2b06\ufe0f": 71.4, + "ARC": 67.58, + "HellaSwag": 88.11, + "MMLU": 66.63, + "TruthfulQA": 68.87, + "Winogrande": 83.66, + "GSM8K": 53.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.86, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "c8741ec6f4f24324a96041efaf2f627a99d946e6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Deacon-34b-qlora-adapter", + "Average \u2b06\ufe0f": 71.39, + "ARC": 64.85, + "HellaSwag": 85.56, + "MMLU": 76.38, + "TruthfulQA": 56.21, + "Winogrande": 83.11, + "GSM8K": 62.24, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "97d19d88f629f6d5270126de7ba1400d3b89a6c6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/OpenHermes-2.5-neural-chat-v3-3-Slerp", + "Average \u2b06\ufe0f": 71.38, + "ARC": 68.09, + "HellaSwag": 86.2, + "MMLU": 64.26, + "TruthfulQA": 62.78, + "Winogrande": 79.16, + "GSM8K": 67.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "91f18df3f5c3d36f1293086113f810f662970449", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Radu1999\/MisterUkrainianDPO", + "Average \u2b06\ufe0f": 71.37, + "ARC": 68.34, + "HellaSwag": 86.78, + "MMLU": 62.92, + "TruthfulQA": 70.18, + "Winogrande": 80.74, + "GSM8K": 59.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "358df4dc83d52399b5471f9aedeefbebce7209cb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fzzhang\/Marcoroni-neural-chat-7B-v2_gsm8k_merged_s", + "Average \u2b06\ufe0f": 71.37, + "ARC": 67.15, + "HellaSwag": 85.68, + "MMLU": 62.72, + "TruthfulQA": 63.29, + "Winogrande": 79.56, + "GSM8K": 69.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c6ab98c227ff5c2e284571ed1a8c21c0f9db1a55", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DiscoResearch\/DiscoLM-70b", + "Average \u2b06\ufe0f": 71.37, + "ARC": 68.77, + "HellaSwag": 86.1, + "MMLU": 68.58, + "TruthfulQA": 57.64, + "Winogrande": 83.58, + "GSM8K": 63.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "5eab2c8ec1c079e53a60ebdb7811756c2faebd9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "leejunhyeok\/MoMo-70B-LoRA-V1.2_1", + "Average \u2b06\ufe0f": 71.36, + "ARC": 70.65, + "HellaSwag": 86.4, + "MMLU": 69.9, + "TruthfulQA": 61.41, + "Winogrande": 83.19, + "GSM8K": 56.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "178d03ccf7e7f83019266396f326fe11382eb20a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/A0113", + "Average \u2b06\ufe0f": 71.36, + "ARC": 66.38, + "HellaSwag": 84.86, + "MMLU": 74.39, + "TruthfulQA": 59.65, + "Winogrande": 82.0, + "GSM8K": 60.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6e36ad0a41135265185038d1d88062d9fb11e8d5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Novocoders\/jaskier-7b-NeuralDPO", + "Average \u2b06\ufe0f": 71.36, + "ARC": 73.46, + "HellaSwag": 88.16, + "MMLU": 63.15, + "TruthfulQA": 59.92, + "Winogrande": 85.48, + "GSM8K": 58.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "29652406c24f9d369d6bfd1ecc4979b2ab124c08", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/A0121", + "Average \u2b06\ufe0f": 71.36, + "ARC": 67.15, + "HellaSwag": 85.45, + "MMLU": 74.93, + "TruthfulQA": 59.61, + "Winogrande": 80.43, + "GSM8K": 60.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2471023d6261084e06eabb6a43b3cf06d4b189d6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "janhq\/supermario-slerp-v2", + "Average \u2b06\ufe0f": 71.35, + "ARC": 69.37, + "HellaSwag": 86.6, + "MMLU": 64.91, + "TruthfulQA": 62.96, + "Winogrande": 80.82, + "GSM8K": 63.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "662c68ece38bcc8cb7b04dc2c0f5d6c03f8d56e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Walmart-the-bag\/Solar-10.7B-Cato", + "Average \u2b06\ufe0f": 71.35, + "ARC": 68.69, + "HellaSwag": 86.16, + "MMLU": 65.76, + "TruthfulQA": 61.68, + "Winogrande": 81.22, + "GSM8K": 64.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "16b230f4e663902787254ecb1781c255b7dcc6ea", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Q-bert\/MetaMath-Cybertron-Starling", + "Average \u2b06\ufe0f": 71.35, + "ARC": 67.75, + "HellaSwag": 86.23, + "MMLU": 65.24, + "TruthfulQA": 55.94, + "Winogrande": 81.45, + "GSM8K": 71.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 40.0, + "Available on the hub": true, + "Model sha": "c274ec29903792dfdc584dc840cc16e952bd3122", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "binbi\/MoMo-70B-V1.2_1", + "Average \u2b06\ufe0f": 71.34, + "ARC": 70.9, + "HellaSwag": 86.47, + "MMLU": 69.95, + "TruthfulQA": 61.31, + "Winogrande": 83.11, + "GSM8K": 56.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "45056003b42a1cb5a6b2a0f338f85ec925a0587b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK-v1.3.0-DPO", + "Average \u2b06\ufe0f": 71.34, + "ARC": 67.49, + "HellaSwag": 86.48, + "MMLU": 66.57, + "TruthfulQA": 67.81, + "Winogrande": 84.21, + "GSM8K": 55.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "86818a7076320a0d25d0374b0b6ea096bf4d3404", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "AbacusResearch\/haLLAwa3", + "Average \u2b06\ufe0f": 71.34, + "ARC": 67.83, + "HellaSwag": 87.02, + "MMLU": 64.23, + "TruthfulQA": 63.71, + "Winogrande": 80.51, + "GSM8K": 64.75, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e8bea52793d4ae58e0772918ea1727808565fc75", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Swisslex\/Mixtral-8x7b-DPO-v0.2", + "Average \u2b06\ufe0f": 71.32, + "ARC": 70.39, + "HellaSwag": 87.73, + "MMLU": 71.03, + "TruthfulQA": 58.69, + "Winogrande": 82.56, + "GSM8K": 57.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d668832717c9331884680506c2fc843cd5269ec8", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "RatanRohith\/NeuralMathChat-7B-V0.2", + "Average \u2b06\ufe0f": 71.32, + "ARC": 67.41, + "HellaSwag": 85.78, + "MMLU": 65.09, + "TruthfulQA": 59.09, + "Winogrande": 80.27, + "GSM8K": 70.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "d59d54fb5a8522b8f79df6abb514f03c091dd88f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "brucethemoose\/CapyTessBorosYi-34B-200K-DARE-Ties", + "Average \u2b06\ufe0f": 71.31, + "ARC": 64.93, + "HellaSwag": 85.92, + "MMLU": 76.18, + "TruthfulQA": 55.84, + "Winogrande": 83.03, + "GSM8K": 61.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "0475128a0e57fc103e65c601be75013f28987e62", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rwitz2\/ipo-test", + "Average \u2b06\ufe0f": 71.29, + "ARC": 67.92, + "HellaSwag": 85.99, + "MMLU": 65.05, + "TruthfulQA": 55.87, + "Winogrande": 80.9, + "GSM8K": 72.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b75cf49b19d31ae6c4f8d2a6f3a1484d143024e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aqweteddy\/mistral_tv-neural-marconroni", + "Average \u2b06\ufe0f": 71.27, + "ARC": 69.2, + "HellaSwag": 86.26, + "MMLU": 65.07, + "TruthfulQA": 60.03, + "Winogrande": 80.9, + "GSM8K": 66.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "969f7483d768b15998cd57b392ea1a9718de3b28", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp", + "Average \u2b06\ufe0f": 71.26, + "ARC": 67.92, + "HellaSwag": 86.32, + "MMLU": 65.47, + "TruthfulQA": 56.45, + "Winogrande": 79.72, + "GSM8K": 71.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "b6211b2dc4dcf29ca79ba3d6751b3ad071413eeb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SyedAbdul\/test-7B-slerp", + "Average \u2b06\ufe0f": 71.26, + "ARC": 68.09, + "HellaSwag": 86.08, + "MMLU": 64.57, + "TruthfulQA": 62.6, + "Winogrande": 80.82, + "GSM8K": 65.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8c0acfaea61f49f679feb694c0de57a7f403d44e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Q-bert\/MetaMath-Cybertron-Starling", + "Average \u2b06\ufe0f": 71.25, + "ARC": 67.41, + "HellaSwag": 86.26, + "MMLU": 65.09, + "TruthfulQA": 55.95, + "Winogrande": 81.29, + "GSM8K": 71.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 40.0, + "Available on the hub": true, + "Model sha": "17c8d4cadb814eaef0fab1d93b29cc150f413205", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Riiid\/sheep-duck-llama-2-70b-v1.1", + "Average \u2b06\ufe0f": 71.22, + "ARC": 73.12, + "HellaSwag": 87.77, + "MMLU": 70.77, + "TruthfulQA": 64.55, + "Winogrande": 83.11, + "GSM8K": 47.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "978c3cc8d44ad37eb764a53e026ae1fa8d334eb2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "APMIC\/caigun-lora-model-34B-v2", + "Average \u2b06\ufe0f": 71.19, + "ARC": 65.02, + "HellaSwag": 85.28, + "MMLU": 75.69, + "TruthfulQA": 58.03, + "Winogrande": 83.03, + "GSM8K": 60.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "913eec9411d7886c0e8abe6842ed09d8932bef10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Intel\/neural-chat-7b-v3-3-Slerp", + "Average \u2b06\ufe0f": 71.19, + "ARC": 66.64, + "HellaSwag": 85.43, + "MMLU": 62.19, + "TruthfulQA": 63.2, + "Winogrande": 79.72, + "GSM8K": 69.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "cbd4f663365e40d50ed9834016bf840971b35db5", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EmbeddedLLM\/Mistral-7B-Merge-14-v0.4", + "Average \u2b06\ufe0f": 71.19, + "ARC": 66.81, + "HellaSwag": 86.15, + "MMLU": 65.1, + "TruthfulQA": 58.25, + "Winogrande": 80.03, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "367cfe8d6e046684ba8626444e82d1600c4e78a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/V0201", + "Average \u2b06\ufe0f": 71.18, + "ARC": 67.24, + "HellaSwag": 83.3, + "MMLU": 88.78, + "TruthfulQA": 53.76, + "Winogrande": 80.51, + "GSM8K": 53.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d49bbca7c6d24e025a2e1175b29ad9fb955e0680", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/neural-chat-v3-3-8x7b-MoE", + "Average \u2b06\ufe0f": 71.17, + "ARC": 66.64, + "HellaSwag": 85.43, + "MMLU": 62.22, + "TruthfulQA": 63.2, + "Winogrande": 79.72, + "GSM8K": 69.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ef354e7938f1c38bb1f73f4ee9a7f325ae32fc2e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Jingyu6\/MergeTest-7B-slerp", + "Average \u2b06\ufe0f": 71.17, + "ARC": 67.75, + "HellaSwag": 86.15, + "MMLU": 63.94, + "TruthfulQA": 59.8, + "Winogrande": 79.64, + "GSM8K": 69.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0c089098a27b01d577747f3071531a1a9c9d627c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.17, + "ARC": 67.75, + "HellaSwag": 86.15, + "MMLU": 63.94, + "TruthfulQA": 59.8, + "Winogrande": 79.64, + "GSM8K": 69.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "e3ba53ca9b2171e3c2134cc022eabada932e032c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "abideen\/MonarchCoder-7B", + "Average \u2b06\ufe0f": 71.17, + "ARC": 68.52, + "HellaSwag": 87.3, + "MMLU": 64.65, + "TruthfulQA": 61.21, + "Winogrande": 80.19, + "GSM8K": 65.13, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d5dbca5f010dd7a811e85597bcecdfd848c4ed25", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Deacon-34b-Adapter", + "Average \u2b06\ufe0f": 71.16, + "ARC": 64.76, + "HellaSwag": 85.57, + "MMLU": 76.28, + "TruthfulQA": 56.24, + "Winogrande": 82.95, + "GSM8K": 61.18, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4d1eca338cda2d7ecb0f0ea549819e7116d43178", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/PlatYi-34B-Llama-Q", + "Average \u2b06\ufe0f": 71.13, + "ARC": 65.7, + "HellaSwag": 85.22, + "MMLU": 78.78, + "TruthfulQA": 53.64, + "Winogrande": 83.03, + "GSM8K": 60.42, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "b786e11fafdd446f155fdb14c6112800f210801b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/Mathral", + "Average \u2b06\ufe0f": 71.13, + "ARC": 66.3, + "HellaSwag": 86.17, + "MMLU": 63.27, + "TruthfulQA": 58.79, + "Winogrande": 79.56, + "GSM8K": 72.71, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6c982afd0745eef8105bad500cbb96c4bf676944", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NExtNewChattingAI\/shark_tank_ai_7_b", + "Average \u2b06\ufe0f": 71.1, + "ARC": 66.89, + "HellaSwag": 86.61, + "MMLU": 65.27, + "TruthfulQA": 60.19, + "Winogrande": 81.93, + "GSM8K": 65.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "feafb4e14863e893ee3d6737ac5b07ac5241f452", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "InnerI\/InnerILLM-7B-slerp", + "Average \u2b06\ufe0f": 71.09, + "ARC": 67.58, + "HellaSwag": 86.19, + "MMLU": 64.15, + "TruthfulQA": 59.84, + "Winogrande": 80.11, + "GSM8K": 68.69, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e95ad53ab333c0cc083b927bddaa02f9423afdbb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Samee-ur\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.09, + "ARC": 67.75, + "HellaSwag": 86.17, + "MMLU": 64.05, + "TruthfulQA": 59.85, + "Winogrande": 80.19, + "GSM8K": 68.54, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6814f1994fd78825ac803afc2684f43d6833f1cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zhengr\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.08, + "ARC": 67.41, + "HellaSwag": 86.12, + "MMLU": 64.07, + "TruthfulQA": 59.82, + "Winogrande": 79.79, + "GSM8K": 69.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6a6405b269c94043658c342d3e124aa3ba75d621", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Abhinav7\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.08, + "ARC": 67.41, + "HellaSwag": 86.12, + "MMLU": 64.07, + "TruthfulQA": 59.82, + "Winogrande": 79.79, + "GSM8K": 69.29, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "62eb03a76c4c607afc8524cf725c48fbb6a1827a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FusionNet_SOLAR", + "Average \u2b06\ufe0f": 71.08, + "ARC": 71.59, + "HellaSwag": 88.4, + "MMLU": 65.29, + "TruthfulQA": 69.21, + "Winogrande": 81.06, + "GSM8K": 50.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 15.97, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3757984c0edebf4300a67cf33b9cca53524a057d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dillfrescott\/Nous-Hermes-2-SOLAR-10.7B-x2-MoE", + "Average \u2b06\ufe0f": 71.08, + "ARC": 67.15, + "HellaSwag": 84.83, + "MMLU": 66.52, + "TruthfulQA": 55.85, + "Winogrande": 83.11, + "GSM8K": 68.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "wtfpl", + "#Params (B)": 19.19, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1cd122567a864075ede6c5684902e8dbfd5eed2e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Loyal-Toppy-Bruins-Maid-7B-DARE", + "Average \u2b06\ufe0f": 71.07, + "ARC": 68.86, + "HellaSwag": 86.03, + "MMLU": 64.84, + "TruthfulQA": 61.19, + "Winogrande": 79.72, + "GSM8K": 65.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "d8d01fbb3aaefda39421850c2dabb38e73546a6e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/MetaMath-bagel-34b-v0.2-c1500", + "Average \u2b06\ufe0f": 71.06, + "ARC": 63.91, + "HellaSwag": 82.43, + "MMLU": 74.51, + "TruthfulQA": 53.7, + "Winogrande": 80.98, + "GSM8K": 70.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3a15e50ba671fe6e3e7725d58d101cbb4f4a997f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rufjdk5480\/WestLake-dpo-train-sft-v1", + "Average \u2b06\ufe0f": 71.06, + "ARC": 65.78, + "HellaSwag": 85.76, + "MMLU": 61.8, + "TruthfulQA": 67.8, + "Winogrande": 82.79, + "GSM8K": 62.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fd04d89dac9f3fc8f8f43048c3fad3821b0fada6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/smol_bruin-7b", + "Average \u2b06\ufe0f": 71.05, + "ARC": 67.58, + "HellaSwag": 86.48, + "MMLU": 65.05, + "TruthfulQA": 55.65, + "Winogrande": 81.14, + "GSM8K": 70.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "967dff56741850954a96491979995a4f686eeb05", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "adamo1139\/Yi-34B-200K-AEZAKMI-RAW-1701", + "Average \u2b06\ufe0f": 71.04, + "ARC": 66.81, + "HellaSwag": 85.79, + "MMLU": 75.44, + "TruthfulQA": 57.91, + "Winogrande": 80.35, + "GSM8K": 59.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "46eae309ae80b25832a2e7d21023239ac4acfdb3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/OpenMia-Indo-Mistral-7b-v3", + "Average \u2b06\ufe0f": 71.04, + "ARC": 66.13, + "HellaSwag": 85.47, + "MMLU": 64.03, + "TruthfulQA": 60.05, + "Winogrande": 82.95, + "GSM8K": 67.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7493632477dea1221505b2af5ecde0757106ff86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nisten\/shqiponja-15b-v1", + "Average \u2b06\ufe0f": 71.03, + "ARC": 66.38, + "HellaSwag": 85.26, + "MMLU": 64.62, + "TruthfulQA": 56.81, + "Winogrande": 84.06, + "GSM8K": 69.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 15.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7658da56ac6e3dab2cc147b2e658c8ca892a0781", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Metabird-7B", + "Average \u2b06\ufe0f": 71.03, + "ARC": 69.54, + "HellaSwag": 87.54, + "MMLU": 65.27, + "TruthfulQA": 57.94, + "Winogrande": 83.03, + "GSM8K": 62.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "73b2f79cf8ef066f04980b182c604f77b1aa9ab8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.01, + "ARC": 67.58, + "HellaSwag": 86.17, + "MMLU": 64.06, + "TruthfulQA": 59.84, + "Winogrande": 80.19, + "GSM8K": 68.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "16485f6a8d83061f67515bfe20ed5afe8218c993", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DeepKarkhanis\/Mistral-Passthrough-8L-10B", + "Average \u2b06\ufe0f": 71.01, + "ARC": 67.58, + "HellaSwag": 86.17, + "MMLU": 64.06, + "TruthfulQA": 59.84, + "Winogrande": 80.19, + "GSM8K": 68.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8ebb167b4a27a9d49ec7399baf23eef6226c242d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DeepKarkhanis\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.01, + "ARC": 67.58, + "HellaSwag": 86.17, + "MMLU": 64.06, + "TruthfulQA": 59.84, + "Winogrande": 80.19, + "GSM8K": 68.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6d45f7ca3e55658264d0b0a26b3ef98433335db0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "superlazycoder\/NeuralPipe-7B-slerp", + "Average \u2b06\ufe0f": 71.01, + "ARC": 67.58, + "HellaSwag": 86.17, + "MMLU": 64.06, + "TruthfulQA": 59.84, + "Winogrande": 80.19, + "GSM8K": 68.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "98bf395c8868b226208debc63d67576fdee52528", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/WestuccineBagel-7B-slerp", + "Average \u2b06\ufe0f": 71.01, + "ARC": 69.37, + "HellaSwag": 86.53, + "MMLU": 64.8, + "TruthfulQA": 67.06, + "Winogrande": 82.56, + "GSM8K": 55.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f9f52bdbe8c668ccab4fe8d737b1005bbed14f34", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "adamo1139\/Yi-34B-200K-AEZAKMI-v2", + "Average \u2b06\ufe0f": 71.0, + "ARC": 67.92, + "HellaSwag": 85.61, + "MMLU": 75.22, + "TruthfulQA": 56.74, + "Winogrande": 81.61, + "GSM8K": 58.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "a7c90fa652ca4b65f4e2db1126be0f884748b7ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Nous-Hermes-2-SOLAR-10.7B", + "Average \u2b06\ufe0f": 71.0, + "ARC": 66.72, + "HellaSwag": 84.89, + "MMLU": 66.3, + "TruthfulQA": 55.82, + "Winogrande": 82.79, + "GSM8K": 69.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 158.0, + "Available on the hub": true, + "Model sha": "1a61a6ff49be395db210a5867f02e04abb982971", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "adamo1139\/yi-34b-200k-rawrr-dpo-1", + "Average \u2b06\ufe0f": 70.97, + "ARC": 65.44, + "HellaSwag": 85.69, + "MMLU": 76.09, + "TruthfulQA": 54.0, + "Winogrande": 82.79, + "GSM8K": 61.79, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "2f6396382239da8aa2858393c62f0c5596bd09f0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "chargoddard\/Yi-34B-Llama", + "Average \u2b06\ufe0f": 70.95, + "ARC": 64.59, + "HellaSwag": 85.63, + "MMLU": 76.31, + "TruthfulQA": 55.6, + "Winogrande": 82.79, + "GSM8K": 60.8, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 52.0, + "Available on the hub": true, + "Model sha": "52feecf18e46dd8ed1db297345957007c3e45de1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-mixtral-7bx8-v18.1-32k", + "Average \u2b06\ufe0f": 70.95, + "ARC": 67.66, + "HellaSwag": 84.3, + "MMLU": 70.94, + "TruthfulQA": 56.72, + "Winogrande": 80.98, + "GSM8K": 65.13, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "8a038d22e0d98c31619bb6b7a372b75eeba04d63", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Loyal-Toppy-Bruins-Maid-7B-DARE", + "Average \u2b06\ufe0f": 70.95, + "ARC": 68.69, + "HellaSwag": 86.04, + "MMLU": 64.89, + "TruthfulQA": 61.26, + "Winogrande": 79.56, + "GSM8K": 65.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "d8d01fbb3aaefda39421850c2dabb38e73546a6e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "decapoda-research\/Antares-11b-v2", + "Average \u2b06\ufe0f": 70.94, + "ARC": 69.03, + "HellaSwag": 87.54, + "MMLU": 66.19, + "TruthfulQA": 59.17, + "Winogrande": 83.19, + "GSM8K": 60.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "f8a863749399d6a11898795bb485e721f42b6338", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIDC-ai-business\/Marcoroni-7B-v2", + "Average \u2b06\ufe0f": 70.92, + "ARC": 68.26, + "HellaSwag": 86.27, + "MMLU": 63.39, + "TruthfulQA": 61.96, + "Winogrande": 80.11, + "GSM8K": 65.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3929ff947202a530d89a2287e19873141a0136c5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/WizardLM-Math-70B-v0.1", + "Average \u2b06\ufe0f": 70.92, + "ARC": 67.06, + "HellaSwag": 86.01, + "MMLU": 69.14, + "TruthfulQA": 57.07, + "Winogrande": 81.77, + "GSM8K": 64.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "agpl-3.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "9db040ac186cf2884ca0759fa26474ddf0e69bce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Seraph-openchat-3.5-1210-Slerp", + "Average \u2b06\ufe0f": 70.89, + "ARC": 68.0, + "HellaSwag": 86.13, + "MMLU": 65.5, + "TruthfulQA": 54.12, + "Winogrande": 79.56, + "GSM8K": 72.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ac09a74aec45a021bd144252a1c2ff9c2631b3ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/Draco-8x7B", + "Average \u2b06\ufe0f": 70.89, + "ARC": 65.02, + "HellaSwag": 85.24, + "MMLU": 64.96, + "TruthfulQA": 62.65, + "Winogrande": 80.66, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c5747ec7ba9ca08eda4fd55ea32c67057db7b4d6", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Draco-8x7B", + "Average \u2b06\ufe0f": 70.89, + "ARC": 65.02, + "HellaSwag": 85.24, + "MMLU": 64.96, + "TruthfulQA": 62.65, + "Winogrande": 80.66, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c5747ec7ba9ca08eda4fd55ea32c67057db7b4d6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bhavinjawade\/SuperAligned-Jawade", + "Average \u2b06\ufe0f": 70.86, + "ARC": 71.59, + "HellaSwag": 90.58, + "MMLU": 60.81, + "TruthfulQA": 69.17, + "Winogrande": 83.82, + "GSM8K": 49.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6a500b5beb37580dd001dd0234d15350a5b6020e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rizla\/trrapi-16", + "Average \u2b06\ufe0f": 70.85, + "ARC": 66.38, + "HellaSwag": 85.05, + "MMLU": 64.84, + "TruthfulQA": 56.47, + "Winogrande": 84.14, + "GSM8K": 68.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fb8eee8952ec40b4165feb1a6c1dba3675ab6969", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yunconglong\/7Bx4_DPO_700", + "Average \u2b06\ufe0f": 70.85, + "ARC": 64.68, + "HellaSwag": 86.12, + "MMLU": 62.23, + "TruthfulQA": 68.99, + "Winogrande": 79.72, + "GSM8K": 63.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "51460af315b0fa3ba2a04716879afa7acfaa65f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chanwit\/flux-7b-v0.1", + "Average \u2b06\ufe0f": 70.85, + "ARC": 67.06, + "HellaSwag": 86.18, + "MMLU": 65.4, + "TruthfulQA": 55.05, + "Winogrande": 79.01, + "GSM8K": 72.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "566b7dcfb2d7233d49611bda27ff5430487d1aad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/MiaAffogato-Indo-Mistral-7b", + "Average \u2b06\ufe0f": 70.83, + "ARC": 66.38, + "HellaSwag": 85.43, + "MMLU": 64.11, + "TruthfulQA": 58.18, + "Winogrande": 83.19, + "GSM8K": 67.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "06664239f5a4440eb71ab0892a7c03517d7da9dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/Lelantos-low-tune", + "Average \u2b06\ufe0f": 70.82, + "ARC": 67.06, + "HellaSwag": 86.06, + "MMLU": 64.11, + "TruthfulQA": 61.33, + "Winogrande": 79.56, + "GSM8K": 66.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a0725dc1d3f591f2e9281c02f123fcde0a03c5db", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "01-ai\/Yi-34B-200K", + "Average \u2b06\ufe0f": 70.81, + "ARC": 65.36, + "HellaSwag": 85.58, + "MMLU": 76.06, + "TruthfulQA": 53.64, + "Winogrande": 82.56, + "GSM8K": 61.64, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 226.0, + "Available on the hub": true, + "Model sha": "bb196389dbbfdf271b5564ce840027f8cd3386ef", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Eric111\/MarcoHermes", + "Average \u2b06\ufe0f": 70.79, + "ARC": 66.21, + "HellaSwag": 85.5, + "MMLU": 64.81, + "TruthfulQA": 58.46, + "Winogrande": 80.74, + "GSM8K": 68.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2a404a22c4347275f8727f13be8ca15d1011b317", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Q-bert\/Terminis-7B", + "Average \u2b06\ufe0f": 70.73, + "ARC": 67.92, + "HellaSwag": 86.22, + "MMLU": 64.07, + "TruthfulQA": 67.31, + "Winogrande": 81.29, + "GSM8K": 57.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "c3cde866d7d3da1173be8593c91e5bf143ea616e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beberik\/Nyxene-v3-11B", + "Average \u2b06\ufe0f": 70.72, + "ARC": 69.62, + "HellaSwag": 85.33, + "MMLU": 64.75, + "TruthfulQA": 60.91, + "Winogrande": 80.19, + "GSM8K": 63.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "706e71043ed40e53bfee7f25a3f2b4a8def36ae8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "one-man-army\/una-neural-chat-v3-3-P2-OMA", + "Average \u2b06\ufe0f": 70.72, + "ARC": 67.32, + "HellaSwag": 86.33, + "MMLU": 63.14, + "TruthfulQA": 65.49, + "Winogrande": 79.79, + "GSM8K": 62.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "7bab67e479c192927c4a781efdf5be27eaa315a8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EmbeddedLLM\/Mistral-7B-Merge-02-v0", + "Average \u2b06\ufe0f": 70.69, + "ARC": 67.49, + "HellaSwag": 85.78, + "MMLU": 64.1, + "TruthfulQA": 60.52, + "Winogrande": 79.01, + "GSM8K": 67.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b142b88a1b6f015b6971d75aa191c6d16324d0c1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jan-hq\/stealth-v1.2", + "Average \u2b06\ufe0f": 70.68, + "ARC": 66.38, + "HellaSwag": 86.14, + "MMLU": 64.33, + "TruthfulQA": 54.23, + "Winogrande": 80.74, + "GSM8K": 72.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "b0a2704027bbfd8ae0a5d88a23115b17d1a23d1f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Q-bert\/Merged-AGI-7B", + "Average \u2b06\ufe0f": 70.68, + "ARC": 68.6, + "HellaSwag": 86.16, + "MMLU": 65.02, + "TruthfulQA": 60.24, + "Winogrande": 80.66, + "GSM8K": 63.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "7b818236625de433802bfe8b32ab8b17a7e58912", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "chargoddard\/internlm2-20b-llama", + "Average \u2b06\ufe0f": 70.66, + "ARC": 64.59, + "HellaSwag": 83.12, + "MMLU": 67.27, + "TruthfulQA": 54.13, + "Winogrande": 84.21, + "GSM8K": 70.66, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.86, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "acf3dfe237a34a1898f57787d531b86497e96777", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Gony_v3.2", + "Average \u2b06\ufe0f": 70.65, + "ARC": 69.45, + "HellaSwag": 86.91, + "MMLU": 70.68, + "TruthfulQA": 58.81, + "Winogrande": 80.98, + "GSM8K": 57.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5fd0b772372a0d908279db56c5bec064e842e029", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "chargoddard\/internlm2-20b-llama", + "Average \u2b06\ufe0f": 70.61, + "ARC": 64.68, + "HellaSwag": 83.16, + "MMLU": 67.17, + "TruthfulQA": 54.17, + "Winogrande": 84.29, + "GSM8K": 70.2, + "Type": "pretrained", + "Architecture": "L;l;a;m;a;F;o;r;C;a;u;s;a;l;L;M", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.86, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "acf3dfe237a34a1898f57787d531b86497e96777", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/strix-rufipes-70b", + "Average \u2b06\ufe0f": 70.61, + "ARC": 71.33, + "HellaSwag": 87.86, + "MMLU": 69.13, + "TruthfulQA": 56.72, + "Winogrande": 84.77, + "GSM8K": 53.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ecb80c1bd98fae238ff5c61d41e75daa4c16a02c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "sethuiyer\/Diana-7B", + "Average \u2b06\ufe0f": 70.6, + "ARC": 68.34, + "HellaSwag": 86.73, + "MMLU": 64.58, + "TruthfulQA": 60.55, + "Winogrande": 80.19, + "GSM8K": 63.23, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "09f1c9e78c1e73a00278ce864470c4ffb35f626d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/dolphin-2.2-70b", + "Average \u2b06\ufe0f": 70.6, + "ARC": 70.05, + "HellaSwag": 85.97, + "MMLU": 69.18, + "TruthfulQA": 60.14, + "Winogrande": 81.45, + "GSM8K": 56.79, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6a2ddfb2ddde603dae91420db019682378aa9d5e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Q-bert\/MetaMath-Cybertron", + "Average \u2b06\ufe0f": 70.6, + "ARC": 66.47, + "HellaSwag": 85.54, + "MMLU": 63.71, + "TruthfulQA": 57.71, + "Winogrande": 79.64, + "GSM8K": 70.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "4fca0e0002db56237fc155f572a34204229e9620", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DrNicefellow\/ChatAllInOne-Yi-34B-200K-V1", + "Average \u2b06\ufe0f": 70.56, + "ARC": 65.96, + "HellaSwag": 84.53, + "MMLU": 74.13, + "TruthfulQA": 56.96, + "Winogrande": 82.72, + "GSM8K": 59.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "d3fb17cdd012a7d532a49adaf798203c6524908d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DrNicefellow\/ChatAllInOne-Yi-34B-200K-V1", + "Average \u2b06\ufe0f": 70.55, + "ARC": 65.96, + "HellaSwag": 84.58, + "MMLU": 73.95, + "TruthfulQA": 56.82, + "Winogrande": 82.48, + "GSM8K": 59.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "d3fb17cdd012a7d532a49adaf798203c6524908d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "one-man-army\/una-neural-chat-v3-3-P2-OMA", + "Average \u2b06\ufe0f": 70.55, + "ARC": 67.24, + "HellaSwag": 86.34, + "MMLU": 63.18, + "TruthfulQA": 65.48, + "Winogrande": 79.64, + "GSM8K": 61.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "7bab67e479c192927c4a781efdf5be27eaa315a8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "sethuiyer\/Eida_10.7B", + "Average \u2b06\ufe0f": 70.54, + "ARC": 70.9, + "HellaSwag": 87.36, + "MMLU": 64.3, + "TruthfulQA": 71.33, + "Winogrande": 81.22, + "GSM8K": 48.14, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9cc692ef0d0821ef113ad175141632d2efad4b33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenPipe\/mistral-ft-optimized-1227", + "Average \u2b06\ufe0f": 70.54, + "ARC": 67.06, + "HellaSwag": 85.85, + "MMLU": 65.19, + "TruthfulQA": 54.57, + "Winogrande": 78.85, + "GSM8K": 71.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 68.0, + "Available on the hub": true, + "Model sha": "a305e828aa2ef0f547e7037edf14bda54b78b210", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KaeriJenti\/kaori-70b-v1", + "Average \u2b06\ufe0f": 70.54, + "ARC": 69.8, + "HellaSwag": 87.36, + "MMLU": 70.82, + "TruthfulQA": 58.81, + "Winogrande": 84.06, + "GSM8K": 52.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fcce042311a54925ae4acdbe33cff535859300b2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "giraffe176\/Open_Maid_Samantha_Hermes_Orca_dare_ties", + "Average \u2b06\ufe0f": 70.53, + "ARC": 67.75, + "HellaSwag": 86.39, + "MMLU": 64.6, + "TruthfulQA": 57.97, + "Winogrande": 81.14, + "GSM8K": 65.35, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f124dfbc767e7ece3fe5f209a0768e69d8024290", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "giraffe176\/Open_Hermes_Maid_Sam_Mistral_dtv0.1", + "Average \u2b06\ufe0f": 70.53, + "ARC": 67.75, + "HellaSwag": 86.39, + "MMLU": 64.6, + "TruthfulQA": 57.97, + "Winogrande": 81.14, + "GSM8K": 65.35, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a141139153dc0804e288e951fb7e777783872946", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xenon1\/Eclipse-13B-dpo", + "Average \u2b06\ufe0f": 70.53, + "ARC": 64.59, + "HellaSwag": 85.0, + "MMLU": 64.85, + "TruthfulQA": 54.76, + "Winogrande": 84.61, + "GSM8K": 69.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c5f4f9175e92e08ce06a01fc2e5ece22ac3c409d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "s3nh\/Mistral_Sonyichi-7B-slerp", + "Average \u2b06\ufe0f": 70.52, + "ARC": 67.49, + "HellaSwag": 86.43, + "MMLU": 63.58, + "TruthfulQA": 63.25, + "Winogrande": 78.53, + "GSM8K": 63.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "openrail", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d6605744836a770190389a73d31440362c81f41e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Pallas-0.2", + "Average \u2b06\ufe0f": 70.51, + "ARC": 64.59, + "HellaSwag": 83.44, + "MMLU": 75.53, + "TruthfulQA": 55.29, + "Winogrande": 81.61, + "GSM8K": 62.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "2a367db35e91a1cac5abad8e5101e85d391e0551", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChuckMcSneed\/Gembo-v1-70b", + "Average \u2b06\ufe0f": 70.51, + "ARC": 71.25, + "HellaSwag": 86.98, + "MMLU": 70.85, + "TruthfulQA": 63.25, + "Winogrande": 80.51, + "GSM8K": 50.19, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "b3767a69eb9b36aba96be586958391c45b695ff4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenPipe\/mistral-ft-optimized-1227", + "Average \u2b06\ufe0f": 70.5, + "ARC": 67.24, + "HellaSwag": 85.9, + "MMLU": 65.17, + "TruthfulQA": 54.51, + "Winogrande": 78.85, + "GSM8K": 71.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 68.0, + "Available on the hub": true, + "Model sha": "a305e828aa2ef0f547e7037edf14bda54b78b210", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "RaduGabriel\/SirUkrainian", + "Average \u2b06\ufe0f": 70.5, + "ARC": 67.32, + "HellaSwag": 85.54, + "MMLU": 63.14, + "TruthfulQA": 68.74, + "Winogrande": 81.53, + "GSM8K": 56.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "556e8d80252fb83b65ddb71e866bbb9eaffd17cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Pallas-0.2", + "Average \u2b06\ufe0f": 70.49, + "ARC": 64.51, + "HellaSwag": 83.47, + "MMLU": 75.64, + "TruthfulQA": 55.27, + "Winogrande": 81.37, + "GSM8K": 62.7, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "2a367db35e91a1cac5abad8e5101e85d391e0551", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "freeCS-dot-org\/ThetaWave-7B-v0.1", + "Average \u2b06\ufe0f": 70.49, + "ARC": 68.09, + "HellaSwag": 86.33, + "MMLU": 62.11, + "TruthfulQA": 71.68, + "Winogrande": 79.08, + "GSM8K": 55.65, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f73322bf5c95ba61e9e72efdf930ec67055ecf57", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/JustToSuffer-7B-slerp", + "Average \u2b06\ufe0f": 70.48, + "ARC": 68.94, + "HellaSwag": 86.79, + "MMLU": 64.66, + "TruthfulQA": 62.69, + "Winogrande": 80.03, + "GSM8K": 59.74, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9253d79afb8ee7441804448f6542878a6e05f098", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Swisslex\/Mixtral-8x7b-DPO-v0.1", + "Average \u2b06\ufe0f": 70.45, + "ARC": 70.9, + "HellaSwag": 87.61, + "MMLU": 70.66, + "TruthfulQA": 57.38, + "Winogrande": 82.4, + "GSM8K": 53.75, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5de7f1532fdeaf36f7ffb180ff510efac2ac90e4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/Konstanta-Gamma-10.9B", + "Average \u2b06\ufe0f": 70.44, + "ARC": 68.26, + "HellaSwag": 87.38, + "MMLU": 64.5, + "TruthfulQA": 64.18, + "Winogrande": 80.98, + "GSM8K": 57.32, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.95, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f9457027c05107889a948a6f3b99ba428e859d48", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/NewtoccineLake-slerp-7B", + "Average \u2b06\ufe0f": 70.43, + "ARC": 68.69, + "HellaSwag": 85.98, + "MMLU": 64.62, + "TruthfulQA": 59.95, + "Winogrande": 81.53, + "GSM8K": 61.79, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "de29875ebd6471c5776813f1f1caa0231df0d699", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-7B-v2.01", + "Average \u2b06\ufe0f": 70.43, + "ARC": 68.86, + "HellaSwag": 86.12, + "MMLU": 63.9, + "TruthfulQA": 63.5, + "Winogrande": 80.51, + "GSM8K": 59.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "438642201e2a91e9456d2a8ca1d7443e5ec55a40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/BagelLake-7B-slerp", + "Average \u2b06\ufe0f": 70.41, + "ARC": 68.26, + "HellaSwag": 85.07, + "MMLU": 64.3, + "TruthfulQA": 63.76, + "Winogrande": 83.66, + "GSM8K": 57.39, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "24a9ebb9bb40e2a9fff9097845980b4dbb53f330", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-8x7B-MoE", + "Average \u2b06\ufe0f": 70.4, + "ARC": 68.77, + "HellaSwag": 86.11, + "MMLU": 63.86, + "TruthfulQA": 63.5, + "Winogrande": 80.51, + "GSM8K": 59.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4df8e16bb4adeff6cfdd6c064819650ae27ff8fa", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "openagi-project\/OpenAGI-7B-v0.2", + "Average \u2b06\ufe0f": 70.37, + "ARC": 68.52, + "HellaSwag": 86.03, + "MMLU": 63.02, + "TruthfulQA": 72.04, + "Winogrande": 79.16, + "GSM8K": 53.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "eb1146479e3912ab02461654d93a907c5b90a059", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Test157t\/Prima-Pastacles-7b-128k", + "Average \u2b06\ufe0f": 70.36, + "ARC": 68.09, + "HellaSwag": 86.57, + "MMLU": 64.58, + "TruthfulQA": 62.51, + "Winogrande": 81.06, + "GSM8K": 59.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "1be449dd843bcc1c9a1bdf4d2e3f506ddd189c10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HyperbeeAI\/Tulpar-7b-v2", + "Average \u2b06\ufe0f": 70.36, + "ARC": 67.49, + "HellaSwag": 84.89, + "MMLU": 63.02, + "TruthfulQA": 63.65, + "Winogrande": 79.48, + "GSM8K": 63.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b466113c7726cfcd98ba602ec4000ae323f112fa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChuckMcSneed\/Gembo-v1.1-70b", + "Average \u2b06\ufe0f": 70.35, + "ARC": 70.99, + "HellaSwag": 86.9, + "MMLU": 70.63, + "TruthfulQA": 62.45, + "Winogrande": 80.51, + "GSM8K": 50.64, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c9755408254f3516e67e3e6a0716d6badb2d2841", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "openagi-project\/OpenAGI-7B-v0.1", + "Average \u2b06\ufe0f": 70.34, + "ARC": 66.72, + "HellaSwag": 86.13, + "MMLU": 63.53, + "TruthfulQA": 69.55, + "Winogrande": 79.48, + "GSM8K": 56.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "36123d69a4dc871fe962337e997c5c5ccf6e739b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openagi-project\/OpenAGI-7B-v0.1-test-ada", + "Average \u2b06\ufe0f": 70.34, + "ARC": 66.72, + "HellaSwag": 86.13, + "MMLU": 63.53, + "TruthfulQA": 69.55, + "Winogrande": 79.48, + "GSM8K": 56.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "635f0d8e3bc9fe0c5fb3954614cef0a324d0bfc8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ValiantLabs\/ShiningValiant", + "Average \u2b06\ufe0f": 70.34, + "ARC": 68.69, + "HellaSwag": 87.31, + "MMLU": 69.64, + "TruthfulQA": 55.78, + "Winogrande": 84.14, + "GSM8K": 56.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 72.0, + "Available on the hub": true, + "Model sha": "7c4401cddc462c5f35d8984c90e293faee37bf8e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-mixtral-8x7b-v0.1", + "Average \u2b06\ufe0f": 70.34, + "ARC": 68.09, + "HellaSwag": 85.76, + "MMLU": 71.49, + "TruthfulQA": 55.31, + "Winogrande": 82.08, + "GSM8K": 59.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "30abf8de36252c1e026fe758b8fde5eba960cd2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-mixtral-8x7b-v1", + "Average \u2b06\ufe0f": 70.34, + "ARC": 68.09, + "HellaSwag": 85.76, + "MMLU": 71.49, + "TruthfulQA": 55.31, + "Winogrande": 82.08, + "GSM8K": 59.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "30abf8de36252c1e026fe758b8fde5eba960cd2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Falkor-7b", + "Average \u2b06\ufe0f": 70.33, + "ARC": 68.26, + "HellaSwag": 85.84, + "MMLU": 63.98, + "TruthfulQA": 63.08, + "Winogrande": 80.35, + "GSM8K": 60.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "b2e3c235196ba859b26ee14fb8c86e632bcf3e88", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Novocoders\/Lotus-7B", + "Average \u2b06\ufe0f": 70.32, + "ARC": 66.47, + "HellaSwag": 84.8, + "MMLU": 64.64, + "TruthfulQA": 55.57, + "Winogrande": 82.16, + "GSM8K": 68.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "58eb22fb92d6dfed4c0b582f1dd4573cdf7cca4a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "one-man-army\/una-neural-chat-v3-3-P1-OMA", + "Average \u2b06\ufe0f": 70.32, + "ARC": 66.81, + "HellaSwag": 85.92, + "MMLU": 63.37, + "TruthfulQA": 64.35, + "Winogrande": 79.64, + "GSM8K": 61.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "014600373086ea46c7cdc4754c984a804b28a070", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AtAndDev\/CapybaraMarcoroni-7B", + "Average \u2b06\ufe0f": 70.32, + "ARC": 65.02, + "HellaSwag": 84.81, + "MMLU": 65.2, + "TruthfulQA": 57.07, + "Winogrande": 81.14, + "GSM8K": 68.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "50dc156e0c016e4e1bc84ff8d067b3eb88d36310", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "RaduGabriel\/MUZD", + "Average \u2b06\ufe0f": 70.32, + "ARC": 66.81, + "HellaSwag": 86.54, + "MMLU": 62.87, + "TruthfulQA": 65.73, + "Winogrande": 81.37, + "GSM8K": 58.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5c19bc74d2b01b36a96e1287103bf56be3e6ad03", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "VAGOsolutions\/SauerkrautLM-7b-LaserChat", + "Average \u2b06\ufe0f": 70.32, + "ARC": 67.58, + "HellaSwag": 83.58, + "MMLU": 64.93, + "TruthfulQA": 56.08, + "Winogrande": 80.9, + "GSM8K": 68.84, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "03b8cef6f31e2a6816186d1bddadd938c19f1cd7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-34B-v1.5b", + "Average \u2b06\ufe0f": 70.31, + "ARC": 63.91, + "HellaSwag": 84.43, + "MMLU": 76.26, + "TruthfulQA": 53.12, + "Winogrande": 81.29, + "GSM8K": 62.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "9f17f1c66209dd923751a5242f33f0dfded9071f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Silicon-Maid-7B", + "Average \u2b06\ufe0f": 70.31, + "ARC": 68.17, + "HellaSwag": 86.52, + "MMLU": 64.58, + "TruthfulQA": 61.64, + "Winogrande": 79.01, + "GSM8K": 61.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 63.0, + "Available on the hub": true, + "Model sha": "ecb260368921c5dfe16c007e871d29de9d561996", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "chanwit\/flux-7b-v0.2", + "Average \u2b06\ufe0f": 70.3, + "ARC": 66.55, + "HellaSwag": 86.12, + "MMLU": 65.38, + "TruthfulQA": 51.8, + "Winogrande": 79.32, + "GSM8K": 72.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6ff053b441ac4efec7b92828c64a8a6f1649a6f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Eric111\/openchat-3.5-0106-128k-DPO", + "Average \u2b06\ufe0f": 70.3, + "ARC": 68.09, + "HellaSwag": 83.82, + "MMLU": 64.74, + "TruthfulQA": 56.34, + "Winogrande": 81.53, + "GSM8K": 67.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "136e3467ffdc6d44ac2d48a35f874238022b9040", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "APMIC\/caigun-lora-model-34B-v3", + "Average \u2b06\ufe0f": 70.27, + "ARC": 66.89, + "HellaSwag": 84.77, + "MMLU": 75.41, + "TruthfulQA": 56.47, + "Winogrande": 83.58, + "GSM8K": 54.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e5a17f9fbd39259cc166c8c75b81be2b41f029f1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Maylin-7b", + "Average \u2b06\ufe0f": 70.26, + "ARC": 66.81, + "HellaSwag": 86.4, + "MMLU": 64.73, + "TruthfulQA": 60.24, + "Winogrande": 79.64, + "GSM8K": 63.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c5fa9f4812daf2538e3e052c0346d9efb321c650", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/MetaMath-Chupacabra-7B-v2.01-Slerp", + "Average \u2b06\ufe0f": 70.26, + "ARC": 65.96, + "HellaSwag": 85.46, + "MMLU": 63.82, + "TruthfulQA": 56.16, + "Winogrande": 80.03, + "GSM8K": 70.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e94f61cd30c697bf1b38c64fa69e93a247f3b58d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "v1olet\/v1olet_merged_dpo_7B", + "Average \u2b06\ufe0f": 70.26, + "ARC": 71.33, + "HellaSwag": 87.34, + "MMLU": 64.13, + "TruthfulQA": 63.37, + "Winogrande": 82.0, + "GSM8K": 53.37, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "299011bf619d9b89f4e545dde8ef7853ec0557b6", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Radu1999\/MisterUkrainian", + "Average \u2b06\ufe0f": 70.23, + "ARC": 67.83, + "HellaSwag": 86.32, + "MMLU": 62.53, + "TruthfulQA": 67.26, + "Winogrande": 80.51, + "GSM8K": 56.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c828c2831c162fa80a5faec73de6b87551bfb6fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/SynthIA-70B-v1.5", + "Average \u2b06\ufe0f": 70.23, + "ARC": 69.37, + "HellaSwag": 86.97, + "MMLU": 69.16, + "TruthfulQA": 57.4, + "Winogrande": 83.66, + "GSM8K": 54.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "40773af947d39495841d825337fdbc7ca977ef1f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Pallas-0.5-LASER-0.1", + "Average \u2b06\ufe0f": 70.23, + "ARC": 64.68, + "HellaSwag": 83.49, + "MMLU": 74.94, + "TruthfulQA": 56.78, + "Winogrande": 81.29, + "GSM8K": 60.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "bc07f9084ad43d2455f12f1707a3c14f1a1de1d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Pallas-0.5", + "Average \u2b06\ufe0f": 70.22, + "ARC": 64.76, + "HellaSwag": 83.46, + "MMLU": 75.01, + "TruthfulQA": 56.88, + "Winogrande": 81.29, + "GSM8K": 59.89, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "4b7aa4e48f3208ab39f6640aa4cc98b1d5eff7e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/MetaMath-Chupacabra-7B-v2.01-Slerp", + "Average \u2b06\ufe0f": 70.21, + "ARC": 66.13, + "HellaSwag": 85.46, + "MMLU": 63.92, + "TruthfulQA": 56.15, + "Winogrande": 79.48, + "GSM8K": 70.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dcc6fff61bfd608d8e14a040dff22cd8dae78b1e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "rombodawg\/Everyone-LLM-7b-Base", + "Average \u2b06\ufe0f": 70.21, + "ARC": 66.38, + "HellaSwag": 86.02, + "MMLU": 64.94, + "TruthfulQA": 57.89, + "Winogrande": 80.43, + "GSM8K": 65.58, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "unknown", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "194a54e6d8ee1ef256e2c57c87ba1f76185663b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/MetaMath-Tulpar-7b-v2-Slerp", + "Average \u2b06\ufe0f": 70.2, + "ARC": 65.61, + "HellaSwag": 85.16, + "MMLU": 63.49, + "TruthfulQA": 56.5, + "Winogrande": 79.48, + "GSM8K": 70.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "41612eecf338ae2b1cbb63a3729ce7b125c6ca3c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/OpenHermes-2.5-neural-chat-v3-2-Slerp", + "Average \u2b06\ufe0f": 70.2, + "ARC": 67.49, + "HellaSwag": 85.42, + "MMLU": 64.13, + "TruthfulQA": 61.05, + "Winogrande": 80.03, + "GSM8K": 63.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bf9ef6df7732dbef3cd0001d9e5cba846cb47306", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rishiraj\/oswald-7b", + "Average \u2b06\ufe0f": 70.19, + "ARC": 66.38, + "HellaSwag": 85.18, + "MMLU": 65.34, + "TruthfulQA": 54.07, + "Winogrande": 80.9, + "GSM8K": 69.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "43326649a8b8b7a43cc4a6d15262625508a50dd2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hfl\/chinese-mixtral-instruct", + "Average \u2b06\ufe0f": 70.19, + "ARC": 67.75, + "HellaSwag": 85.67, + "MMLU": 71.53, + "TruthfulQA": 57.46, + "Winogrande": 83.11, + "GSM8K": 55.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "219c9d65843f4c7356e5efffe399a7208e0dea25", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jeiku\/Luna_7B", + "Average \u2b06\ufe0f": 70.17, + "ARC": 68.86, + "HellaSwag": 86.28, + "MMLU": 64.06, + "TruthfulQA": 58.09, + "Winogrande": 79.08, + "GSM8K": 64.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "29751a19842fd9cae038b120dc77793b63cda663", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/ToppyLake-Bagel-7B-slerp", + "Average \u2b06\ufe0f": 70.14, + "ARC": 67.66, + "HellaSwag": 85.7, + "MMLU": 64.87, + "TruthfulQA": 61.74, + "Winogrande": 83.19, + "GSM8K": 57.7, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f827b067ce4bec3cecb4bf88fb8ec2c244af6803", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_Gony_v0.2", + "Average \u2b06\ufe0f": 70.13, + "ARC": 68.86, + "HellaSwag": 86.61, + "MMLU": 70.33, + "TruthfulQA": 59.46, + "Winogrande": 82.4, + "GSM8K": 53.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ec7ea7c16e1a8b5968cab37aab70d926c8ec341d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Newton-OpenHermes-2.5-neural-chat-v3-3-Slerp", + "Average \u2b06\ufe0f": 70.13, + "ARC": 68.77, + "HellaSwag": 85.0, + "MMLU": 65.06, + "TruthfulQA": 56.84, + "Winogrande": 80.11, + "GSM8K": 64.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "27d3bd02299580f326cc358d6d98e06a950d937e", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "adamo1139\/Yi-34B-200K-AEZAKMI-RAW-2301", + "Average \u2b06\ufe0f": 70.12, + "ARC": 66.04, + "HellaSwag": 84.7, + "MMLU": 74.89, + "TruthfulQA": 56.89, + "Winogrande": 81.14, + "GSM8K": 57.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "32621cf1ace03f976b1a73f899817a76a4111bdb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp", + "Average \u2b06\ufe0f": 70.11, + "ARC": 64.59, + "HellaSwag": 85.39, + "MMLU": 64.27, + "TruthfulQA": 55.14, + "Winogrande": 79.64, + "GSM8K": 71.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "111ae8b3fb38d550a32f04dbd977f8cd447a3a92", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-34B-v1.4", + "Average \u2b06\ufe0f": 70.11, + "ARC": 64.59, + "HellaSwag": 83.37, + "MMLU": 75.02, + "TruthfulQA": 56.79, + "Winogrande": 81.22, + "GSM8K": 59.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "173d834656c3965cbaa49be6aab0772c3ce57821", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "upstage\/SOLAR-0-70b-16bit", + "Average \u2b06\ufe0f": 70.11, + "ARC": 71.08, + "HellaSwag": 87.89, + "MMLU": 70.58, + "TruthfulQA": 62.25, + "Winogrande": 83.58, + "GSM8K": 45.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 250.0, + "Available on the hub": false, + "Model sha": "5f9c77b2c0397cf83d2f97740483f107c7109e8c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beberik\/Lonepino-11B", + "Average \u2b06\ufe0f": 70.1, + "ARC": 68.26, + "HellaSwag": 84.57, + "MMLU": 63.76, + "TruthfulQA": 63.45, + "Winogrande": 78.93, + "GSM8K": 61.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "392a0d8806638a235020b2146d83628b19516be5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/Westuccine-7B-slerp", + "Average \u2b06\ufe0f": 70.08, + "ARC": 69.37, + "HellaSwag": 87.34, + "MMLU": 63.8, + "TruthfulQA": 69.34, + "Winogrande": 82.08, + "GSM8K": 48.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "44bf54f7466a508e4e82883f0cbc8aba9aec85c6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Pallas-0.4", + "Average \u2b06\ufe0f": 70.08, + "ARC": 63.65, + "HellaSwag": 83.3, + "MMLU": 74.93, + "TruthfulQA": 57.26, + "Winogrande": 80.43, + "GSM8K": 60.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "2cef301d3afa127217c000f2fdc4c527dfa6145e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/MetaMath-Tulpar-7b-v2-Slerp", + "Average \u2b06\ufe0f": 70.07, + "ARC": 65.96, + "HellaSwag": 85.11, + "MMLU": 63.37, + "TruthfulQA": 56.44, + "Winogrande": 79.08, + "GSM8K": 70.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "644e2ca7db569c38a2bf06077fd8ee6d04f3edba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Pallas-0.3", + "Average \u2b06\ufe0f": 70.06, + "ARC": 63.74, + "HellaSwag": 83.3, + "MMLU": 75.08, + "TruthfulQA": 57.31, + "Winogrande": 80.66, + "GSM8K": 60.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1207a09c7bd4539bcefce62e1376495b0761b08a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GritLM\/GritLM-8x7B", + "Average \u2b06\ufe0f": 70.06, + "ARC": 67.83, + "HellaSwag": 86.42, + "MMLU": 71.48, + "TruthfulQA": 49.37, + "Winogrande": 82.79, + "GSM8K": 62.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "7f089b13e3345510281733ca1e6ff871b5b4bc76", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ICBU-NPU\/FashionGPT-70B-V1.1", + "Average \u2b06\ufe0f": 70.05, + "ARC": 71.76, + "HellaSwag": 88.2, + "MMLU": 70.99, + "TruthfulQA": 65.26, + "Winogrande": 82.64, + "GSM8K": 41.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "05941a3eaacff0dead79b09d2175b5d7b98c525b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Pallas-0.4", + "Average \u2b06\ufe0f": 70.04, + "ARC": 63.65, + "HellaSwag": 83.3, + "MMLU": 75.11, + "TruthfulQA": 57.29, + "Winogrande": 80.58, + "GSM8K": 60.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "2cef301d3afa127217c000f2fdc4c527dfa6145e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/OpenMia-Indo-Engineering", + "Average \u2b06\ufe0f": 70.03, + "ARC": 67.15, + "HellaSwag": 85.01, + "MMLU": 62.86, + "TruthfulQA": 57.94, + "Winogrande": 82.32, + "GSM8K": 64.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cac4a2663504ccf1ca8975787a4b99df50b68bd1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "indischepartij\/OpenMia-Indo-Engineering-7b", + "Average \u2b06\ufe0f": 70.03, + "ARC": 67.15, + "HellaSwag": 85.01, + "MMLU": 62.86, + "TruthfulQA": 57.94, + "Winogrande": 82.32, + "GSM8K": 64.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6bff9bd6e953c6354473402f8b0e43e95a421f43", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "flemmingmiguel\/Distilled-HermesChat-7B", + "Average \u2b06\ufe0f": 70.02, + "ARC": 67.49, + "HellaSwag": 85.21, + "MMLU": 65.22, + "TruthfulQA": 54.77, + "Winogrande": 80.11, + "GSM8K": 67.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e7ca19cecb52c40f0f6bb31cfa258fad0c004dfa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Pallas-0.5-LASER-0.2", + "Average \u2b06\ufe0f": 70.01, + "ARC": 64.68, + "HellaSwag": 83.49, + "MMLU": 74.84, + "TruthfulQA": 56.76, + "Winogrande": 81.37, + "GSM8K": 58.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9119f34f298645df22e0e042f6631af8f67f4b33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "RaduGabriel\/MUZ", + "Average \u2b06\ufe0f": 70.01, + "ARC": 66.38, + "HellaSwag": 86.38, + "MMLU": 63.03, + "TruthfulQA": 64.18, + "Winogrande": 81.77, + "GSM8K": 58.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "56f4a9b2f7fcc6891536de338fdb4b302a1fbcfa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/RolePlayLake-7B-Toxic", + "Average \u2b06\ufe0f": 70.0, + "ARC": 66.98, + "HellaSwag": 84.86, + "MMLU": 63.79, + "TruthfulQA": 56.54, + "Winogrande": 82.24, + "GSM8K": 65.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "5aa57df9a1490c1eda582ac59919476e3f34a1ea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "flemmingmiguel\/Mistrality-7B", + "Average \u2b06\ufe0f": 69.97, + "ARC": 66.55, + "HellaSwag": 85.82, + "MMLU": 64.63, + "TruthfulQA": 56.8, + "Winogrande": 79.32, + "GSM8K": 66.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "05e7408486426ab8c8ed595945454eb181ba6eb0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Solstice-11B-v1", + "Average \u2b06\ufe0f": 69.97, + "ARC": 70.56, + "HellaSwag": 87.39, + "MMLU": 65.98, + "TruthfulQA": 61.98, + "Winogrande": 83.11, + "GSM8K": 50.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 11.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "cb2392b7d1913ea071c56ba4224966c70109a3c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Eurdem\/megatron_1.1_MoE_2x7B", + "Average \u2b06\ufe0f": 69.94, + "ARC": 65.53, + "HellaSwag": 84.52, + "MMLU": 65.02, + "TruthfulQA": 51.58, + "Winogrande": 81.53, + "GSM8K": 71.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "21d9b8365b6e9cc9ece2f27e75d7085c0359f119", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/openchat-nectar-0.1", + "Average \u2b06\ufe0f": 69.94, + "ARC": 66.21, + "HellaSwag": 82.99, + "MMLU": 65.17, + "TruthfulQA": 54.22, + "Winogrande": 81.37, + "GSM8K": 69.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cf913c9f807a9bdbe606ac4bf445d93a082a118c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp", + "Average \u2b06\ufe0f": 69.92, + "ARC": 64.59, + "HellaSwag": 85.37, + "MMLU": 64.29, + "TruthfulQA": 55.14, + "Winogrande": 79.08, + "GSM8K": 71.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f209799cbf4f782e1c6352e427599e2f8a6038ad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sethuiyer\/MedleyMD", + "Average \u2b06\ufe0f": 69.89, + "ARC": 66.47, + "HellaSwag": 86.06, + "MMLU": 65.1, + "TruthfulQA": 52.46, + "Winogrande": 80.27, + "GSM8K": 68.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ce34d7174f0522f91723bc47419d60fbaec659cd", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Pallas-0.3", + "Average \u2b06\ufe0f": 69.88, + "ARC": 63.57, + "HellaSwag": 83.36, + "MMLU": 75.09, + "TruthfulQA": 57.32, + "Winogrande": 80.19, + "GSM8K": 59.74, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1207a09c7bd4539bcefce62e1376495b0761b08a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Ba2han\/BruinsV2-OpHermesNeu-11B", + "Average \u2b06\ufe0f": 69.88, + "ARC": 68.09, + "HellaSwag": 84.7, + "MMLU": 64.19, + "TruthfulQA": 62.76, + "Winogrande": 79.48, + "GSM8K": 60.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "9a5567cf04d6bd8bbd77743f303ce7ecebec78c5", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/PlatYi-34B-Q", + "Average \u2b06\ufe0f": 69.86, + "ARC": 66.89, + "HellaSwag": 85.14, + "MMLU": 77.66, + "TruthfulQA": 53.03, + "Winogrande": 82.48, + "GSM8K": 53.98, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "187442aa0d250dc3c44451d71bf8fcdd556bdb24", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Intel\/neural-chat-7b-v3-3", + "Average \u2b06\ufe0f": 69.83, + "ARC": 66.89, + "HellaSwag": 85.26, + "MMLU": 63.07, + "TruthfulQA": 63.01, + "Winogrande": 79.64, + "GSM8K": 61.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 51.0, + "Available on the hub": true, + "Model sha": "fac83ab297a1c9ecc8affd97c998d864c10b9ff4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-7B-v2.02", + "Average \u2b06\ufe0f": 69.82, + "ARC": 67.66, + "HellaSwag": 83.9, + "MMLU": 61.98, + "TruthfulQA": 64.06, + "Winogrande": 79.4, + "GSM8K": 61.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "24fb5e81b1d39d4358930a1f9054513e9e2d6373", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/A0119", + "Average \u2b06\ufe0f": 69.82, + "ARC": 64.25, + "HellaSwag": 84.74, + "MMLU": 73.1, + "TruthfulQA": 57.96, + "Winogrande": 81.45, + "GSM8K": 57.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "33978688c6fa79679b2cafc504c4f9b9ddccd136", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sumo43\/SOLAR-10.7B-Instruct-DPO-v1.0", + "Average \u2b06\ufe0f": 69.81, + "ARC": 73.12, + "HellaSwag": 89.77, + "MMLU": 64.21, + "TruthfulQA": 73.27, + "Winogrande": 81.93, + "GSM8K": 36.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9e439597e3e788e3ff8a41df54e0dae0acda14a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-M-v1.1", + "Average \u2b06\ufe0f": 69.79, + "ARC": 67.15, + "HellaSwag": 84.76, + "MMLU": 74.5, + "TruthfulQA": 54.8, + "Winogrande": 82.87, + "GSM8K": 54.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "e5a016b08aa507fe9db45436074016928bf6f939", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/MetaMath-neural-chat-7b-v3-2-Slerp", + "Average \u2b06\ufe0f": 69.79, + "ARC": 65.7, + "HellaSwag": 84.51, + "MMLU": 63.5, + "TruthfulQA": 55.23, + "Winogrande": 79.95, + "GSM8K": 69.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "147f8e0526768591a7a119b7ec5b8cb821dbe900", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "internlm\/internlm2-20b", + "Average \u2b06\ufe0f": 69.75, + "ARC": 62.97, + "HellaSwag": 83.21, + "MMLU": 67.58, + "TruthfulQA": 51.27, + "Winogrande": 85.56, + "GSM8K": 67.93, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 30.0, + "Available on the hub": true, + "Model sha": "ec0e34824038c66745ba035f5c1994bd8cb99574", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-70b-3.1.2", + "Average \u2b06\ufe0f": 69.74, + "ARC": 70.14, + "HellaSwag": 86.88, + "MMLU": 69.72, + "TruthfulQA": 59.19, + "Winogrande": 83.11, + "GSM8K": 49.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "2de01b0a516bc64859abb16a948733d616dfb6d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/NinjaDolphin-7B", + "Average \u2b06\ufe0f": 69.74, + "ARC": 65.61, + "HellaSwag": 85.35, + "MMLU": 64.43, + "TruthfulQA": 54.94, + "Winogrande": 80.27, + "GSM8K": 67.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0c2f691bda2d1131ef87767ccf47ba7560578c48", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/MathDolphin-7B", + "Average \u2b06\ufe0f": 69.73, + "ARC": 65.87, + "HellaSwag": 85.49, + "MMLU": 65.02, + "TruthfulQA": 52.92, + "Winogrande": 81.22, + "GSM8K": 67.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6dcfc55a6e845fac45b8dbe3d8c2506fd1348834", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rishiraj\/oswald-4x7b", + "Average \u2b06\ufe0f": 69.72, + "ARC": 65.78, + "HellaSwag": 85.29, + "MMLU": 64.49, + "TruthfulQA": 57.39, + "Winogrande": 79.16, + "GSM8K": 66.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1a2a1c2a7cb0d18ae4af77f99a7adbe8d9718f92", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-M-v1.3", + "Average \u2b06\ufe0f": 69.71, + "ARC": 62.54, + "HellaSwag": 83.95, + "MMLU": 75.36, + "TruthfulQA": 56.03, + "Winogrande": 81.14, + "GSM8K": 59.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "7d733ec8449ec0219a9f499084a94a4248846f7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/SlimMelodicMaid", + "Average \u2b06\ufe0f": 69.7, + "ARC": 67.15, + "HellaSwag": 86.01, + "MMLU": 64.75, + "TruthfulQA": 60.88, + "Winogrande": 78.61, + "GSM8K": 60.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "36c2dfb9e7822dc77a97172a517952bd6c32cd88", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/bagel-34b-v0.2", + "Average \u2b06\ufe0f": 69.7, + "ARC": 68.77, + "HellaSwag": 83.72, + "MMLU": 76.45, + "TruthfulQA": 59.26, + "Winogrande": 83.82, + "GSM8K": 46.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "bc599b31f468d46d873964a58cab78380366d934", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "viethq188\/Rabbit-7B-DPO-Chat", + "Average \u2b06\ufe0f": 69.69, + "ARC": 70.31, + "HellaSwag": 87.43, + "MMLU": 60.5, + "TruthfulQA": 62.18, + "Winogrande": 79.16, + "GSM8K": 58.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "04d42accbc808eec8c020f17392efa07c95ae565", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/openchat-nectar-0.5", + "Average \u2b06\ufe0f": 69.67, + "ARC": 66.72, + "HellaSwag": 83.53, + "MMLU": 65.36, + "TruthfulQA": 52.15, + "Winogrande": 82.08, + "GSM8K": 68.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ba3caf530cbd9caf5c7cc7639cc47a910ed2a120", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/una-cybertron-7b-v2-bf16", + "Average \u2b06\ufe0f": 69.67, + "ARC": 68.26, + "HellaSwag": 85.85, + "MMLU": 63.23, + "TruthfulQA": 64.63, + "Winogrande": 80.98, + "GSM8K": 55.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 115.0, + "Available on the hub": true, + "Model sha": "82599694771bd375c91f36dfdf30c448e4e33b3c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "kidyu\/Moza-7B-v1.0", + "Average \u2b06\ufe0f": 69.66, + "ARC": 66.55, + "HellaSwag": 83.45, + "MMLU": 62.77, + "TruthfulQA": 65.16, + "Winogrande": 77.51, + "GSM8K": 62.55, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5c7f382e59c9a114ea9c9f1f380739fc9e4a9d9e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EmbeddedLLM\/Mistral-7B-Merge-14-v0.3", + "Average \u2b06\ufe0f": 69.66, + "ARC": 65.96, + "HellaSwag": 85.29, + "MMLU": 64.35, + "TruthfulQA": 57.8, + "Winogrande": 78.3, + "GSM8K": 66.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "5ff4289d7f8b7f82f2453c611d737edce6b5efdc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/average-dolphin-8x7B", + "Average \u2b06\ufe0f": 69.64, + "ARC": 68.6, + "HellaSwag": 85.99, + "MMLU": 70.84, + "TruthfulQA": 54.51, + "Winogrande": 81.37, + "GSM8K": 56.56, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b0345662588e8c99d8e504bab894fa41e2199463", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Argetsu", + "Average \u2b06\ufe0f": 69.64, + "ARC": 67.06, + "HellaSwag": 86.32, + "MMLU": 65.55, + "TruthfulQA": 56.46, + "Winogrande": 79.16, + "GSM8K": 63.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e7238116d58f218368ab8e8099abec3cd60237c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/openchat-nectar-0.6", + "Average \u2b06\ufe0f": 69.64, + "ARC": 66.55, + "HellaSwag": 83.22, + "MMLU": 65.19, + "TruthfulQA": 51.9, + "Winogrande": 81.22, + "GSM8K": 69.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "502b55ebd1ca3c159591a9d7e9d9a456ac067e8d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/mixtralmerge-8x7B-rebalanced-test", + "Average \u2b06\ufe0f": 69.61, + "ARC": 68.17, + "HellaSwag": 85.76, + "MMLU": 70.47, + "TruthfulQA": 53.75, + "Winogrande": 81.29, + "GSM8K": 58.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "25093d03a4ee3a58b8eeb4d040b02b3a5f39ca95", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "Steelskull\/Lumosia-MoE-4x10.7", + "Average \u2b06\ufe0f": 69.61, + "ARC": 68.34, + "HellaSwag": 87.13, + "MMLU": 64.38, + "TruthfulQA": 63.81, + "Winogrande": 82.95, + "GSM8K": 51.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "0027074811e8901b63a27cc6d95db66fdafe8c90", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK_gony", + "Average \u2b06\ufe0f": 69.61, + "ARC": 69.11, + "HellaSwag": 86.78, + "MMLU": 69.43, + "TruthfulQA": 56.74, + "Winogrande": 81.53, + "GSM8K": 54.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cb62ef5613e162437a0803cddabc50e21437cd1b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/openchat-nectar-0.11", + "Average \u2b06\ufe0f": 69.59, + "ARC": 66.21, + "HellaSwag": 83.28, + "MMLU": 65.25, + "TruthfulQA": 52.92, + "Winogrande": 81.45, + "GSM8K": 68.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "311304dd45050345aea499c85ddd3af89411513d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "adamo1139\/Yi-34B-200K-AEZAKMI-RAW-2901", + "Average \u2b06\ufe0f": 69.59, + "ARC": 64.93, + "HellaSwag": 84.98, + "MMLU": 73.7, + "TruthfulQA": 55.09, + "Winogrande": 79.32, + "GSM8K": 59.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "85cab3d5de8a4e2907616016eefc846a4ee1da61", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jan-ai\/Pandora-13B-v1", + "Average \u2b06\ufe0f": 69.59, + "ARC": 67.06, + "HellaSwag": 87.53, + "MMLU": 63.65, + "TruthfulQA": 65.77, + "Winogrande": 80.51, + "GSM8K": 52.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "16013ee5682ef9b38c8f27a2c2b78956befdbe52", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/orthorus-125b-moe", + "Average \u2b06\ufe0f": 69.58, + "ARC": 67.66, + "HellaSwag": 85.52, + "MMLU": 68.94, + "TruthfulQA": 56.27, + "Winogrande": 82.32, + "GSM8K": 56.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 125.35, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "3d45ea8340fd5d34db86a7099c2422480fe64533", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "openaccess-ai-collective\/DPOpenHermes-7B-v2", + "Average \u2b06\ufe0f": 69.58, + "ARC": 66.64, + "HellaSwag": 85.22, + "MMLU": 63.64, + "TruthfulQA": 59.22, + "Winogrande": 79.16, + "GSM8K": 63.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "3ebea1710b555a205a04e69c743fe90162df63c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Tippy-Toppy-7b", + "Average \u2b06\ufe0f": 69.58, + "ARC": 66.89, + "HellaSwag": 85.88, + "MMLU": 65.49, + "TruthfulQA": 55.7, + "Winogrande": 78.85, + "GSM8K": 64.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "933d5b9cd8963398e3cc2875ff76e5c57c1877c7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/WizardDolphin-7B", + "Average \u2b06\ufe0f": 69.56, + "ARC": 64.68, + "HellaSwag": 85.86, + "MMLU": 62.75, + "TruthfulQA": 59.28, + "Winogrande": 78.53, + "GSM8K": 66.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5317ae098bdb1d8bbcbc13330aa9b96c5edae3b4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Weyaxi\/Qwen-72B-Llama", + "Average \u2b06\ufe0f": 69.53, + "ARC": 64.85, + "HellaSwag": 83.27, + "MMLU": 73.66, + "TruthfulQA": 57.6, + "Winogrande": 81.53, + "GSM8K": 56.25, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "e94ac9684f607c71f443b7098c434b543cc62fd6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/openchat-nectar-0.4", + "Average \u2b06\ufe0f": 69.52, + "ARC": 66.64, + "HellaSwag": 83.23, + "MMLU": 65.22, + "TruthfulQA": 51.71, + "Winogrande": 81.69, + "GSM8K": 68.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "25eaf0bb01b56d1ce515dd1aa972be468e04c3ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/CognitiveFusion-4x7B-bf16-MoE", + "Average \u2b06\ufe0f": 69.5, + "ARC": 67.41, + "HellaSwag": 86.16, + "MMLU": 65.14, + "TruthfulQA": 67.05, + "Winogrande": 78.69, + "GSM8K": 52.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "40c2fdf46e33f4f84742fff63d5fb46932492e03", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/una-cybertron-7b-v1-fp16", + "Average \u2b06\ufe0f": 69.49, + "ARC": 68.43, + "HellaSwag": 85.42, + "MMLU": 63.34, + "TruthfulQA": 63.28, + "Winogrande": 81.37, + "GSM8K": 55.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "7bf918ddf0878a693f24f39e9f1a520464b44268", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Azazelle\/Silicon-Medley", + "Average \u2b06\ufe0f": 69.49, + "ARC": 67.24, + "HellaSwag": 86.21, + "MMLU": 64.51, + "TruthfulQA": 61.34, + "Winogrande": 79.24, + "GSM8K": 58.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "98e46cc2715fdeead6c6b79307b40682efb83bfc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "splm\/openchat-spin-slimorca-iter0", + "Average \u2b06\ufe0f": 69.49, + "ARC": 67.15, + "HellaSwag": 83.61, + "MMLU": 64.45, + "TruthfulQA": 56.87, + "Winogrande": 81.37, + "GSM8K": 63.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0d2acfc959ca3adb6ea9a122007fac80cb008e4d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/ExtremeDolphin-MoE", + "Average \u2b06\ufe0f": 69.46, + "ARC": 65.1, + "HellaSwag": 86.07, + "MMLU": 63.76, + "TruthfulQA": 57.28, + "Winogrande": 78.69, + "GSM8K": 65.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1983955d7a48548e196a7b725cae4ddccdd7e357", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "DopeorNope\/You_can_cry_Snowman-13B", + "Average \u2b06\ufe0f": 69.46, + "ARC": 69.11, + "HellaSwag": 86.3, + "MMLU": 63.77, + "TruthfulQA": 70.24, + "Winogrande": 80.27, + "GSM8K": 47.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 13.35, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b50693bb4d8965ca9d48ff3c0c21fbfaa524d37c", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/openchat-3.5-0106-laser", + "Average \u2b06\ufe0f": 69.46, + "ARC": 66.04, + "HellaSwag": 83.18, + "MMLU": 65.11, + "TruthfulQA": 52.08, + "Winogrande": 81.45, + "GSM8K": 68.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "56805ed2f93e991f77fa6dd83502daf96aff2c9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "MayaPH\/GodziLLa2-70B", + "Average \u2b06\ufe0f": 69.46, + "ARC": 71.42, + "HellaSwag": 87.53, + "MMLU": 69.88, + "TruthfulQA": 61.54, + "Winogrande": 83.19, + "GSM8K": 43.21, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": true, + "Model sha": "7b78087db07eec97f7b461d10758ece76d685543", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MisterRid\/saulgoodman-2x7b-alpha1", + "Average \u2b06\ufe0f": 69.43, + "ARC": 66.21, + "HellaSwag": 85.36, + "MMLU": 64.95, + "TruthfulQA": 60.06, + "Winogrande": 79.24, + "GSM8K": 60.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b5ad66de184f72fa9525877ea6a62aa7bdc4815c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "01-ai\/Yi-34B", + "Average \u2b06\ufe0f": 69.42, + "ARC": 64.59, + "HellaSwag": 85.69, + "MMLU": 76.35, + "TruthfulQA": 56.23, + "Winogrande": 83.03, + "GSM8K": 50.64, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1187.0, + "Available on the hub": true, + "Model sha": "cd8d59de87ea11c6453ee287ac82e5523f08c8ec", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "adamo1139\/yi-34b-200k-rawrr-dpo-2", + "Average \u2b06\ufe0f": 69.42, + "ARC": 64.68, + "HellaSwag": 84.74, + "MMLU": 75.96, + "TruthfulQA": 46.15, + "Winogrande": 83.19, + "GSM8K": 61.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "6682e3f76d02f280c4a265c9192c5a9e117cfdd4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChuckMcSneed\/WinterGoddess-1.4x-70b-32k", + "Average \u2b06\ufe0f": 69.4, + "ARC": 71.16, + "HellaSwag": 89.12, + "MMLU": 66.42, + "TruthfulQA": 63.87, + "Winogrande": 82.56, + "GSM8K": 43.29, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "136d8ad5d94b8ac02ac7cd4e0b32e09366a550dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rishiraj\/oswald-2x7b", + "Average \u2b06\ufe0f": 69.4, + "ARC": 66.47, + "HellaSwag": 85.46, + "MMLU": 65.2, + "TruthfulQA": 60.06, + "Winogrande": 79.4, + "GSM8K": 59.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "50fa192492461fdfcd8ce1c84e9081891141a5ac", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/Bald-Eagle-7B", + "Average \u2b06\ufe0f": 69.39, + "ARC": 64.51, + "HellaSwag": 84.79, + "MMLU": 64.39, + "TruthfulQA": 54.65, + "Winogrande": 80.98, + "GSM8K": 67.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6f5a38b66c4121b2dae4545ad3b2c42fb2637556", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MisterRid\/saulgoodman-7b-alpha1", + "Average \u2b06\ufe0f": 69.38, + "ARC": 65.7, + "HellaSwag": 85.5, + "MMLU": 65.19, + "TruthfulQA": 61.13, + "Winogrande": 79.01, + "GSM8K": 59.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c417af695d4e3370348e2ef15961884f127f7ff0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Sina-Thor-7b-Merge", + "Average \u2b06\ufe0f": 69.38, + "ARC": 66.21, + "HellaSwag": 85.69, + "MMLU": 65.17, + "TruthfulQA": 50.01, + "Winogrande": 80.51, + "GSM8K": 68.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d2074b9f23665b98362a52ce22ba62d4870985d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "deepseek-ai\/deepseek-llm-67b-base", + "Average \u2b06\ufe0f": 69.38, + "ARC": 65.44, + "HellaSwag": 87.1, + "MMLU": 71.78, + "TruthfulQA": 51.08, + "Winogrande": 84.14, + "GSM8K": 56.71, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 67.0, + "Hub \u2764\ufe0f": 97.0, + "Available on the hub": true, + "Model sha": "c3f813a1121c95488a20132d3a4da89f4a46452f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Sensualize-Mixtral-bf16", + "Average \u2b06\ufe0f": 69.37, + "ARC": 70.14, + "HellaSwag": 86.6, + "MMLU": 70.89, + "TruthfulQA": 54.17, + "Winogrande": 82.4, + "GSM8K": 52.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "50427f68da578b238e3e41b1126704cb0d06fb6a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "sethuiyer\/SynthIQ-7b", + "Average \u2b06\ufe0f": 69.37, + "ARC": 65.87, + "HellaSwag": 85.82, + "MMLU": 64.75, + "TruthfulQA": 57.0, + "Winogrande": 78.69, + "GSM8K": 64.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "32612e89aa87a23f6b1c5c5a9165896e599ca9ca", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/openchat-nectar-0.3", + "Average \u2b06\ufe0f": 69.36, + "ARC": 65.96, + "HellaSwag": 83.15, + "MMLU": 65.46, + "TruthfulQA": 52.38, + "Winogrande": 81.53, + "GSM8K": 67.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cc29b95f9d0bee765206b07e4d9bba05a0fcafb2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "viethq188\/Rabbit-7B-v2-DPO-Chat", + "Average \u2b06\ufe0f": 69.36, + "ARC": 66.13, + "HellaSwag": 85.18, + "MMLU": 62.92, + "TruthfulQA": 67.06, + "Winogrande": 79.24, + "GSM8K": 55.65, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7dae800851457f1dcccf00a2517448c9a9400b15", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "freecs\/ThetaWave-7B", + "Average \u2b06\ufe0f": 69.35, + "ARC": 67.49, + "HellaSwag": 86.01, + "MMLU": 62.26, + "TruthfulQA": 65.26, + "Winogrande": 79.01, + "GSM8K": 56.1, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "21a306726dae52eee662b83fadc9657cef10dd02", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_2-7B-slerp", + "Average \u2b06\ufe0f": 69.34, + "ARC": 66.89, + "HellaSwag": 85.52, + "MMLU": 65.22, + "TruthfulQA": 54.53, + "Winogrande": 82.4, + "GSM8K": 61.49, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d25a34b28ddfbe101b24537647d5db751baf2c9e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-deepseek-67b-v15-base", + "Average \u2b06\ufe0f": 69.34, + "ARC": 66.3, + "HellaSwag": 86.03, + "MMLU": 70.97, + "TruthfulQA": 52.31, + "Winogrande": 83.58, + "GSM8K": 56.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 67.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2717bb85e0cd4c1c4abfa3d4abb7f9b6e55c1322", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "gagan3012\/MetaModel_moe_multilingualv1", + "Average \u2b06\ufe0f": 69.33, + "ARC": 67.58, + "HellaSwag": 84.72, + "MMLU": 63.77, + "TruthfulQA": 61.21, + "Winogrande": 77.35, + "GSM8K": 61.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1b27a5aa3381f82ae99e8187bbd982e319eafd17", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "adamo1139\/Yi-34B-200K-AEZAKMI-RAW-2301-LoRA", + "Average \u2b06\ufe0f": 69.31, + "ARC": 65.96, + "HellaSwag": 83.89, + "MMLU": 74.76, + "TruthfulQA": 57.08, + "Winogrande": 78.69, + "GSM8K": 55.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "533506a750975d612071ab9a56e076d65e65cef4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CallComply\/openchat-3.5-0106-32k", + "Average \u2b06\ufe0f": 69.3, + "ARC": 66.04, + "HellaSwag": 82.93, + "MMLU": 65.04, + "TruthfulQA": 51.9, + "Winogrande": 81.77, + "GSM8K": 68.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "8d566086308e80e8aa01e70acfac10adcf457fe3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Jaume\/openchat-3.5-0106-mod-gpt5", + "Average \u2b06\ufe0f": 69.3, + "ARC": 66.04, + "HellaSwag": 82.93, + "MMLU": 65.04, + "TruthfulQA": 51.9, + "Winogrande": 81.77, + "GSM8K": 68.16, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e48411ee9b41210b2bf019e5b6e58a6cde3d04f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "openchat\/openchat-3.5-0106", + "Average \u2b06\ufe0f": 69.3, + "ARC": 66.04, + "HellaSwag": 82.93, + "MMLU": 65.04, + "TruthfulQA": 51.9, + "Winogrande": 81.77, + "GSM8K": 68.16, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 209.0, + "Available on the hub": true, + "Model sha": "9619fb7d2a8e25fa6b0633c0f57f7f4aa79b45c4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "garage-bAInd\/Platypus2-70B-instruct", + "Average \u2b06\ufe0f": 69.3, + "ARC": 71.84, + "HellaSwag": 87.94, + "MMLU": 70.48, + "TruthfulQA": 62.26, + "Winogrande": 82.72, + "GSM8K": 40.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 173.0, + "Available on the hub": true, + "Model sha": "a66378c15f89756215ccc64572ba69b161173703", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "adamo1139\/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3", + "Average \u2b06\ufe0f": 69.29, + "ARC": 64.85, + "HellaSwag": 84.77, + "MMLU": 76.0, + "TruthfulQA": 45.35, + "Winogrande": 83.11, + "GSM8K": 61.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8248694fd93e0c5a5a6bce8b6aa9923174fc6779", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/openchat-nectar-0.8", + "Average \u2b06\ufe0f": 69.26, + "ARC": 65.78, + "HellaSwag": 83.05, + "MMLU": 65.16, + "TruthfulQA": 52.26, + "Winogrande": 81.61, + "GSM8K": 67.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "639db94ac706d6964a3eed642b8de3a582bbffa8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/Hermes-low-tune-3", + "Average \u2b06\ufe0f": 69.25, + "ARC": 66.21, + "HellaSwag": 84.99, + "MMLU": 63.74, + "TruthfulQA": 57.94, + "Winogrande": 78.77, + "GSM8K": 63.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d3824696c2c4b45aff9ee5c2725bd1780d163fa8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/BeagleLake-7B-Toxic", + "Average \u2b06\ufe0f": 69.24, + "ARC": 65.19, + "HellaSwag": 83.83, + "MMLU": 62.82, + "TruthfulQA": 57.67, + "Winogrande": 82.32, + "GSM8K": 63.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d5c8a91a088942987fb4c3af188f13b3d8e75ad1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "jpechg\/Sour-Marcoro-12.5B", + "Average \u2b06\ufe0f": 69.23, + "ARC": 67.92, + "HellaSwag": 83.7, + "MMLU": 65.85, + "TruthfulQA": 68.17, + "Winogrande": 82.08, + "GSM8K": 47.69, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "abe2e19a88077dd184782946963148e8fc62ed05", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/BagelToppyLake-7B-slerp", + "Average \u2b06\ufe0f": 69.22, + "ARC": 67.15, + "HellaSwag": 84.79, + "MMLU": 64.31, + "TruthfulQA": 62.15, + "Winogrande": 81.85, + "GSM8K": 55.04, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "291f0e17b1322c7fb10e770f0febc15216beab29", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LHC88\/LaseredHermes-7B-v1", + "Average \u2b06\ufe0f": 69.2, + "ARC": 66.98, + "HellaSwag": 85.22, + "MMLU": 63.6, + "TruthfulQA": 59.01, + "Winogrande": 78.3, + "GSM8K": 62.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2971ac5fdf665330b38abacef92b8d4b36f875c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Jaume\/openchat-3.5-0106-mod-gpt5", + "Average \u2b06\ufe0f": 69.19, + "ARC": 65.87, + "HellaSwag": 82.93, + "MMLU": 65.12, + "TruthfulQA": 51.93, + "Winogrande": 81.53, + "GSM8K": 67.78, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e48411ee9b41210b2bf019e5b6e58a6cde3d04f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "llmixer\/BigWeave-v12-90b", + "Average \u2b06\ufe0f": 69.19, + "ARC": 68.09, + "HellaSwag": 87.7, + "MMLU": 69.41, + "TruthfulQA": 61.35, + "Winogrande": 81.22, + "GSM8K": 47.38, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 87.8, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4518c1d85135efdb14ed8d3581d325ea2167d6b4", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/openchat-nectar-0.7", + "Average \u2b06\ufe0f": 69.19, + "ARC": 65.78, + "HellaSwag": 83.0, + "MMLU": 65.1, + "TruthfulQA": 52.05, + "Winogrande": 81.37, + "GSM8K": 67.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "082de25a339e1e8e5a64c9fc84429f1a4a0847ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "splm\/openchat-spin-slimorca-iter1", + "Average \u2b06\ufe0f": 69.18, + "ARC": 67.32, + "HellaSwag": 83.86, + "MMLU": 62.64, + "TruthfulQA": 58.76, + "Winogrande": 79.4, + "GSM8K": 63.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d2725936c02b9ec7e11a09857f69dd327151615c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PistachioAlt\/Synatra-MCS-7B-v0.3-RP-Slerp", + "Average \u2b06\ufe0f": 69.18, + "ARC": 66.64, + "HellaSwag": 84.97, + "MMLU": 63.61, + "TruthfulQA": 53.93, + "Winogrande": 79.72, + "GSM8K": 66.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "69369829e665cbcda97e7fd178f1c43720f0fce4", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "freecs\/ThetaWave-7B-v0.1", + "Average \u2b06\ufe0f": 69.17, + "ARC": 66.3, + "HellaSwag": 85.4, + "MMLU": 63.47, + "TruthfulQA": 60.24, + "Winogrande": 80.19, + "GSM8K": 59.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c2aea352e9697d0bbeb4e3e469f71ba691625c00", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Pallas-0.5-LASER-0.3", + "Average \u2b06\ufe0f": 69.17, + "ARC": 64.76, + "HellaSwag": 83.17, + "MMLU": 74.66, + "TruthfulQA": 55.43, + "Winogrande": 80.9, + "GSM8K": 56.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d2532427a883434ac152061b27d7c3cf0778868c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/Xwin-LM-70B-V0.1_Limarpv3", + "Average \u2b06\ufe0f": 69.16, + "ARC": 70.82, + "HellaSwag": 86.97, + "MMLU": 69.28, + "TruthfulQA": 57.15, + "Winogrande": 81.77, + "GSM8K": 48.98, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "80a9d5efe8d6d7189cea710c31c244db3b203fc0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "adamo1139\/Yi-34b-200K-rawrr-v2-run-0902-LoRA", + "Average \u2b06\ufe0f": 69.15, + "ARC": 64.68, + "HellaSwag": 84.5, + "MMLU": 75.76, + "TruthfulQA": 46.66, + "Winogrande": 81.14, + "GSM8K": 62.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3fbaa2965a16992f1e8cddbc0c9b40efd6f15698", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_12-7B-slerp", + "Average \u2b06\ufe0f": 69.13, + "ARC": 66.64, + "HellaSwag": 85.89, + "MMLU": 64.94, + "TruthfulQA": 52.55, + "Winogrande": 81.69, + "GSM8K": 63.08, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "68ce0b9e6244fe02571b5d6b40660abbb37470b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/airoboros-l2-70b-2.2.1", + "Average \u2b06\ufe0f": 69.13, + "ARC": 69.71, + "HellaSwag": 87.95, + "MMLU": 69.79, + "TruthfulQA": 59.49, + "Winogrande": 82.95, + "GSM8K": 44.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "eadc78a4a9e173bccdca7dc8d12a34e80317c66c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/piano-medley-7b", + "Average \u2b06\ufe0f": 69.1, + "ARC": 67.58, + "HellaSwag": 85.36, + "MMLU": 64.49, + "TruthfulQA": 61.42, + "Winogrande": 79.16, + "GSM8K": 56.56, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "38da429cb28f667e8868574f32269a04dfe41280", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LHC88\/LaseredHermes-7B-v1", + "Average \u2b06\ufe0f": 69.09, + "ARC": 66.89, + "HellaSwag": 85.21, + "MMLU": 63.58, + "TruthfulQA": 59.09, + "Winogrande": 78.45, + "GSM8K": 61.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2971ac5fdf665330b38abacef92b8d4b36f875c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "saishf\/West-Maid-7B", + "Average \u2b06\ufe0f": 69.09, + "ARC": 67.24, + "HellaSwag": 86.44, + "MMLU": 64.85, + "TruthfulQA": 51.0, + "Winogrande": 82.72, + "GSM8K": 62.32, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a271497bda998eed0acd3e68165133e7f3d196a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/openchat-nectar-0.14", + "Average \u2b06\ufe0f": 69.09, + "ARC": 65.61, + "HellaSwag": 83.02, + "MMLU": 64.58, + "TruthfulQA": 50.09, + "Winogrande": 82.0, + "GSM8K": 69.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6a3412e4ece04c794bef9d90e38a6dcb6ad07f70", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "itsliupeng\/Mixtral-8x7B-v0.1-top3", + "Average \u2b06\ufe0f": 69.09, + "ARC": 67.41, + "HellaSwag": 86.63, + "MMLU": 71.98, + "TruthfulQA": 48.58, + "Winogrande": 82.4, + "GSM8K": 57.54, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "41de832eae882f2c951b64ff5f04d7a809d0a99c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Q-bert\/Optimus-7B", + "Average \u2b06\ufe0f": 69.09, + "ARC": 65.44, + "HellaSwag": 85.41, + "MMLU": 63.61, + "TruthfulQA": 55.79, + "Winogrande": 78.77, + "GSM8K": 65.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "d9dd63bc4437c2089f40ce37e689ad530060519c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-RawEmerald-7B", + "Average \u2b06\ufe0f": 69.09, + "ARC": 66.89, + "HellaSwag": 85.75, + "MMLU": 63.23, + "TruthfulQA": 57.58, + "Winogrande": 78.22, + "GSM8K": 62.85, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c9903c39faa7cf6c2694b24f5e15e29b372f2143", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/FettuccineLake-DPO-7B-slerp", + "Average \u2b06\ufe0f": 69.09, + "ARC": 67.92, + "HellaSwag": 86.37, + "MMLU": 63.24, + "TruthfulQA": 68.64, + "Winogrande": 80.58, + "GSM8K": 47.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fbbbda1a8c1c00f65768391f608bd922dd757bf6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "liminerity\/Blurstral-7b-slerp", + "Average \u2b06\ufe0f": 69.08, + "ARC": 66.3, + "HellaSwag": 85.38, + "MMLU": 65.18, + "TruthfulQA": 53.4, + "Winogrande": 81.37, + "GSM8K": 62.85, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d9480038f0136e51d37810cd7d574818f48e90e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/loyal-piano-m7-cdpo", + "Average \u2b06\ufe0f": 69.08, + "ARC": 67.15, + "HellaSwag": 85.39, + "MMLU": 64.52, + "TruthfulQA": 61.53, + "Winogrande": 79.4, + "GSM8K": 56.48, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5f5a78bedc2d3e5314589f685489bc981890cadf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "diffnamehard\/Mistral-CatMacaroni-slerp-gradient", + "Average \u2b06\ufe0f": 69.08, + "ARC": 65.53, + "HellaSwag": 85.66, + "MMLU": 61.53, + "TruthfulQA": 64.1, + "Winogrande": 80.03, + "GSM8K": 57.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "daf6eee865b05b45a4ce61af906313a80de06a9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "freeCS-dot-org\/ThetaZero-7B-1", + "Average \u2b06\ufe0f": 69.07, + "ARC": 67.49, + "HellaSwag": 85.69, + "MMLU": 63.03, + "TruthfulQA": 62.48, + "Winogrande": 79.87, + "GSM8K": 55.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5af7656feb7c0f4f33aaca6984b4600c511613f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_12-7B-slerp", + "Average \u2b06\ufe0f": 69.05, + "ARC": 66.64, + "HellaSwag": 85.9, + "MMLU": 65.06, + "TruthfulQA": 52.55, + "Winogrande": 81.53, + "GSM8K": 62.62, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "68ce0b9e6244fe02571b5d6b40660abbb37470b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/Neural-una-cybertron-7b", + "Average \u2b06\ufe0f": 69.05, + "ARC": 69.03, + "HellaSwag": 84.51, + "MMLU": 62.79, + "TruthfulQA": 64.99, + "Winogrande": 80.66, + "GSM8K": 52.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "66dae63f92cac0c99b1b162383506b60ac060225", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Test157t\/HerculeanSea-upd-7b-128k", + "Average \u2b06\ufe0f": 69.03, + "ARC": 66.13, + "HellaSwag": 85.89, + "MMLU": 64.48, + "TruthfulQA": 55.54, + "Winogrande": 81.22, + "GSM8K": 60.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "64c1b6cef98190b6a54d9718c18cb2dd3e9badcc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/orca_mini_v3_70b", + "Average \u2b06\ufe0f": 69.02, + "ARC": 71.25, + "HellaSwag": 87.85, + "MMLU": 70.18, + "TruthfulQA": 61.27, + "Winogrande": 82.72, + "GSM8K": 40.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c1d4f997f8ed685a6efc72229523b2e56fd0774b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vihangd\/smartsolmix-4x10.7b-v1", + "Average \u2b06\ufe0f": 69.01, + "ARC": 64.93, + "HellaSwag": 85.13, + "MMLU": 66.1, + "TruthfulQA": 55.03, + "Winogrande": 83.43, + "GSM8K": 59.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f7ace5190d07c08c17f846cab5619260bee5ff69", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "chargoddard\/loyal-piano-m7-cdpo", + "Average \u2b06\ufe0f": 69.0, + "ARC": 67.06, + "HellaSwag": 85.42, + "MMLU": 64.54, + "TruthfulQA": 61.54, + "Winogrande": 79.08, + "GSM8K": 56.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5f5a78bedc2d3e5314589f685489bc981890cadf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/servile-harpsichord-cdpo", + "Average \u2b06\ufe0f": 68.98, + "ARC": 67.32, + "HellaSwag": 85.18, + "MMLU": 64.54, + "TruthfulQA": 60.61, + "Winogrande": 79.16, + "GSM8K": 57.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "13cdf6bd90df46f4fae1d31b9d3b4f7fc31a7777", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/Monarch-7B-SFT", + "Average \u2b06\ufe0f": 68.98, + "ARC": 63.74, + "HellaSwag": 83.58, + "MMLU": 64.11, + "TruthfulQA": 54.25, + "Winogrande": 79.79, + "GSM8K": 68.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1b031916ab87c2d1b9712fbc1901ecaec144f3d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Mixtral_13B_Chat", + "Average \u2b06\ufe0f": 68.98, + "ARC": 67.41, + "HellaSwag": 85.87, + "MMLU": 64.54, + "TruthfulQA": 58.98, + "Winogrande": 80.43, + "GSM8K": 56.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2469744c92f2bc1f988b1588fff86bfcbf084ed6", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ignos\/LeoScorpius-GreenNode-Platypus-7B-v1", + "Average \u2b06\ufe0f": 68.96, + "ARC": 66.04, + "HellaSwag": 86.53, + "MMLU": 62.06, + "TruthfulQA": 52.78, + "Winogrande": 82.16, + "GSM8K": 64.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "606894800b6de3fa7a21b46427c3165968fdf3b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-RawRuby-7B", + "Average \u2b06\ufe0f": 68.95, + "ARC": 66.89, + "HellaSwag": 85.53, + "MMLU": 63.46, + "TruthfulQA": 57.09, + "Winogrande": 78.69, + "GSM8K": 62.02, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "547f6b51a5bc0798c762cb097d1c1d33e8cc336f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HanNayeoniee\/LHK_44", + "Average \u2b06\ufe0f": 68.95, + "ARC": 66.55, + "HellaSwag": 84.86, + "MMLU": 65.37, + "TruthfulQA": 59.58, + "Winogrande": 80.9, + "GSM8K": 56.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "89b6a3be6c3b6a2fa729de466ec20153665359dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/MegaDolphin-120b", + "Average \u2b06\ufe0f": 68.91, + "ARC": 69.03, + "HellaSwag": 87.8, + "MMLU": 69.26, + "TruthfulQA": 59.28, + "Winogrande": 81.85, + "GSM8K": 46.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 120.32, + "Hub \u2764\ufe0f": 61.0, + "Available on the hub": true, + "Model sha": "561d22376c354903641165d6691eb4df9405a4cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/ConfigurableHermes-7B", + "Average \u2b06\ufe0f": 68.89, + "ARC": 66.04, + "HellaSwag": 84.31, + "MMLU": 62.44, + "TruthfulQA": 61.71, + "Winogrande": 77.43, + "GSM8K": 61.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "54b290ffcf07040c5e202f1a5f2a82d455c575af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat-3.5-1210", + "Average \u2b06\ufe0f": 68.89, + "ARC": 64.93, + "HellaSwag": 84.92, + "MMLU": 64.62, + "TruthfulQA": 52.15, + "Winogrande": 80.74, + "GSM8K": 65.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 262.0, + "Available on the hub": true, + "Model sha": "e5df841b685e5b5ca11ce142f29c6c731bf087a0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/MetaMath-una-cybertron-v2-bf16-Ties", + "Average \u2b06\ufe0f": 68.88, + "ARC": 65.02, + "HellaSwag": 83.68, + "MMLU": 62.58, + "TruthfulQA": 55.52, + "Winogrande": 77.27, + "GSM8K": 69.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e613cc45140352e2d1759f0f551021e928de006e", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "macadeliccc\/Monarch-7B-SFT", + "Average \u2b06\ufe0f": 68.88, + "ARC": 63.82, + "HellaSwag": 83.63, + "MMLU": 64.2, + "TruthfulQA": 54.26, + "Winogrande": 79.95, + "GSM8K": 67.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1b031916ab87c2d1b9712fbc1901ecaec144f3d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dfurman\/Mixtral-8x7B-peft-v0.1", + "Average \u2b06\ufe0f": 68.87, + "ARC": 67.24, + "HellaSwag": 86.03, + "MMLU": 68.59, + "TruthfulQA": 59.54, + "Winogrande": 80.43, + "GSM8K": 51.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "87dac68765c899952d9d91ce827cda867d115c6f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sethuiyer\/distilabled_Chikuma_10.7B", + "Average \u2b06\ufe0f": 68.87, + "ARC": 66.38, + "HellaSwag": 85.14, + "MMLU": 64.7, + "TruthfulQA": 59.2, + "Winogrande": 79.4, + "GSM8K": 58.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a5a6ba84916b025cdce898d17387e4b4bc31104f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-DesolatingRuby-7B", + "Average \u2b06\ufe0f": 68.86, + "ARC": 66.89, + "HellaSwag": 85.46, + "MMLU": 63.38, + "TruthfulQA": 57.05, + "Winogrande": 78.45, + "GSM8K": 61.94, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "addeaf592042c08f64930aaa09a61d6deb74d109", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-SharpEmerald-7B", + "Average \u2b06\ufe0f": 68.86, + "ARC": 66.72, + "HellaSwag": 85.4, + "MMLU": 63.21, + "TruthfulQA": 56.52, + "Winogrande": 78.53, + "GSM8K": 62.77, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "28b728dd8fe67e04015f7181233b21c78050b993", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/FT", + "Average \u2b06\ufe0f": 68.85, + "ARC": 63.05, + "HellaSwag": 82.78, + "MMLU": 69.69, + "TruthfulQA": 59.88, + "Winogrande": 79.64, + "GSM8K": 58.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1b91227a0539deaf4dfb5b18d15c92316e0254c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cloudyu\/Mixtral_7Bx4_MOE_24B", + "Average \u2b06\ufe0f": 68.85, + "ARC": 65.36, + "HellaSwag": 85.23, + "MMLU": 62.96, + "TruthfulQA": 59.78, + "Winogrande": 78.06, + "GSM8K": 61.71, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "1cc519b70e87de1c632a6dc98ac6383cf0dd994e", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "splm\/openchat-spin-slimorca-iter2", + "Average \u2b06\ufe0f": 68.85, + "ARC": 68.0, + "HellaSwag": 83.97, + "MMLU": 64.39, + "TruthfulQA": 59.0, + "Winogrande": 77.98, + "GSM8K": 59.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "051fc15365204500bc32de026063fa25b5513413", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decruz07\/kellemar-DPO-7B-d", + "Average \u2b06\ufe0f": 68.84, + "ARC": 66.89, + "HellaSwag": 85.16, + "MMLU": 62.77, + "TruthfulQA": 56.88, + "Winogrande": 79.32, + "GSM8K": 62.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d0583642fd14d4881ba7799cea1eb3a12daed62e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/mixtral_7bx4_moe", + "Average \u2b06\ufe0f": 68.83, + "ARC": 65.27, + "HellaSwag": 85.28, + "MMLU": 62.84, + "TruthfulQA": 59.85, + "Winogrande": 77.66, + "GSM8K": 62.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1cc519b70e87de1c632a6dc98ac6383cf0dd994e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "AIDC-ai-business\/Marcoroni-70B-v1", + "Average \u2b06\ufe0f": 68.83, + "ARC": 73.55, + "HellaSwag": 87.62, + "MMLU": 70.67, + "TruthfulQA": 64.41, + "Winogrande": 83.43, + "GSM8K": 33.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "55a30d29db194832c0b5de1392a6598a63582144", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Eurdem\/megatron_v1", + "Average \u2b06\ufe0f": 68.82, + "ARC": 65.96, + "HellaSwag": 84.8, + "MMLU": 65.02, + "TruthfulQA": 60.32, + "Winogrande": 79.79, + "GSM8K": 57.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "526323001ad41288cadb1395405e7df79524c68e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "giraffe176\/Open_Maid_Samantha_Hermes_Orca", + "Average \u2b06\ufe0f": 68.81, + "ARC": 66.81, + "HellaSwag": 85.83, + "MMLU": 64.58, + "TruthfulQA": 53.91, + "Winogrande": 80.35, + "GSM8K": 61.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fd850286fb7795e531edaeb7c3ecb4ed72d9e636", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AiMavenAi\/AiMaven-SmartDawg-7b", + "Average \u2b06\ufe0f": 68.81, + "ARC": 67.92, + "HellaSwag": 87.16, + "MMLU": 62.69, + "TruthfulQA": 58.86, + "Winogrande": 79.01, + "GSM8K": 57.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b91cc33a1842344921dfd8ea9d7040277cafd8d6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/FT", + "Average \u2b06\ufe0f": 68.81, + "ARC": 63.14, + "HellaSwag": 82.78, + "MMLU": 69.5, + "TruthfulQA": 59.8, + "Winogrande": 79.4, + "GSM8K": 58.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1b91227a0539deaf4dfb5b18d15c92316e0254c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Technoculture\/Medmerge-tulu-70b", + "Average \u2b06\ufe0f": 68.81, + "ARC": 67.41, + "HellaSwag": 87.46, + "MMLU": 70.1, + "TruthfulQA": 47.89, + "Winogrande": 83.43, + "GSM8K": 56.56, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "aed9ff4b3edc3ed0672de35551dc750ea8fbac3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "martyn\/solar-megamerge-dare-10.7b-v1", + "Average \u2b06\ufe0f": 68.79, + "ARC": 66.13, + "HellaSwag": 85.3, + "MMLU": 66.03, + "TruthfulQA": 54.33, + "Winogrande": 82.95, + "GSM8K": 58.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c08c204161faa4bd853856dc2c868dbab534632b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Test157t\/Kunocchini-7b", + "Average \u2b06\ufe0f": 68.78, + "ARC": 67.49, + "HellaSwag": 86.85, + "MMLU": 63.89, + "TruthfulQA": 68.62, + "Winogrande": 77.98, + "GSM8K": 47.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a8bf199949b35a6037d197ffc21ae5c26fd1947b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Epiculous\/Crunchy-onion", + "Average \u2b06\ufe0f": 68.75, + "ARC": 67.15, + "HellaSwag": 86.19, + "MMLU": 70.02, + "TruthfulQA": 63.88, + "Winogrande": 73.24, + "GSM8K": 52.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "agpl-3.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "53db5c3846780919b8838ed8e1415bb86c475247", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "HanNayeoniee\/LHK", + "Average \u2b06\ufe0f": 68.74, + "ARC": 66.38, + "HellaSwag": 84.49, + "MMLU": 65.13, + "TruthfulQA": 59.12, + "Winogrande": 80.98, + "GSM8K": 56.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0cf54af3c084e70b6e544326d63ecffccac30b47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/limb", + "Average \u2b06\ufe0f": 68.73, + "ARC": 63.48, + "HellaSwag": 83.07, + "MMLU": 72.25, + "TruthfulQA": 58.37, + "Winogrande": 79.79, + "GSM8K": 55.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "55473b7666b66e5b51bb3c4e6b5bc88d1bd00666", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/A11P", + "Average \u2b06\ufe0f": 68.73, + "ARC": 62.54, + "HellaSwag": 82.53, + "MMLU": 70.56, + "TruthfulQA": 56.44, + "Winogrande": 79.87, + "GSM8K": 60.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0a14aa5fd9ae557d7dbd02e503deab50544d5a6f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TokenBender\/pic_7B_mistral_Full_v0.2", + "Average \u2b06\ufe0f": 68.72, + "ARC": 65.36, + "HellaSwag": 84.03, + "MMLU": 64.51, + "TruthfulQA": 59.2, + "Winogrande": 79.48, + "GSM8K": 59.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "4499c15a16b11d6491dcbe029acff64f03e1a5fd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/OpenHermes-2.5-neural-chat-7b-v3-2-7B", + "Average \u2b06\ufe0f": 68.71, + "ARC": 66.38, + "HellaSwag": 84.11, + "MMLU": 62.84, + "TruthfulQA": 63.59, + "Winogrande": 78.53, + "GSM8K": 56.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "585c2fca1dce1904491c40408f6dd5404eca3754", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-ShatteredRuby-7B", + "Average \u2b06\ufe0f": 68.7, + "ARC": 66.21, + "HellaSwag": 85.38, + "MMLU": 63.29, + "TruthfulQA": 56.99, + "Winogrande": 78.61, + "GSM8K": 61.71, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "84b3f2e27187058045e104b6ed1d51905d73bc1c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-Ruby-7B-Fixed", + "Average \u2b06\ufe0f": 68.68, + "ARC": 67.24, + "HellaSwag": 85.22, + "MMLU": 63.21, + "TruthfulQA": 56.49, + "Winogrande": 77.98, + "GSM8K": 61.94, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f0d1375d6e960a9c735949414e1727cf3354b9e3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-Ruby-7B", + "Average \u2b06\ufe0f": 68.68, + "ARC": 67.24, + "HellaSwag": 85.22, + "MMLU": 63.21, + "TruthfulQA": 56.49, + "Winogrande": 77.98, + "GSM8K": 61.94, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9fc954264f09be86a91b9f79d44151cf7cda2572", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "pinkyponky\/SOLAR-10.7B-dpo-instruct-tuned-v0.1", + "Average \u2b06\ufe0f": 68.68, + "ARC": 65.19, + "HellaSwag": 86.09, + "MMLU": 66.25, + "TruthfulQA": 51.81, + "Winogrande": 83.98, + "GSM8K": 58.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bb3b052f07ab6bc00a03dc5c7b510c0760bfd650", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "adamo1139\/Yi-34B-AEZAKMI-v1", + "Average \u2b06\ufe0f": 68.67, + "ARC": 64.33, + "HellaSwag": 84.31, + "MMLU": 73.91, + "TruthfulQA": 55.73, + "Winogrande": 80.82, + "GSM8K": 52.92, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c56dc8471eba802f74fed756f555b718d975d00a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/loyal-piano-m7", + "Average \u2b06\ufe0f": 68.67, + "ARC": 66.72, + "HellaSwag": 85.03, + "MMLU": 64.43, + "TruthfulQA": 60.03, + "Winogrande": 79.08, + "GSM8K": 56.71, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "d74ae6cb13325e0f81797ee33c07f0e234a2caa4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/openchat-3.5-1210-starling-slerp", + "Average \u2b06\ufe0f": 68.67, + "ARC": 63.91, + "HellaSwag": 85.27, + "MMLU": 65.05, + "TruthfulQA": 49.92, + "Winogrande": 80.82, + "GSM8K": 67.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f6b1d9d6f613c6311b95d44b335a679e01e61140", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/A12P", + "Average \u2b06\ufe0f": 68.64, + "ARC": 64.42, + "HellaSwag": 82.32, + "MMLU": 69.97, + "TruthfulQA": 62.22, + "Winogrande": 79.64, + "GSM8K": 53.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e2eb6a36741dfc799fd13f67cba385f6e3992393", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mncai\/agiin-13.6B-v0.0", + "Average \u2b06\ufe0f": 68.63, + "ARC": 69.45, + "HellaSwag": 86.59, + "MMLU": 61.94, + "TruthfulQA": 67.4, + "Winogrande": 78.69, + "GSM8K": 47.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "631e80949b055193053c802437f3a31fe4e1390d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-ShinyEmerald-7B", + "Average \u2b06\ufe0f": 68.63, + "ARC": 66.21, + "HellaSwag": 85.37, + "MMLU": 63.36, + "TruthfulQA": 56.65, + "Winogrande": 78.37, + "GSM8K": 61.79, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "836539ad2aae2f30a29516ef381b0ab0bdb69a22", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/spicyboros-70b-2.2", + "Average \u2b06\ufe0f": 68.62, + "ARC": 70.73, + "HellaSwag": 87.58, + "MMLU": 70.32, + "TruthfulQA": 58.31, + "Winogrande": 83.82, + "GSM8K": 40.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "533f7dda1e3fe462a0abb00671f9a48d5fd51093", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luqmanxyz\/Maya_Hermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 68.6, + "ARC": 66.3, + "HellaSwag": 85.07, + "MMLU": 63.23, + "TruthfulQA": 55.89, + "Winogrande": 78.85, + "GSM8K": 62.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a0ca78bdb647ffde1ed79f6dd85ed5e7694c1eaf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/MixtralRPChat-ZLoss", + "Average \u2b06\ufe0f": 68.59, + "ARC": 68.6, + "HellaSwag": 86.1, + "MMLU": 70.44, + "TruthfulQA": 53.85, + "Winogrande": 82.0, + "GSM8K": 50.57, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "94e804a4cd8e3ed54105f400118c60fa0cce764d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/aegolius-acadicus-34b-v3", + "Average \u2b06\ufe0f": 68.59, + "ARC": 67.66, + "HellaSwag": 85.54, + "MMLU": 62.13, + "TruthfulQA": 63.33, + "Winogrande": 78.69, + "GSM8K": 54.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c43b47a1d94a5daf790c506d113e5ee258871822", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "LHC88\/DPOpenHermes-7B-v2-PerfLaser", + "Average \u2b06\ufe0f": 68.58, + "ARC": 66.38, + "HellaSwag": 84.58, + "MMLU": 62.77, + "TruthfulQA": 59.07, + "Winogrande": 78.61, + "GSM8K": 60.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "178f18610436183f66d5eaf3be46ecf020214be3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "brucethemoose\/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties", + "Average \u2b06\ufe0f": 68.57, + "ARC": 64.93, + "HellaSwag": 84.99, + "MMLU": 75.37, + "TruthfulQA": 52.84, + "Winogrande": 79.24, + "GSM8K": 54.06, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "7be35464f07307b5503d12736f732a34f3c1d8c1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/model_007", + "Average \u2b06\ufe0f": 68.56, + "ARC": 71.08, + "HellaSwag": 87.65, + "MMLU": 69.04, + "TruthfulQA": 63.12, + "Winogrande": 83.35, + "GSM8K": 37.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0f5d81b13718a866cb078bd8762ab80a41972663", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uproai\/RosMistral-2x7B", + "Average \u2b06\ufe0f": 68.56, + "ARC": 66.21, + "HellaSwag": 85.54, + "MMLU": 65.35, + "TruthfulQA": 52.87, + "Winogrande": 79.24, + "GSM8K": 62.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "edf49ed0bf25f2656cf715400a1911b69237a0f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sequelbox\/SpellBlade", + "Average \u2b06\ufe0f": 68.54, + "ARC": 69.28, + "HellaSwag": 87.31, + "MMLU": 70.5, + "TruthfulQA": 47.1, + "Winogrande": 83.19, + "GSM8K": 53.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "258211a0cceaa08f7c8df3660ff8cd7cb6bee5e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Test157t\/HerculeanSea-7b-128k", + "Average \u2b06\ufe0f": 68.53, + "ARC": 66.21, + "HellaSwag": 85.8, + "MMLU": 64.28, + "TruthfulQA": 55.77, + "Winogrande": 80.74, + "GSM8K": 58.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "142b62bd4c61639c71c15dbd7ac793bfe30a6349", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "shahzebnaveed\/StarlingHermes-2.5-Mistral-7B-slerp", + "Average \u2b06\ufe0f": 68.53, + "ARC": 66.04, + "HellaSwag": 85.18, + "MMLU": 64.72, + "TruthfulQA": 49.56, + "Winogrande": 79.72, + "GSM8K": 65.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c3902e03960f3b38ba98b733bfc1192198efb869", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/model_009", + "Average \u2b06\ufe0f": 68.53, + "ARC": 71.59, + "HellaSwag": 87.7, + "MMLU": 69.43, + "TruthfulQA": 60.72, + "Winogrande": 82.32, + "GSM8K": 39.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5020869e6394b1ac039bf80a0a1d2bed6be6707e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jan-hq\/stealth-v1.3", + "Average \u2b06\ufe0f": 68.53, + "ARC": 65.19, + "HellaSwag": 84.44, + "MMLU": 62.7, + "TruthfulQA": 59.12, + "Winogrande": 78.61, + "GSM8K": 61.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "b76e2592849352c5073ebddec5748975f16e4895", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-PrimordialSapphire-7B", + "Average \u2b06\ufe0f": 68.52, + "ARC": 65.87, + "HellaSwag": 85.51, + "MMLU": 63.11, + "TruthfulQA": 57.25, + "Winogrande": 78.22, + "GSM8K": 61.18, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eeb2ef916586cbcf0b699a91190e659c66d848fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Yuma42\/KangalKhan-Sapphire-7B", + "Average \u2b06\ufe0f": 68.52, + "ARC": 66.3, + "HellaSwag": 85.34, + "MMLU": 63.32, + "TruthfulQA": 56.09, + "Winogrande": 78.14, + "GSM8K": 61.94, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5e20ee421f38f83e6f1541a85457485cf6aae370", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-7B-v2.04", + "Average \u2b06\ufe0f": 68.52, + "ARC": 66.3, + "HellaSwag": 85.7, + "MMLU": 60.94, + "TruthfulQA": 67.76, + "Winogrande": 78.93, + "GSM8K": 51.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b6eb3c3293fff1cb3d38bbfefa9adfce3e20f053", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "freecs\/ThetaWave-7B-v0", + "Average \u2b06\ufe0f": 68.49, + "ARC": 68.52, + "HellaSwag": 85.35, + "MMLU": 61.07, + "TruthfulQA": 61.56, + "Winogrande": 79.64, + "GSM8K": 54.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "89c74880ff1621a555374b2867f564131b3f4352", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Test157t\/Pasta-PrimaMaid-7b", + "Average \u2b06\ufe0f": 68.48, + "ARC": 67.92, + "HellaSwag": 86.18, + "MMLU": 63.31, + "TruthfulQA": 66.47, + "Winogrande": 77.9, + "GSM8K": 49.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c00e0ed6d1c118b377faeabde26a4620cc94930d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/Sonya-7B", + "Average \u2b06\ufe0f": 68.48, + "ARC": 64.59, + "HellaSwag": 85.11, + "MMLU": 62.72, + "TruthfulQA": 61.22, + "Winogrande": 77.74, + "GSM8K": 59.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "228e7ab8b24ebb3d459160c0b665a821d1785dc5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Instruct-v0.2-Seraph-7B", + "Average \u2b06\ufe0f": 68.48, + "ARC": 64.76, + "HellaSwag": 84.2, + "MMLU": 62.9, + "TruthfulQA": 65.39, + "Winogrande": 79.16, + "GSM8K": 54.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6ea01ce2a3b6967d9aaf968ed8015da21c979928", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mistralai\/Mixtral-8x7B-v0.1", + "Average \u2b06\ufe0f": 68.47, + "ARC": 66.38, + "HellaSwag": 86.46, + "MMLU": 71.88, + "TruthfulQA": 46.81, + "Winogrande": 81.69, + "GSM8K": 57.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1362.0, + "Available on the hub": true, + "Model sha": "58301445dc1378584211722b7ebf8743ec4e192b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "LoSboccacc\/orthogonal-2x7B-v2-base", + "Average \u2b06\ufe0f": 68.47, + "ARC": 66.89, + "HellaSwag": 85.69, + "MMLU": 62.65, + "TruthfulQA": 66.8, + "Winogrande": 77.35, + "GSM8K": 51.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0d5011506f7782cbbdc3feb0fed079f400292f2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/model_101", + "Average \u2b06\ufe0f": 68.46, + "ARC": 68.69, + "HellaSwag": 86.42, + "MMLU": 69.92, + "TruthfulQA": 58.85, + "Winogrande": 82.08, + "GSM8K": 44.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "884c53a64a3c5faf7b0706d36a587ca1532ed8f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tenyx\/TenyxChat-7B-v1", + "Average \u2b06\ufe0f": 68.46, + "ARC": 65.61, + "HellaSwag": 85.55, + "MMLU": 64.81, + "TruthfulQA": 51.28, + "Winogrande": 80.51, + "GSM8K": 63.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "c3c7ee002c4fdb1b8c2e2c78b7fba0c389673710", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/V0202", + "Average \u2b06\ufe0f": 68.46, + "ARC": 66.55, + "HellaSwag": 82.75, + "MMLU": 86.32, + "TruthfulQA": 50.89, + "Winogrande": 78.37, + "GSM8K": 45.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6f115d4ae1b6015420558aa5684c530f41c0e7da", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ZoidBB\/Jovian-10.7B-v1.0", + "Average \u2b06\ufe0f": 68.42, + "ARC": 67.41, + "HellaSwag": 86.4, + "MMLU": 65.66, + "TruthfulQA": 52.0, + "Winogrande": 81.85, + "GSM8K": 57.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ba8433fe1cdf03a7fe25650d99219d34fce13bb8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "alykassem\/ds_diasum_md_mixtral", + "Average \u2b06\ufe0f": 68.42, + "ARC": 66.3, + "HellaSwag": 85.45, + "MMLU": 69.51, + "TruthfulQA": 55.72, + "Winogrande": 80.35, + "GSM8K": 53.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8ee85e4555b4c4a75b29ee749a86c97e0d37d242", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "mistralai\/Mixtral-8x7B-v0.1", + "Average \u2b06\ufe0f": 68.42, + "ARC": 66.04, + "HellaSwag": 86.49, + "MMLU": 71.82, + "TruthfulQA": 46.78, + "Winogrande": 81.93, + "GSM8K": 57.47, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1362.0, + "Available on the hub": true, + "Model sha": "4dd4b0f2d577d7b74152732d5543a92201481fe2", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "argilla\/distilabeled-Hermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 68.42, + "ARC": 66.3, + "HellaSwag": 85.15, + "MMLU": 63.5, + "TruthfulQA": 55.75, + "Winogrande": 78.93, + "GSM8K": 60.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "71e12bedd29a0d8e8744f32a41aca68769fc99c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvilasuero\/NeuralHermes-2.5-Mistral-7B-distilabel", + "Average \u2b06\ufe0f": 68.4, + "ARC": 65.78, + "HellaSwag": 84.97, + "MMLU": 63.63, + "TruthfulQA": 55.86, + "Winogrande": 78.69, + "GSM8K": 61.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a932ff3b8c3186bb12224857dd412f1cda56546e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mncai\/agiin-13.6B-v0.1", + "Average \u2b06\ufe0f": 68.4, + "ARC": 69.45, + "HellaSwag": 86.64, + "MMLU": 61.15, + "TruthfulQA": 67.97, + "Winogrande": 78.69, + "GSM8K": 46.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.78, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "6c93ca1d60b09b9b91e15c57dc8525827d371798", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xDAN-AI\/xDAN-L1-Chat-RL-v1", + "Average \u2b06\ufe0f": 68.38, + "ARC": 66.3, + "HellaSwag": 85.81, + "MMLU": 63.21, + "TruthfulQA": 56.7, + "Winogrande": 78.85, + "GSM8K": 59.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 55.0, + "Available on the hub": true, + "Model sha": "0591b1690e5b7c800758f9f5de17a2e60cecf11e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/PlatYi-34B-Llama", + "Average \u2b06\ufe0f": 68.37, + "ARC": 67.83, + "HellaSwag": 85.35, + "MMLU": 78.26, + "TruthfulQA": 53.46, + "Winogrande": 82.87, + "GSM8K": 42.46, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e641a44c60ddf1f31d898ca53810ccb1e7a30972", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "budecosystem\/genz-70b", + "Average \u2b06\ufe0f": 68.35, + "ARC": 71.42, + "HellaSwag": 87.99, + "MMLU": 70.78, + "TruthfulQA": 62.66, + "Winogrande": 83.5, + "GSM8K": 33.74, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 29.0, + "Available on the hub": false, + "Model sha": "32110b4f33e5e80073ca1f47638482fdc0e19297", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "amu\/zen_moe", + "Average \u2b06\ufe0f": 68.34, + "ARC": 63.82, + "HellaSwag": 85.05, + "MMLU": 64.75, + "TruthfulQA": 50.03, + "Winogrande": 81.06, + "GSM8K": 65.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5e6e23c4da1c3b6049a42d755cdf74848efd454a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Dumb-Maidlet", + "Average \u2b06\ufe0f": 68.34, + "ARC": 66.81, + "HellaSwag": 86.06, + "MMLU": 65.17, + "TruthfulQA": 50.7, + "Winogrande": 80.19, + "GSM8K": 61.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1bbd507bb7dd502bbca4105406a6e57abe3c1187", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ZoidBB\/Jovian-10.7B-v1.0", + "Average \u2b06\ufe0f": 68.34, + "ARC": 67.06, + "HellaSwag": 86.39, + "MMLU": 65.5, + "TruthfulQA": 52.0, + "Winogrande": 81.45, + "GSM8K": 57.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ba8433fe1cdf03a7fe25650d99219d34fce13bb8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/ColorShadow-7B", + "Average \u2b06\ufe0f": 68.34, + "ARC": 67.83, + "HellaSwag": 85.15, + "MMLU": 61.69, + "TruthfulQA": 59.56, + "Winogrande": 80.58, + "GSM8K": 55.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6fafdfbf1a92be78735623506bf676f5d8f7030a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decruz07\/kellemar-DPO-7B-v1.01", + "Average \u2b06\ufe0f": 68.32, + "ARC": 65.78, + "HellaSwag": 85.04, + "MMLU": 63.24, + "TruthfulQA": 55.54, + "Winogrande": 78.69, + "GSM8K": 61.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "b032e5ce518cf12383f4ec12952732d21f8321af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/PlatYi-34B-Llama-Q-FastChat", + "Average \u2b06\ufe0f": 68.31, + "ARC": 66.13, + "HellaSwag": 85.25, + "MMLU": 78.37, + "TruthfulQA": 53.62, + "Winogrande": 82.16, + "GSM8K": 44.35, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dab86ae57fe51dc5e993769ebb69a173637852bc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Falkor-8x7B-MoE", + "Average \u2b06\ufe0f": 68.31, + "ARC": 66.3, + "HellaSwag": 85.03, + "MMLU": 64.13, + "TruthfulQA": 53.5, + "Winogrande": 80.19, + "GSM8K": 60.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "8a13e5399c12811d178cea09ffa719596410c9b4", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/Hermes-low-tune-3.1", + "Average \u2b06\ufe0f": 68.31, + "ARC": 65.44, + "HellaSwag": 84.6, + "MMLU": 64.13, + "TruthfulQA": 53.59, + "Winogrande": 78.61, + "GSM8K": 63.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": null, + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "836fc89c13c6e93f6afe86a756585c2cf455cfe2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "jeiku\/NarrativeNexus_7B", + "Average \u2b06\ufe0f": 68.3, + "ARC": 66.13, + "HellaSwag": 85.74, + "MMLU": 63.17, + "TruthfulQA": 63.95, + "Winogrande": 79.01, + "GSM8K": 51.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "98a4cb1db6369cda6330441ad083f4d1fa3bca29", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Intel\/neural-chat-7b-v3-2", + "Average \u2b06\ufe0f": 68.29, + "ARC": 67.49, + "HellaSwag": 83.92, + "MMLU": 63.55, + "TruthfulQA": 59.68, + "Winogrande": 79.95, + "GSM8K": 55.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 52.0, + "Available on the hub": true, + "Model sha": "2ecaf100bcf63da6cf87dd7bfbea5732fa74c413", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Prima-LelantaclesV4-7b-16k-bf16", + "Average \u2b06\ufe0f": 68.28, + "ARC": 66.04, + "HellaSwag": 85.07, + "MMLU": 64.7, + "TruthfulQA": 54.76, + "Winogrande": 80.27, + "GSM8K": 58.83, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4021f84b780a27eefd2f0e32a0c4ec4c3a01761d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Pallas-0.5-LASER-0.4", + "Average \u2b06\ufe0f": 68.28, + "ARC": 63.31, + "HellaSwag": 82.74, + "MMLU": 74.32, + "TruthfulQA": 55.25, + "Winogrande": 80.58, + "GSM8K": 53.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b2f3a60d2cbf70d773f45cc9a7363481f7d1027f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/Xwin-LM-70B-V0.1_Jannie", + "Average \u2b06\ufe0f": 68.26, + "ARC": 71.16, + "HellaSwag": 86.86, + "MMLU": 69.56, + "TruthfulQA": 60.14, + "Winogrande": 81.06, + "GSM8K": 40.79, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3c4341265d5a1be0d7125bd0eadc455632b6cc1f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decruz07\/kellemar-DPO-7B", + "Average \u2b06\ufe0f": 68.26, + "ARC": 66.04, + "HellaSwag": 85.21, + "MMLU": 63.42, + "TruthfulQA": 55.55, + "Winogrande": 78.93, + "GSM8K": 60.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "860ee984db0e2830a969fc616128c4c7d2bca233", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xenon1\/Eclipse-7B", + "Average \u2b06\ufe0f": 68.25, + "ARC": 62.54, + "HellaSwag": 84.19, + "MMLU": 64.92, + "TruthfulQA": 53.37, + "Winogrande": 84.29, + "GSM8K": 60.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "596b923442ef607dcec88d1c1af8f6cefbb82b5c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Walmart-the-bag\/WordWoven-13B", + "Average \u2b06\ufe0f": 68.25, + "ARC": 66.13, + "HellaSwag": 85.81, + "MMLU": 64.06, + "TruthfulQA": 54.45, + "Winogrande": 78.93, + "GSM8K": 60.12, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d398693041f482ee7ee9c91c804206e7f62ea58c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "elinas\/chronos007-70b", + "Average \u2b06\ufe0f": 68.25, + "ARC": 70.14, + "HellaSwag": 87.52, + "MMLU": 69.33, + "TruthfulQA": 57.65, + "Winogrande": 82.24, + "GSM8K": 42.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "c775f87a56f00725de4263f8d527995d40f611c4", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "itsliupeng\/llama2_70b_mmlu", + "Average \u2b06\ufe0f": 68.24, + "ARC": 65.61, + "HellaSwag": 87.37, + "MMLU": 71.89, + "TruthfulQA": 49.15, + "Winogrande": 82.4, + "GSM8K": 52.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a0592c8eeba5ba1519dd6843774baca1d400d00e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decapoda-research\/Antares-11b-v1", + "Average \u2b06\ufe0f": 68.24, + "ARC": 64.51, + "HellaSwag": 84.85, + "MMLU": 65.96, + "TruthfulQA": 52.84, + "Winogrande": 82.95, + "GSM8K": 58.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "f5bda513641d782ab5278e993eb3ba8c7799f1b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decruz07\/kellemar-DPO-7B", + "Average \u2b06\ufe0f": 68.23, + "ARC": 66.21, + "HellaSwag": 85.25, + "MMLU": 63.38, + "TruthfulQA": 55.53, + "Winogrande": 78.37, + "GSM8K": 60.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "860ee984db0e2830a969fc616128c4c7d2bca233", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/NeuralHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 68.22, + "ARC": 66.55, + "HellaSwag": 84.9, + "MMLU": 63.32, + "TruthfulQA": 54.93, + "Winogrande": 78.3, + "GSM8K": 61.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 138.0, + "Available on the hub": true, + "Model sha": "351028e0532a084c2c1370029fcf2ef805da3929", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "martyn\/mixtral-megamerge-dare-8x7b-v2", + "Average \u2b06\ufe0f": 68.2, + "ARC": 66.47, + "HellaSwag": 86.11, + "MMLU": 69.14, + "TruthfulQA": 53.81, + "Winogrande": 79.79, + "GSM8K": 53.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a2dda73a962e3bda8893d951c836711e8ca84cea", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "vistagi\/Mixtral-8x7b-v0.1-dpo", + "Average \u2b06\ufe0f": 68.18, + "ARC": 66.55, + "HellaSwag": 86.4, + "MMLU": 71.65, + "TruthfulQA": 46.74, + "Winogrande": 81.53, + "GSM8K": 56.18, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9eb8bc4d6874f44022930456c287e0ecc4661568", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "vistagi\/Mixtral-8x7b-v0.1-sft", + "Average \u2b06\ufe0f": 68.18, + "ARC": 66.55, + "HellaSwag": 86.4, + "MMLU": 71.65, + "TruthfulQA": 46.74, + "Winogrande": 81.53, + "GSM8K": 56.18, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fb517dd1f789b474803895a0dc5cc16832268f21", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "OrionStarAI\/OrionStar-Yi-34B-Chat-Llama", + "Average \u2b06\ufe0f": 68.17, + "ARC": 64.93, + "HellaSwag": 84.34, + "MMLU": 73.67, + "TruthfulQA": 53.35, + "Winogrande": 78.85, + "GSM8K": 53.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "333c788e0d026cdb76bb827b8dcbc14a859ae2cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Sensualize-Solar-10.7B", + "Average \u2b06\ufe0f": 68.17, + "ARC": 65.02, + "HellaSwag": 84.55, + "MMLU": 65.27, + "TruthfulQA": 53.63, + "Winogrande": 83.98, + "GSM8K": 56.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "126d7e645300a7773044408f77a810bc4f423949", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sethuiyer\/Chikuma_10.7B", + "Average \u2b06\ufe0f": 68.17, + "ARC": 65.7, + "HellaSwag": 84.31, + "MMLU": 64.81, + "TruthfulQA": 57.01, + "Winogrande": 79.56, + "GSM8K": 57.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "3c99ba83d1b6cdee68696fc8443dbd4c71cf9cfe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azure99\/blossom-v3_1-yi-34b", + "Average \u2b06\ufe0f": 68.16, + "ARC": 65.36, + "HellaSwag": 84.24, + "MMLU": 74.37, + "TruthfulQA": 56.06, + "Winogrande": 82.08, + "GSM8K": 46.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "2ec5cbb112a31c62c8631b89fbde0aebaabb6e0a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-llama2-70b-v10.1-bf16", + "Average \u2b06\ufe0f": 68.16, + "ARC": 61.86, + "HellaSwag": 83.13, + "MMLU": 67.41, + "TruthfulQA": 56.18, + "Winogrande": 80.11, + "GSM8K": 60.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 49.0, + "Available on the hub": false, + "Model sha": "a6ee90d262ac729f90ed8de97127766df070074c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/AZG", + "Average \u2b06\ufe0f": 68.16, + "ARC": 62.88, + "HellaSwag": 82.02, + "MMLU": 70.29, + "TruthfulQA": 53.84, + "Winogrande": 79.95, + "GSM8K": 59.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "36c17124ff891121c39f2d5e4d203daad5350c48", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "argilla\/CapybaraHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 68.14, + "ARC": 65.78, + "HellaSwag": 85.45, + "MMLU": 63.13, + "TruthfulQA": 56.91, + "Winogrande": 78.3, + "GSM8K": 59.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "488b5d3a878dcbadf3f316dca9332f484ffd4e0d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LoSboccacc\/orthogonal-2x7B-base", + "Average \u2b06\ufe0f": 68.13, + "ARC": 66.89, + "HellaSwag": 85.54, + "MMLU": 62.49, + "TruthfulQA": 66.0, + "Winogrande": 77.03, + "GSM8K": 50.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b96572f91bdbb612299825f9ce793dabd63917dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fzzhang\/Marcoroni-neural-chat-7B-v2_gsm8k_merged", + "Average \u2b06\ufe0f": 68.13, + "ARC": 65.78, + "HellaSwag": 85.26, + "MMLU": 64.26, + "TruthfulQA": 53.18, + "Winogrande": 78.93, + "GSM8K": 61.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dfabf300a516c8a8695bc62784c2b0bc2db7242b", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Fredithefish\/OpenZephyrChat", + "Average \u2b06\ufe0f": 68.12, + "ARC": 64.85, + "HellaSwag": 85.08, + "MMLU": 64.92, + "TruthfulQA": 48.24, + "Winogrande": 81.06, + "GSM8K": 64.59, + "Type": "", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "146727eb2ebe09ea90552b0b22cb0abbfb830999", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NousResearch\/Nous-Hermes-2-Mistral-7B-DPO", + "Average \u2b06\ufe0f": 68.1, + "ARC": 65.7, + "HellaSwag": 84.94, + "MMLU": 63.25, + "TruthfulQA": 55.78, + "Winogrande": 78.45, + "GSM8K": 60.5, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": true, + "Model sha": "868f0aaeba382aa63bef6ff2bc370be5df16ce9a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "mncai\/agiin-11.1B-v0.0", + "Average \u2b06\ufe0f": 68.1, + "ARC": 67.32, + "HellaSwag": 86.35, + "MMLU": 64.99, + "TruthfulQA": 67.67, + "Winogrande": 78.85, + "GSM8K": 43.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 11.17, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0b086b46a672f450d7b2e8c307526e62d8d0cfdf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/PlatYi-34B-LoRA", + "Average \u2b06\ufe0f": 68.1, + "ARC": 67.15, + "HellaSwag": 85.37, + "MMLU": 78.46, + "TruthfulQA": 53.32, + "Winogrande": 83.66, + "GSM8K": 40.64, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5dcc36255b4632ba32a6b940fa43d53764a3fae3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NousResearch\/Nous-Hermes-2-Mistral-7B-DPO", + "Average \u2b06\ufe0f": 68.1, + "ARC": 66.04, + "HellaSwag": 84.95, + "MMLU": 63.36, + "TruthfulQA": 55.75, + "Winogrande": 78.06, + "GSM8K": 60.42, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": true, + "Model sha": "868f0aaeba382aa63bef6ff2bc370be5df16ce9a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Voldemort-10B", + "Average \u2b06\ufe0f": 68.08, + "ARC": 64.42, + "HellaSwag": 84.25, + "MMLU": 62.87, + "TruthfulQA": 59.92, + "Winogrande": 77.03, + "GSM8K": 59.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f13fc663669481fae7dcff5a218623b3ca6c79a3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "GreenNode\/Merged-DPO-7B", + "Average \u2b06\ufe0f": 68.06, + "ARC": 68.94, + "HellaSwag": 87.75, + "MMLU": 55.35, + "TruthfulQA": 72.76, + "Winogrande": 78.37, + "GSM8K": 45.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1c0e61c7da6839fe4cc34433b899c5416fadbe18", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/xDAN-SlimOrca", + "Average \u2b06\ufe0f": 68.04, + "ARC": 65.61, + "HellaSwag": 85.7, + "MMLU": 63.67, + "TruthfulQA": 57.68, + "Winogrande": 77.66, + "GSM8K": 57.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f6c9f9451d35e8c3d9d5243324921114409ee077", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/Hermes-low-tune-2", + "Average \u2b06\ufe0f": 68.04, + "ARC": 65.61, + "HellaSwag": 84.47, + "MMLU": 63.69, + "TruthfulQA": 53.18, + "Winogrande": 77.74, + "GSM8K": 63.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5e9fbbcf7c7959356574179f1091bc7bf4033a98", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "llmixer\/BigWeave-v20-110b", + "Average \u2b06\ufe0f": 68.03, + "ARC": 68.17, + "HellaSwag": 88.54, + "MMLU": 70.51, + "TruthfulQA": 62.47, + "Winogrande": 82.08, + "GSM8K": 36.39, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 110.05, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1e363188df8256180530fc42688bdb6b3de66b0a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "deepnight-research\/lil-c3po", + "Average \u2b06\ufe0f": 68.03, + "ARC": 65.02, + "HellaSwag": 84.45, + "MMLU": 62.36, + "TruthfulQA": 68.73, + "Winogrande": 79.16, + "GSM8K": 48.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7888318c72df9f668df20b2916b651b94a6ed77c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "cris177\/DesivoMerge0.1", + "Average \u2b06\ufe0f": 68.01, + "ARC": 65.87, + "HellaSwag": 85.39, + "MMLU": 64.35, + "TruthfulQA": 55.36, + "Winogrande": 78.53, + "GSM8K": 58.53, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d92500827c768d24362b53b94501bee63d65823f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "indischepartij\/OpenMia-Indo-Mistral-7b-v3-refined", + "Average \u2b06\ufe0f": 68.0, + "ARC": 64.42, + "HellaSwag": 84.22, + "MMLU": 62.64, + "TruthfulQA": 53.95, + "Winogrande": 81.53, + "GSM8K": 61.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ce2b8e2503f9e927acbe3314c69d4a04468df55b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/OpenMia-Indo-Mistral-7b-v3-refined", + "Average \u2b06\ufe0f": 68.0, + "ARC": 64.42, + "HellaSwag": 84.22, + "MMLU": 62.64, + "TruthfulQA": 53.95, + "Winogrande": 81.53, + "GSM8K": 61.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c2c84867adc3160d6c39acf3e8cb56413a9000ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "joowon99\/SOLAR-10.7B-ko_alpaca", + "Average \u2b06\ufe0f": 67.98, + "ARC": 64.16, + "HellaSwag": 82.62, + "MMLU": 65.71, + "TruthfulQA": 55.95, + "Winogrande": 81.06, + "GSM8K": 58.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "04b63652663be2d6c7178577781efdd737b3c37a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Walmart-the-bag\/openchat-3.5-Infinity", + "Average \u2b06\ufe0f": 67.95, + "ARC": 62.63, + "HellaSwag": 84.05, + "MMLU": 64.65, + "TruthfulQA": 51.99, + "Winogrande": 80.11, + "GSM8K": 64.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d117307b5b813186aa4707ff602f0fb056752d66", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/bagel-dpo-7b-v0.1", + "Average \u2b06\ufe0f": 67.95, + "ARC": 66.72, + "HellaSwag": 84.16, + "MMLU": 64.24, + "TruthfulQA": 64.05, + "Winogrande": 80.9, + "GSM8K": 47.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 40.0, + "Available on the hub": true, + "Model sha": "6444a0bc809bad1322820b48707746f027e01b96", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Pallas-0.5-LASER-exp2-0.1", + "Average \u2b06\ufe0f": 67.92, + "ARC": 62.97, + "HellaSwag": 82.11, + "MMLU": 74.66, + "TruthfulQA": 55.24, + "Winogrande": 79.79, + "GSM8K": 52.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4369d91f05edaba98055e476a054441eee27ca37", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Liangmingxin\/ThetaWave-7B-sft", + "Average \u2b06\ufe0f": 67.92, + "ARC": 63.14, + "HellaSwag": 84.42, + "MMLU": 63.78, + "TruthfulQA": 59.74, + "Winogrande": 79.64, + "GSM8K": 56.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "ab3b156ff4a40d0e95f77b395aaa655a78b1f198", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "freecs\/Zero-7B-test-2", + "Average \u2b06\ufe0f": 67.91, + "ARC": 66.13, + "HellaSwag": 84.77, + "MMLU": 62.98, + "TruthfulQA": 59.95, + "Winogrande": 80.03, + "GSM8K": 53.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f84d973ccd63d8380994ce83a49b16ba7b4034db", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Prima-Pastacles-7b", + "Average \u2b06\ufe0f": 67.91, + "ARC": 66.04, + "HellaSwag": 85.83, + "MMLU": 64.21, + "TruthfulQA": 56.69, + "Winogrande": 79.64, + "GSM8K": 55.04, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "0375c801fc511b3c63ece6e9c6e05bc926d1cfb4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/Ryu-4x7B-MoE-bf16", + "Average \u2b06\ufe0f": 67.9, + "ARC": 66.47, + "HellaSwag": 83.1, + "MMLU": 63.89, + "TruthfulQA": 64.96, + "Winogrande": 79.24, + "GSM8K": 49.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "26e93b95a192650f8b145d103dead6162568953c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Test157t\/Echidna-7b-128k", + "Average \u2b06\ufe0f": 67.88, + "ARC": 66.13, + "HellaSwag": 85.18, + "MMLU": 63.04, + "TruthfulQA": 56.07, + "Winogrande": 80.03, + "GSM8K": 56.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "9bbbcdae306c8e5a8a7c695411274321abcea485", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/solarized-18B-dpo", + "Average \u2b06\ufe0f": 67.88, + "ARC": 68.34, + "HellaSwag": 87.79, + "MMLU": 63.89, + "TruthfulQA": 66.49, + "Winogrande": 80.51, + "GSM8K": 40.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 17.93, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "92f4d0deff86b73f0ac57367c1f86d3b22575530", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/PlatYi-34B-Llama-Q-v2", + "Average \u2b06\ufe0f": 67.88, + "ARC": 61.09, + "HellaSwag": 85.09, + "MMLU": 76.59, + "TruthfulQA": 52.65, + "Winogrande": 82.79, + "GSM8K": 49.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "10ca8ee92ce7e749b8480de603bd8599d8d1fb29", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Einstein-openchat-7B", + "Average \u2b06\ufe0f": 67.87, + "ARC": 65.1, + "HellaSwag": 83.57, + "MMLU": 64.01, + "TruthfulQA": 54.51, + "Winogrande": 79.16, + "GSM8K": 60.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d90583c8391ecadb2ea1b47951e8b7817733447b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "meta-llama\/Llama-2-70b-hf", + "Average \u2b06\ufe0f": 67.87, + "ARC": 67.32, + "HellaSwag": 87.33, + "MMLU": 69.83, + "TruthfulQA": 44.92, + "Winogrande": 83.74, + "GSM8K": 54.06, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 755.0, + "Available on the hub": false, + "Model sha": "ed7b07231238f836b99bf45701b9a0063576b194", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "martyn\/mixtral-megamerge-dare-8x7b-v2", + "Average \u2b06\ufe0f": 67.87, + "ARC": 66.47, + "HellaSwag": 86.05, + "MMLU": 69.08, + "TruthfulQA": 53.82, + "Winogrande": 79.32, + "GSM8K": 52.46, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a2dda73a962e3bda8893d951c836711e8ca84cea", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "openagi-project\/OpenAGI-7B-v0.1", + "Average \u2b06\ufe0f": 67.87, + "ARC": 68.26, + "HellaSwag": 85.06, + "MMLU": 61.6, + "TruthfulQA": 59.4, + "Winogrande": 79.79, + "GSM8K": 53.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8f6bcbc440db8044af878f4a60e7fd000741daa5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "indischepartij\/MiaLatte-Indo-Mistral-7b", + "Average \u2b06\ufe0f": 67.86, + "ARC": 66.55, + "HellaSwag": 85.23, + "MMLU": 63.93, + "TruthfulQA": 56.04, + "Winogrande": 80.35, + "GSM8K": 55.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e6ad0daaeb0e2d1f4b01fb8f409b146a4b752317", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/PlatYi-34B-200k-Q-FastChat", + "Average \u2b06\ufe0f": 67.85, + "ARC": 64.93, + "HellaSwag": 84.46, + "MMLU": 77.13, + "TruthfulQA": 48.38, + "Winogrande": 80.74, + "GSM8K": 51.48, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "92a96144f94c24341cb6a40259be28627bc76298", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/Hermes-low-tune-2", + "Average \u2b06\ufe0f": 67.85, + "ARC": 65.27, + "HellaSwag": 84.41, + "MMLU": 63.63, + "TruthfulQA": 53.12, + "Winogrande": 78.22, + "GSM8K": 62.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5e9fbbcf7c7959356574179f1091bc7bf4033a98", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "tiiuae\/falcon-180B", + "Average \u2b06\ufe0f": 67.85, + "ARC": 69.45, + "HellaSwag": 88.86, + "MMLU": 70.5, + "TruthfulQA": 45.47, + "Winogrande": 86.9, + "GSM8K": 45.94, + "Type": "pretrained", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 179.52, + "Hub \u2764\ufe0f": 1044.0, + "Available on the hub": true, + "Model sha": "71a1a70b629e9963f7b4601e82f3f9079d48011e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beberik\/Nyxene-v2-11B", + "Average \u2b06\ufe0f": 67.84, + "ARC": 67.41, + "HellaSwag": 84.54, + "MMLU": 65.26, + "TruthfulQA": 55.62, + "Winogrande": 79.56, + "GSM8K": 54.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "07d017d24117fabce2e7b67819f6689e3187404f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/OpenHermes-2.5-neural-chat-7b-v3-1-7B", + "Average \u2b06\ufe0f": 67.84, + "ARC": 66.55, + "HellaSwag": 84.47, + "MMLU": 63.34, + "TruthfulQA": 61.22, + "Winogrande": 78.37, + "GSM8K": 53.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 40.0, + "Available on the hub": true, + "Model sha": "2e72eb3999108b7a9c7d0d0c6b8d81ad3470f1f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "freecs\/Zero-7B-test-1", + "Average \u2b06\ufe0f": 67.83, + "ARC": 66.13, + "HellaSwag": 84.62, + "MMLU": 63.12, + "TruthfulQA": 58.97, + "Winogrande": 79.64, + "GSM8K": 54.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6da901880f66d738a6899f65a881c46a49db51b7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Swisslex\/Mixtral-Orca-v0.1", + "Average \u2b06\ufe0f": 67.82, + "ARC": 69.71, + "HellaSwag": 88.88, + "MMLU": 66.06, + "TruthfulQA": 63.85, + "Winogrande": 81.14, + "GSM8K": 37.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9adcd9c408cce6c9c5e403dfda429bf90184a3e9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/NarutoDolphin-7B", + "Average \u2b06\ufe0f": 67.82, + "ARC": 63.82, + "HellaSwag": 84.17, + "MMLU": 62.85, + "TruthfulQA": 59.13, + "Winogrande": 77.51, + "GSM8K": 59.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fcf546ffbfdee6e9bd288eec27316cac533d1ffe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/NarutoDolphin-10B", + "Average \u2b06\ufe0f": 67.82, + "ARC": 63.82, + "HellaSwag": 84.17, + "MMLU": 62.85, + "TruthfulQA": 59.13, + "Winogrande": 77.51, + "GSM8K": 59.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "20c3e2a3d13afb7340d1261e76528b1cbe6cd7ce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "VAGOsolutions\/SauerkrautLM-Mixtral-8x7B", + "Average \u2b06\ufe0f": 67.8, + "ARC": 68.86, + "HellaSwag": 86.01, + "MMLU": 66.69, + "TruthfulQA": 57.2, + "Winogrande": 80.51, + "GSM8K": 47.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "82dc0ab70090085b4271f0f317f667f180db9872", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "giraffe176\/Open_Maid_Samantha_Hermes_Orca_dare_tiesv0.1", + "Average \u2b06\ufe0f": 67.8, + "ARC": 65.87, + "HellaSwag": 85.48, + "MMLU": 64.5, + "TruthfulQA": 51.92, + "Winogrande": 80.35, + "GSM8K": 58.68, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ce0c36f4e93320b3871d575cf7bb3a3d2ee63b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jan-hq\/stealth-rag-v1.1", + "Average \u2b06\ufe0f": 67.79, + "ARC": 62.12, + "HellaSwag": 83.83, + "MMLU": 64.06, + "TruthfulQA": 49.64, + "Winogrande": 79.32, + "GSM8K": 67.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ad40db97e7329778c9a3781049f7e31c57df83f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xwin-LM\/Xwin-Math-70B-V1.0", + "Average \u2b06\ufe0f": 67.78, + "ARC": 64.51, + "HellaSwag": 84.88, + "MMLU": 66.2, + "TruthfulQA": 51.58, + "Winogrande": 81.53, + "GSM8K": 58.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "00dc7125d7471bb12035667f54e02b9472dfbca6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/DistilHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 67.76, + "ARC": 65.87, + "HellaSwag": 84.78, + "MMLU": 63.65, + "TruthfulQA": 54.24, + "Winogrande": 78.22, + "GSM8K": 59.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b75259311e80e39117c7c31e5f93ebd8e33ffc75", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-7B", + "Average \u2b06\ufe0f": 67.76, + "ARC": 66.81, + "HellaSwag": 83.52, + "MMLU": 62.68, + "TruthfulQA": 52.31, + "Winogrande": 79.08, + "GSM8K": 62.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "ae20703e16d89ba4a4301d12195cede64bd2ebdd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "RatanRohith\/MistralBeagle-RS-7B-V0.1", + "Average \u2b06\ufe0f": 67.75, + "ARC": 69.45, + "HellaSwag": 84.62, + "MMLU": 63.07, + "TruthfulQA": 69.78, + "Winogrande": 81.69, + "GSM8K": 37.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a96439634909a69b9f508195ed53f0b43b034e8e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "liminerity\/Blur-7b-v1.2", + "Average \u2b06\ufe0f": 67.74, + "ARC": 65.36, + "HellaSwag": 83.88, + "MMLU": 63.45, + "TruthfulQA": 60.3, + "Winogrande": 80.58, + "GSM8K": 52.84, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6311ad57d16c3d9724930fc0aa5b38fc844eb977", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Q-bert\/Bumblebee-7B", + "Average \u2b06\ufe0f": 67.73, + "ARC": 63.4, + "HellaSwag": 84.16, + "MMLU": 64.0, + "TruthfulQA": 50.96, + "Winogrande": 78.22, + "GSM8K": 65.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0c95c597b9c6c5563273126d1306fdd56bd31618", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051612\/B0122", + "Average \u2b06\ufe0f": 67.73, + "ARC": 67.92, + "HellaSwag": 84.92, + "MMLU": 81.53, + "TruthfulQA": 58.2, + "Winogrande": 80.82, + "GSM8K": 32.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9123a8512a24024afe2dac6f67cb28dca10cceb2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beberik\/Nyxene-11B", + "Average \u2b06\ufe0f": 67.72, + "ARC": 68.34, + "HellaSwag": 84.54, + "MMLU": 65.09, + "TruthfulQA": 57.5, + "Winogrande": 79.08, + "GSM8K": 51.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "55e115157836e1529dd28fc56e2900a5f0e79b89", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PetroGPT\/Voldemort-10B-DPO", + "Average \u2b06\ufe0f": 67.69, + "ARC": 65.7, + "HellaSwag": 84.79, + "MMLU": 62.82, + "TruthfulQA": 61.33, + "Winogrande": 77.27, + "GSM8K": 54.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dfb9681fdbcd421f15f9cc3fb5d4df9adb539944", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PetroGPT\/Voldemort-10B-DPO", + "Average \u2b06\ufe0f": 67.68, + "ARC": 66.04, + "HellaSwag": 84.84, + "MMLU": 62.88, + "TruthfulQA": 61.44, + "Winogrande": 77.03, + "GSM8K": 53.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dfb9681fdbcd421f15f9cc3fb5d4df9adb539944", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Euryale-1.3-L2-70B", + "Average \u2b06\ufe0f": 67.66, + "ARC": 70.82, + "HellaSwag": 87.92, + "MMLU": 70.39, + "TruthfulQA": 59.85, + "Winogrande": 82.79, + "GSM8K": 34.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 38.0, + "Available on the hub": true, + "Model sha": "6e3ce78eb5346bf3a5ee88cd60c25dc0d73de639", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Eurdem\/Megatron-Mx", + "Average \u2b06\ufe0f": 67.65, + "ARC": 66.89, + "HellaSwag": 84.98, + "MMLU": 62.08, + "TruthfulQA": 59.95, + "Winogrande": 79.01, + "GSM8K": 52.99, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0e82c4271fa9de78e829c717af871ab7067243c4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "rombodawg\/Everyone-Coder-4x7b-Base", + "Average \u2b06\ufe0f": 67.65, + "ARC": 64.51, + "HellaSwag": 84.76, + "MMLU": 64.35, + "TruthfulQA": 49.19, + "Winogrande": 79.16, + "GSM8K": 63.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 37.0, + "Available on the hub": true, + "Model sha": "df11f29693b1cd4da9967f1c1832c4f4e0eb3303", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "freeCS-dot-org\/OpenAGI-testing-truthyDPO-1", + "Average \u2b06\ufe0f": 67.64, + "ARC": 67.32, + "HellaSwag": 85.99, + "MMLU": 63.12, + "TruthfulQA": 71.12, + "Winogrande": 81.22, + "GSM8K": 37.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "07fc27e045d1388a9e0afb3bc12ac595c8cb34be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mrfakename\/NeuralOrca-7B-v1", + "Average \u2b06\ufe0f": 67.64, + "ARC": 65.27, + "HellaSwag": 85.07, + "MMLU": 63.68, + "TruthfulQA": 54.58, + "Winogrande": 78.77, + "GSM8K": 58.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "32fb215494467cc6fa2f283a4b02f23546a26807", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/DPOpenHermes-7B", + "Average \u2b06\ufe0f": 67.63, + "ARC": 65.96, + "HellaSwag": 85.9, + "MMLU": 63.98, + "TruthfulQA": 56.92, + "Winogrande": 78.22, + "GSM8K": 54.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "f7742bd00c7d66791e94882b196b4d96fb88e63a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JaeyeonKang\/CCK-v2.0-DPO", + "Average \u2b06\ufe0f": 67.62, + "ARC": 65.87, + "HellaSwag": 86.81, + "MMLU": 62.1, + "TruthfulQA": 69.33, + "Winogrande": 82.16, + "GSM8K": 39.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "84ceccea3e3cde7348a07f3e2bfb1f58b07b38ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/MetaMath-NeuralHermes-2.5-Mistral-7B-Linear", + "Average \u2b06\ufe0f": 67.6, + "ARC": 62.8, + "HellaSwag": 84.21, + "MMLU": 63.43, + "TruthfulQA": 48.57, + "Winogrande": 76.8, + "GSM8K": 69.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6aa0b89656b98f8f2212f6822ce665ac9517dbd7", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fangloveskari\/ORCA_LLaMA_70B_QLoRA", + "Average \u2b06\ufe0f": 67.6, + "ARC": 72.27, + "HellaSwag": 87.74, + "MMLU": 70.23, + "TruthfulQA": 63.37, + "Winogrande": 83.66, + "GSM8K": 28.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 52.0, + "Available on the hub": true, + "Model sha": "ef9b04ef02ccc4d96f1181467da92bb6b5baf835", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beberik\/Nyxene-v1-11B", + "Average \u2b06\ufe0f": 67.58, + "ARC": 67.49, + "HellaSwag": 84.52, + "MMLU": 65.12, + "TruthfulQA": 57.28, + "Winogrande": 79.01, + "GSM8K": 52.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1af08865a403f3be77898d7fbc89bd3be5dfb21f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "openaccess-ai-collective\/DPOpenHermes-7B", + "Average \u2b06\ufe0f": 67.58, + "ARC": 65.7, + "HellaSwag": 85.96, + "MMLU": 63.89, + "TruthfulQA": 56.95, + "Winogrande": 78.61, + "GSM8K": 54.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "f7742bd00c7d66791e94882b196b4d96fb88e63a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "r2rss\/Malachite-7b-v0", + "Average \u2b06\ufe0f": 67.58, + "ARC": 67.75, + "HellaSwag": 83.66, + "MMLU": 63.54, + "TruthfulQA": 64.49, + "Winogrande": 81.22, + "GSM8K": 44.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e9b44b31a7ec203b301a7820a1c5000a30ed68a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "SeaLLMs\/SeaLLM-7B-v2", + "Average \u2b06\ufe0f": 67.57, + "ARC": 62.03, + "HellaSwag": 82.32, + "MMLU": 61.89, + "TruthfulQA": 51.11, + "Winogrande": 79.08, + "GSM8K": 68.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": true, + "Model sha": "8bb693e108dc92efdd608767144bc0232721b18a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "fangloveskari\/Platypus_QLoRA_LLaMA_70b", + "Average \u2b06\ufe0f": 67.57, + "ARC": 72.1, + "HellaSwag": 87.46, + "MMLU": 71.02, + "TruthfulQA": 61.18, + "Winogrande": 82.87, + "GSM8K": 30.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "b9b8560832276f60ba6bf37ac913b230a85ac19b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rombodawg\/Everyone-Coder-4x7b-Base", + "Average \u2b06\ufe0f": 67.56, + "ARC": 64.51, + "HellaSwag": 84.81, + "MMLU": 64.27, + "TruthfulQA": 49.16, + "Winogrande": 79.16, + "GSM8K": 63.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 37.0, + "Available on the hub": true, + "Model sha": "df11f29693b1cd4da9967f1c1832c4f4e0eb3303", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/MetaMath-neural-chat-7b-v3-2-Ties", + "Average \u2b06\ufe0f": 67.54, + "ARC": 63.48, + "HellaSwag": 82.34, + "MMLU": 62.25, + "TruthfulQA": 52.06, + "Winogrande": 76.87, + "GSM8K": 68.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2b0436588c205a6ecae5f32617d88b087b3cc644", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bongchoi\/MoMo-70B-LoRA-V1.1", + "Average \u2b06\ufe0f": 67.53, + "ARC": 66.64, + "HellaSwag": 87.16, + "MMLU": 66.76, + "TruthfulQA": 54.98, + "Winogrande": 83.35, + "GSM8K": 46.32, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ade069976a810b6b7caf3173a1aa4bfb30534ec9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "argilla\/DistilabelBeagle14-7B", + "Average \u2b06\ufe0f": 67.52, + "ARC": 71.08, + "HellaSwag": 87.0, + "MMLU": 61.27, + "TruthfulQA": 68.91, + "Winogrande": 80.74, + "GSM8K": 36.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "a7c3dec7418b86dc4b6169d349d0f11199a222ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abideen\/NexoNimbus-MoE-2x7B", + "Average \u2b06\ufe0f": 67.51, + "ARC": 66.81, + "HellaSwag": 85.66, + "MMLU": 64.51, + "TruthfulQA": 53.06, + "Winogrande": 81.53, + "GSM8K": 53.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "b775c263bfde51a9536ce412893b69d87d064fb1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "r2rss\/Malachite-7b-v0", + "Average \u2b06\ufe0f": 67.5, + "ARC": 67.75, + "HellaSwag": 83.68, + "MMLU": 63.64, + "TruthfulQA": 64.54, + "Winogrande": 81.37, + "GSM8K": 44.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e9b44b31a7ec203b301a7820a1c5000a30ed68a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decruz07\/kellemar-DPO-7B-c", + "Average \u2b06\ufe0f": 67.5, + "ARC": 65.7, + "HellaSwag": 84.98, + "MMLU": 63.7, + "TruthfulQA": 54.08, + "Winogrande": 78.3, + "GSM8K": 58.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e9cc6491994a6babaa14f70ad425418d5c4bc7ae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "llmixer\/BigWeave-v6-90b", + "Average \u2b06\ufe0f": 67.47, + "ARC": 65.36, + "HellaSwag": 87.21, + "MMLU": 68.04, + "TruthfulQA": 57.96, + "Winogrande": 81.69, + "GSM8K": 44.58, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 87.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cf0355244f8cb18a0e3128e292219ccf774fe418", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fzzhang\/toten_gsm8k_merged_s", + "Average \u2b06\ufe0f": 67.47, + "ARC": 65.27, + "HellaSwag": 84.7, + "MMLU": 62.83, + "TruthfulQA": 54.92, + "Winogrande": 77.9, + "GSM8K": 59.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "34ed7e1f452179f5b551cae07d4b4e2ac15aac2c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ICBU-NPU\/FashionGPT-70B-V1", + "Average \u2b06\ufe0f": 67.47, + "ARC": 71.08, + "HellaSwag": 87.32, + "MMLU": 70.7, + "TruthfulQA": 63.92, + "Winogrande": 83.66, + "GSM8K": 28.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "060c096af49700760f734c0102250a524d46b3eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/juanako-7b-UNA", + "Average \u2b06\ufe0f": 67.46, + "ARC": 68.17, + "HellaSwag": 85.34, + "MMLU": 62.47, + "TruthfulQA": 65.13, + "Winogrande": 78.85, + "GSM8K": 44.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "3e12f691e1f442f69eaff408677a54ebc69d5dc8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "tourist800\/Mistral-7B-Merge-14-v0.2", + "Average \u2b06\ufe0f": 67.46, + "ARC": 65.02, + "HellaSwag": 85.13, + "MMLU": 64.36, + "TruthfulQA": 54.15, + "Winogrande": 79.24, + "GSM8K": 56.86, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "570081fa881550751d3f2a2be160a8a08b965a8d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "aloobun\/slerp_bun_mistral_7b_v2", + "Average \u2b06\ufe0f": 67.45, + "ARC": 65.61, + "HellaSwag": 85.28, + "MMLU": 64.61, + "TruthfulQA": 48.1, + "Winogrande": 80.82, + "GSM8K": 60.27, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "18a2ee1b7535ccb435b15b78eea285ce8042d21b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/Samantha-1.1-70b", + "Average \u2b06\ufe0f": 67.43, + "ARC": 68.77, + "HellaSwag": 87.46, + "MMLU": 68.6, + "TruthfulQA": 64.85, + "Winogrande": 83.27, + "GSM8K": 31.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a3819d186f5b4d52ced7ddeb7fa16bf66e8a2ea7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/UNA-dolphin-2.6-mistral-7b-dpo-laser", + "Average \u2b06\ufe0f": 67.43, + "ARC": 67.15, + "HellaSwag": 86.31, + "MMLU": 63.36, + "TruthfulQA": 64.15, + "Winogrande": 79.24, + "GSM8K": 44.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "3e2cd605dde0bd7443172c722a1f34a498a36901", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AI-B\/UTENA-7B-V3", + "Average \u2b06\ufe0f": 67.42, + "ARC": 65.96, + "HellaSwag": 85.7, + "MMLU": 64.72, + "TruthfulQA": 53.64, + "Winogrande": 80.27, + "GSM8K": 54.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "unlicense", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "47815871459a27e38d9b981d5096cf777585e461", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nextai-team\/Moe-2x7b-QA-Code", + "Average \u2b06\ufe0f": 67.42, + "ARC": 65.19, + "HellaSwag": 85.36, + "MMLU": 61.71, + "TruthfulQA": 65.23, + "Winogrande": 77.35, + "GSM8K": 49.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "a7c3b2a840ba788a2adbb664f89bc6d95b4a8071", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "stabilityai\/StableBeluga2", + "Average \u2b06\ufe0f": 67.42, + "ARC": 71.08, + "HellaSwag": 86.37, + "MMLU": 68.79, + "TruthfulQA": 59.44, + "Winogrande": 82.95, + "GSM8K": 35.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 873.0, + "Available on the hub": false, + "Model sha": "e4944caa6ece819413b140b8dcecea79fe7e22cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Praneeth\/StarMix-7B-slerp", + "Average \u2b06\ufe0f": 67.41, + "ARC": 65.36, + "HellaSwag": 85.1, + "MMLU": 62.57, + "TruthfulQA": 57.81, + "Winogrande": 79.95, + "GSM8K": 53.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5ab001441b789f05af53f43b07844dcfa63e78a7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beowolx\/CodeNinja-1.0-OpenChat-7B", + "Average \u2b06\ufe0f": 67.4, + "ARC": 63.48, + "HellaSwag": 83.65, + "MMLU": 63.77, + "TruthfulQA": 47.16, + "Winogrande": 79.79, + "GSM8K": 66.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 92.0, + "Available on the hub": true, + "Model sha": "9934c04c767e6ae0f792712a060f02915391d4ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/test_42_70b", + "Average \u2b06\ufe0f": 67.38, + "ARC": 68.26, + "HellaSwag": 87.65, + "MMLU": 70.0, + "TruthfulQA": 48.76, + "Winogrande": 83.66, + "GSM8K": 45.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ca3789cd6b683e97dcd6a5f0367f90a63d7a4e7b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "freecs\/ThetaWave-7B-v0.2", + "Average \u2b06\ufe0f": 67.38, + "ARC": 64.51, + "HellaSwag": 85.0, + "MMLU": 61.01, + "TruthfulQA": 59.95, + "Winogrande": 82.32, + "GSM8K": 51.48, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "308462cc42873575ddd847ab7941304b6d441c2f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GOAT-AI\/GOAT-70B-Storytelling", + "Average \u2b06\ufe0f": 67.38, + "ARC": 68.77, + "HellaSwag": 87.74, + "MMLU": 69.92, + "TruthfulQA": 53.53, + "Winogrande": 83.5, + "GSM8K": 40.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "337fe3de7874d3a09aa1cfe9e78f5efd81c00f43", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "upstage\/Llama-2-70b-instruct", + "Average \u2b06\ufe0f": 67.38, + "ARC": 70.9, + "HellaSwag": 87.48, + "MMLU": 69.8, + "TruthfulQA": 60.97, + "Winogrande": 82.87, + "GSM8K": 32.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 62.0, + "Available on the hub": false, + "Model sha": "8469429924dc2e1a9394b8095753985668a4052e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "charlesdedampierre\/TopicNeuralHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 67.36, + "ARC": 67.06, + "HellaSwag": 85.44, + "MMLU": 63.66, + "TruthfulQA": 55.47, + "Winogrande": 78.3, + "GSM8K": 54.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "c1c3fdde57d33f759b16f87a56c25a834bca0a38", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-v3.0-11B", + "Average \u2b06\ufe0f": 67.35, + "ARC": 64.08, + "HellaSwag": 85.32, + "MMLU": 66.18, + "TruthfulQA": 48.22, + "Winogrande": 84.21, + "GSM8K": 56.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 11.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "236b393ae07c1d80004eeda47ee017a71a899853", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Bucharest-0.1", + "Average \u2b06\ufe0f": 67.35, + "ARC": 65.36, + "HellaSwag": 85.45, + "MMLU": 66.1, + "TruthfulQA": 47.94, + "Winogrande": 82.16, + "GSM8K": 57.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "987e4e74a98f1ff961f1ef388631ee53f1985b9f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Fewshot-Metamath-OrcaVicuna-Mistral", + "Average \u2b06\ufe0f": 67.33, + "ARC": 59.64, + "HellaSwag": 81.82, + "MMLU": 61.69, + "TruthfulQA": 53.23, + "Winogrande": 78.45, + "GSM8K": 69.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "42ac13a68c242f7aa1ffb9385871fc3ae7d8415d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/ColorShadow-7B-v3", + "Average \u2b06\ufe0f": 67.29, + "ARC": 67.58, + "HellaSwag": 85.04, + "MMLU": 60.57, + "TruthfulQA": 62.88, + "Winogrande": 80.11, + "GSM8K": 47.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9dd05fe04e8a0ef7e7c0f72dd9ca2319c5813072", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/NeuralHermes-2.5-Mistral-7B-laser", + "Average \u2b06\ufe0f": 67.29, + "ARC": 66.38, + "HellaSwag": 85.09, + "MMLU": 63.43, + "TruthfulQA": 54.95, + "Winogrande": 78.14, + "GSM8K": 55.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "76efb2db34ee99b591431a3055eca785ffed44f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "diffnamehard\/Mistral-CatMacaroni-slerp-uncensored", + "Average \u2b06\ufe0f": 67.28, + "ARC": 64.25, + "HellaSwag": 84.09, + "MMLU": 62.66, + "TruthfulQA": 56.87, + "Winogrande": 79.72, + "GSM8K": 56.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "18a3b2e5a34765daafb8e36318a4baf33e272c83", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/dolphin-2.6-mistral-7b-dpo-laser", + "Average \u2b06\ufe0f": 67.28, + "ARC": 66.3, + "HellaSwag": 85.73, + "MMLU": 63.16, + "TruthfulQA": 61.71, + "Winogrande": 79.16, + "GSM8K": 47.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 94.0, + "Available on the hub": true, + "Model sha": "05cc9e559e87e7e269401a3843a0e63a6084a85e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/Samantha-1.11-70b", + "Average \u2b06\ufe0f": 67.28, + "ARC": 70.05, + "HellaSwag": 87.55, + "MMLU": 67.82, + "TruthfulQA": 65.02, + "Winogrande": 83.27, + "GSM8K": 29.95, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "49e5b5ee0bed2864f0b38ba8bf9e01ccc5e0ba5f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ChaoticNeutrals\/Lunar_10.7B", + "Average \u2b06\ufe0f": 67.25, + "ARC": 65.87, + "HellaSwag": 84.85, + "MMLU": 64.23, + "TruthfulQA": 53.51, + "Winogrande": 81.37, + "GSM8K": 53.68, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c4f668605515745bb097e3bbbfec808550324704", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jeiku\/Lunar_10.7B", + "Average \u2b06\ufe0f": 67.25, + "ARC": 65.87, + "HellaSwag": 84.85, + "MMLU": 64.23, + "TruthfulQA": 53.51, + "Winogrande": 81.37, + "GSM8K": 53.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8a6dc10058be04af2e76e088a04ab192352416d5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Ana-v1-m7", + "Average \u2b06\ufe0f": 67.24, + "ARC": 67.41, + "HellaSwag": 85.98, + "MMLU": 64.43, + "TruthfulQA": 55.03, + "Winogrande": 78.06, + "GSM8K": 52.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "375e1a29c36bc1bf7bee972a28f47f9db1e85696", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Test157t\/Kunocchini-7b-128k-test", + "Average \u2b06\ufe0f": 67.24, + "ARC": 66.98, + "HellaSwag": 85.62, + "MMLU": 61.27, + "TruthfulQA": 59.35, + "Winogrande": 77.9, + "GSM8K": 52.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": false, + "Model sha": "c3a102205219be392f9fdb12468a394525fc73b4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "louisbrulenaudet\/Pearl-3x7B", + "Average \u2b06\ufe0f": 67.23, + "ARC": 65.53, + "HellaSwag": 85.54, + "MMLU": 64.27, + "TruthfulQA": 52.17, + "Winogrande": 78.69, + "GSM8K": 57.16, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "63499a3e77b66d0709c15208720d48e89b4c1786", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-10.7B-v1.5b", + "Average \u2b06\ufe0f": 67.21, + "ARC": 65.36, + "HellaSwag": 85.33, + "MMLU": 66.24, + "TruthfulQA": 47.38, + "Winogrande": 82.79, + "GSM8K": 56.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "c6659f344448dc66044df9b5b3e223419b0bcfbd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Pallas-0.5-LASER-0.5", + "Average \u2b06\ufe0f": 67.21, + "ARC": 63.48, + "HellaSwag": 82.21, + "MMLU": 74.31, + "TruthfulQA": 54.64, + "Winogrande": 79.64, + "GSM8K": 48.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1ba6929dbc914f50469dd6bf62082bc52207a03b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beberik\/rawr", + "Average \u2b06\ufe0f": 67.21, + "ARC": 63.99, + "HellaSwag": 84.86, + "MMLU": 64.7, + "TruthfulQA": 52.07, + "Winogrande": 79.56, + "GSM8K": 58.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a8853791580ca0841cb7805462df7c57089d6762", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/dolphin-2.6-mistral-7b-dpo", + "Average \u2b06\ufe0f": 67.2, + "ARC": 65.61, + "HellaSwag": 85.48, + "MMLU": 63.24, + "TruthfulQA": 61.47, + "Winogrande": 78.61, + "GSM8K": 48.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 51.0, + "Available on the hub": true, + "Model sha": "5c32e515f3d79beefc110e8a07c3671269a0f5ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/neural-chat-7b-v3-1-OpenHermes-2.5-7B", + "Average \u2b06\ufe0f": 67.19, + "ARC": 66.13, + "HellaSwag": 84.09, + "MMLU": 63.22, + "TruthfulQA": 61.23, + "Winogrande": 77.58, + "GSM8K": 50.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "b620ea7af98730695e051be48273cdded8923a2b", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/Hermes-low-tune", + "Average \u2b06\ufe0f": 67.18, + "ARC": 63.99, + "HellaSwag": 83.75, + "MMLU": 63.6, + "TruthfulQA": 51.37, + "Winogrande": 77.9, + "GSM8K": 62.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "302b18f207e867b5bd918aa268bff0268b8a6f78", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ICBU-NPU\/FashionGPT-70B-V1.2", + "Average \u2b06\ufe0f": 67.17, + "ARC": 73.04, + "HellaSwag": 88.15, + "MMLU": 70.11, + "TruthfulQA": 65.15, + "Winogrande": 82.56, + "GSM8K": 24.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "990a1664fc058de6ee2406af62c0a817d7047304", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "sonthenguyen\/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered", + "Average \u2b06\ufe0f": 67.16, + "ARC": 65.27, + "HellaSwag": 84.62, + "MMLU": 63.82, + "TruthfulQA": 52.91, + "Winogrande": 78.06, + "GSM8K": 58.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f60f1f62c9e7e7440b24cdd7a1333dac739cc359", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "macadeliccc\/laser-dolphin-mixtral-2x7b-dpo", + "Average \u2b06\ufe0f": 67.16, + "ARC": 65.96, + "HellaSwag": 85.8, + "MMLU": 63.17, + "TruthfulQA": 60.76, + "Winogrande": 79.01, + "GSM8K": 48.29, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 33.0, + "Available on the hub": true, + "Model sha": "0ece1807074c4f1b9461e271a8931e4947902fbb", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "berkeley-nest\/Starling-LM-7B-alpha", + "Average \u2b06\ufe0f": 67.13, + "ARC": 63.82, + "HellaSwag": 84.9, + "MMLU": 64.67, + "TruthfulQA": 46.39, + "Winogrande": 80.58, + "GSM8K": 62.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 476.0, + "Available on the hub": true, + "Model sha": "f721e85293598f2ef774e483ae95343e39811577", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/bagel-dpo-7b-v0.4", + "Average \u2b06\ufe0f": 67.13, + "ARC": 67.58, + "HellaSwag": 84.3, + "MMLU": 61.95, + "TruthfulQA": 63.94, + "Winogrande": 78.14, + "GSM8K": 46.85, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "1407000b20cf38cf59d7a2d1143cb0883abe5ab3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lizpreciatior\/lzlv_70b_fp16_hf", + "Average \u2b06\ufe0f": 67.13, + "ARC": 70.14, + "HellaSwag": 87.54, + "MMLU": 70.23, + "TruthfulQA": 60.49, + "Winogrande": 83.43, + "GSM8K": 30.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 56.0, + "Available on the hub": true, + "Model sha": "b366c0bb318ae592023cca894cc6b4421a607a0d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/model_007_v2", + "Average \u2b06\ufe0f": 67.13, + "ARC": 71.42, + "HellaSwag": 87.31, + "MMLU": 68.58, + "TruthfulQA": 62.65, + "Winogrande": 84.14, + "GSM8K": 28.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3d95e0f3598f7a76ab97cb2cc0e4aae957d77479", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/MelangeB-70b", + "Average \u2b06\ufe0f": 67.12, + "ARC": 71.67, + "HellaSwag": 87.5, + "MMLU": 70.03, + "TruthfulQA": 59.36, + "Winogrande": 83.5, + "GSM8K": 30.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "08239fb1e30b1e42b14370f23e942bc51e76027c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Starling-LM-alpha-8x7B-MoE", + "Average \u2b06\ufe0f": 67.11, + "ARC": 63.65, + "HellaSwag": 84.9, + "MMLU": 64.68, + "TruthfulQA": 46.39, + "Winogrande": 80.58, + "GSM8K": 62.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "61a66c526af1238690c815051c0f4ebe866ca588", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "rishiraj\/smol-7b", + "Average \u2b06\ufe0f": 67.11, + "ARC": 63.74, + "HellaSwag": 84.77, + "MMLU": 65.0, + "TruthfulQA": 46.17, + "Winogrande": 80.66, + "GSM8K": 62.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "d3e24684f38e0332cf4a6c70a37ee894e7a27fdc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decem\/Dionysus-Mistral-m3-v6", + "Average \u2b06\ufe0f": 67.1, + "ARC": 63.14, + "HellaSwag": 84.51, + "MMLU": 62.82, + "TruthfulQA": 49.49, + "Winogrande": 78.45, + "GSM8K": 64.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "417618a86cd04bfcc48bd987043a4ef096e866cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "sonthenguyen\/OpenHermes-2.5-Mistral-7B-mt-bench-DPO", + "Average \u2b06\ufe0f": 67.1, + "ARC": 65.27, + "HellaSwag": 84.62, + "MMLU": 63.83, + "TruthfulQA": 52.91, + "Winogrande": 78.06, + "GSM8K": 57.92, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3668a898cbb72a4915f6dce6cdbe6ba0c3582026", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "sonthenguyen\/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-corrupted", + "Average \u2b06\ufe0f": 67.09, + "ARC": 65.27, + "HellaSwag": 84.58, + "MMLU": 63.74, + "TruthfulQA": 52.84, + "Winogrande": 78.06, + "GSM8K": 58.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7cb70ae8584ec2ef48372bc4db1210e0502f9654", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "freecs\/ThetaWave-7B-v1", + "Average \u2b06\ufe0f": 67.08, + "ARC": 66.89, + "HellaSwag": 84.91, + "MMLU": 61.62, + "TruthfulQA": 55.96, + "Winogrande": 80.43, + "GSM8K": 52.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7cad16a292a7b96d671e20dad3609d03814149d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "paulilioaica\/Hugo-7B-slerp", + "Average \u2b06\ufe0f": 67.07, + "ARC": 64.51, + "HellaSwag": 84.77, + "MMLU": 62.54, + "TruthfulQA": 57.13, + "Winogrande": 80.03, + "GSM8K": 53.45, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "820dcd204a79f46110fad378907f0be35a266ecb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gqd\/mistral-merge-7b", + "Average \u2b06\ufe0f": 67.07, + "ARC": 63.91, + "HellaSwag": 84.48, + "MMLU": 64.04, + "TruthfulQA": 53.73, + "Winogrande": 77.35, + "GSM8K": 58.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "unlicense", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ffaddf395e00015873137562a8a34e1bb8123b41", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_18-7B-dare_ties", + "Average \u2b06\ufe0f": 67.06, + "ARC": 64.08, + "HellaSwag": 84.37, + "MMLU": 63.65, + "TruthfulQA": 52.17, + "Winogrande": 77.27, + "GSM8K": 60.8, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "157b267cb015d177d88b16e2f25f0307772b99d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "berkeley-nest\/Starling-LM-7B-alpha", + "Average \u2b06\ufe0f": 67.05, + "ARC": 63.65, + "HellaSwag": 84.87, + "MMLU": 64.7, + "TruthfulQA": 46.32, + "Winogrande": 80.43, + "GSM8K": 62.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 476.0, + "Available on the hub": true, + "Model sha": "76e60ca9807f55acd8eff3ec7ae022c5fbdf1e0e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/Bageluccine-2-7B-slerp", + "Average \u2b06\ufe0f": 67.05, + "ARC": 66.38, + "HellaSwag": 85.51, + "MMLU": 62.23, + "TruthfulQA": 65.57, + "Winogrande": 76.87, + "GSM8K": 45.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "551789fbe4826ea310d24aa66f4df7761f0a97b2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-7B-v2", + "Average \u2b06\ufe0f": 67.04, + "ARC": 65.19, + "HellaSwag": 83.39, + "MMLU": 63.6, + "TruthfulQA": 57.17, + "Winogrande": 78.14, + "GSM8K": 54.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 33.0, + "Available on the hub": true, + "Model sha": "0c7f7c85359f15d3e6c361e8192738bdfb14ea6c", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/MetaMath-NeuralHermes-2.5-Mistral-7B-Ties", + "Average \u2b06\ufe0f": 67.03, + "ARC": 62.46, + "HellaSwag": 82.89, + "MMLU": 62.25, + "TruthfulQA": 50.15, + "Winogrande": 75.14, + "GSM8K": 69.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b11bbd94238e1cc568c476844b1900c6e3facfa7", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/franken-SOLAR-18B-v1.0", + "Average \u2b06\ufe0f": 67.03, + "ARC": 65.53, + "HellaSwag": 86.45, + "MMLU": 63.72, + "TruthfulQA": 62.14, + "Winogrande": 78.53, + "GSM8K": 45.79, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 17.93, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "03c5412b8b0a6272cf02b399221ab94dbfd3157e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "meta-math\/MetaMath-70B-V1.0", + "Average \u2b06\ufe0f": 67.02, + "ARC": 68.0, + "HellaSwag": 86.85, + "MMLU": 69.31, + "TruthfulQA": 50.98, + "Winogrande": 82.32, + "GSM8K": 44.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "783a3c7d5d0a75e6e11074f2577b90dd219ef7b1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-70B-v1.2b", + "Average \u2b06\ufe0f": 67.0, + "ARC": 68.77, + "HellaSwag": 87.57, + "MMLU": 68.81, + "TruthfulQA": 57.69, + "Winogrande": 83.9, + "GSM8K": 35.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "7b687d6e4101b8bb8cc4062f8a318d639098a55d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Open-Orca\/Mixtral-SlimOrca-8x7B", + "Average \u2b06\ufe0f": 66.97, + "ARC": 67.66, + "HellaSwag": 85.11, + "MMLU": 67.98, + "TruthfulQA": 54.98, + "Winogrande": 80.51, + "GSM8K": 45.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 50.0, + "Available on the hub": true, + "Model sha": "e06a613acf6c8cb3e5a740e2ed6348b8047d90a8", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "chargoddard\/internlm2-7b-llama", + "Average \u2b06\ufe0f": 66.94, + "ARC": 60.49, + "HellaSwag": 80.99, + "MMLU": 63.16, + "TruthfulQA": 54.25, + "Winogrande": 79.87, + "GSM8K": 62.85, + "Type": "pretrained", + "Architecture": "L;l;a;m;a;F;o;r;C;a;u;s;a;l;L;M", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.74, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "67517f8c49907cf4c1e515b356ce6907189dbdd4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Walmart-the-bag\/Misted-7B", + "Average \u2b06\ufe0f": 66.94, + "ARC": 63.65, + "HellaSwag": 84.14, + "MMLU": 63.94, + "TruthfulQA": 52.0, + "Winogrande": 78.3, + "GSM8K": 59.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "31245dbdcd0ace447a4434ac5e393a90ac862a87", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/neural-chat-7B-v3-2-GPTQ", + "Average \u2b06\ufe0f": 66.93, + "ARC": 65.96, + "HellaSwag": 83.24, + "MMLU": 60.29, + "TruthfulQA": 59.79, + "Winogrande": 79.48, + "GSM8K": 52.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 9.59, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "cfe57da77e55efcb0e1087dc3948aeaa6ca55c74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-70B-v1.2", + "Average \u2b06\ufe0f": 66.9, + "ARC": 70.48, + "HellaSwag": 86.98, + "MMLU": 70.13, + "TruthfulQA": 58.64, + "Winogrande": 83.27, + "GSM8K": 31.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "9b92ee1093b125035ba1649dca6f4ceb9d86a656", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nlpguy\/ColorShadow-7B-v2", + "Average \u2b06\ufe0f": 66.88, + "ARC": 67.15, + "HellaSwag": 84.69, + "MMLU": 60.34, + "TruthfulQA": 62.93, + "Winogrande": 78.85, + "GSM8K": 47.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "63713211df4348f2d73529c49a7cd0c1bb580ad7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "giraffe176\/Open_Hermes_Orca_Mistral-7B", + "Average \u2b06\ufe0f": 66.87, + "ARC": 64.68, + "HellaSwag": 84.63, + "MMLU": 63.93, + "TruthfulQA": 53.34, + "Winogrande": 78.45, + "GSM8K": 56.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "68c4c546542e361c1e1c0cd6b70b7586e55fd7b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Cartinoe5930\/MoE-Merging", + "Average \u2b06\ufe0f": 66.84, + "ARC": 65.44, + "HellaSwag": 84.58, + "MMLU": 61.31, + "TruthfulQA": 57.83, + "Winogrande": 77.66, + "GSM8K": 54.21, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "022dfa677128a9d9b71a5350d7340b6f1f023ea0", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "macadeliccc\/polyglot-math-4x7b", + "Average \u2b06\ufe0f": 66.84, + "ARC": 63.74, + "HellaSwag": 84.85, + "MMLU": 63.57, + "TruthfulQA": 53.78, + "Winogrande": 78.45, + "GSM8K": 56.63, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "13b5f7d30c5db5060b41b2889f1c8df5ef7a8303", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/DPOpenHermes-11B", + "Average \u2b06\ufe0f": 66.83, + "ARC": 66.55, + "HellaSwag": 84.8, + "MMLU": 64.02, + "TruthfulQA": 57.34, + "Winogrande": 76.95, + "GSM8K": 51.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6b78354a0789d3e9d0bfa6dd3d0b52c5e4594c39", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/YarnLake-Swap-7B", + "Average \u2b06\ufe0f": 66.82, + "ARC": 65.27, + "HellaSwag": 85.17, + "MMLU": 64.78, + "TruthfulQA": 49.07, + "Winogrande": 81.45, + "GSM8K": 55.19, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e37156f35e8c4849cd9b3ae83a4a6937279d5105", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-70B-v1.1", + "Average \u2b06\ufe0f": 66.81, + "ARC": 70.05, + "HellaSwag": 87.12, + "MMLU": 70.34, + "TruthfulQA": 57.84, + "Winogrande": 83.66, + "GSM8K": 31.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "05a13f6adfe95a713dff04dc2eaa214c77c2512a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Bucharest-0.2", + "Average \u2b06\ufe0f": 66.81, + "ARC": 64.59, + "HellaSwag": 84.87, + "MMLU": 66.03, + "TruthfulQA": 45.3, + "Winogrande": 83.27, + "GSM8K": 56.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8cbf07c769e920054948dada4d4a1d4f914d32fa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Frostwind-10.7B-v1", + "Average \u2b06\ufe0f": 66.81, + "ARC": 63.99, + "HellaSwag": 85.36, + "MMLU": 64.49, + "TruthfulQA": 50.41, + "Winogrande": 83.82, + "GSM8K": 52.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "5b465f636e1d354718e393e85914865a64840903", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dillfrescott\/sonya-medium-x8-MoE", + "Average \u2b06\ufe0f": 66.76, + "ARC": 64.25, + "HellaSwag": 83.7, + "MMLU": 62.53, + "TruthfulQA": 60.15, + "Winogrande": 76.24, + "GSM8K": 53.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "wtfpl", + "#Params (B)": 69.92, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "e8151c3609889dc7746ca748f4e16098663a5880", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Frostwind-10.7B-v1", + "Average \u2b06\ufe0f": 66.75, + "ARC": 64.16, + "HellaSwag": 85.38, + "MMLU": 64.64, + "TruthfulQA": 50.43, + "Winogrande": 83.74, + "GSM8K": 52.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "5b465f636e1d354718e393e85914865a64840903", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v4-qwen1_5-14b", + "Average \u2b06\ufe0f": 66.74, + "ARC": 57.34, + "HellaSwag": 79.84, + "MMLU": 67.92, + "TruthfulQA": 55.21, + "Winogrande": 73.64, + "GSM8K": 66.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b505d4e2311a709de56a214a33820f5a4ee0d3e5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-70B", + "Average \u2b06\ufe0f": 66.72, + "ARC": 69.45, + "HellaSwag": 87.11, + "MMLU": 68.91, + "TruthfulQA": 59.79, + "Winogrande": 83.66, + "GSM8K": 31.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "d63dfdd0baed756981f5f78f7419fd822c572362", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "macadeliccc\/laser-dolphin-mixtral-4x7b-dpo", + "Average \u2b06\ufe0f": 66.71, + "ARC": 64.93, + "HellaSwag": 85.81, + "MMLU": 63.04, + "TruthfulQA": 63.77, + "Winogrande": 77.82, + "GSM8K": 44.88, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "472637ca2bf2bfb08aa4b5ebcdc5f89f48c7b257", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "nextai-team\/Moe-3x7b-QA-Code-Inst", + "Average \u2b06\ufe0f": 66.7, + "ARC": 64.25, + "HellaSwag": 84.6, + "MMLU": 62.15, + "TruthfulQA": 63.15, + "Winogrande": 77.43, + "GSM8K": 48.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "9127c38cad1a2b9dd3d3fa7ab71706585b46225d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen2-beta-14B", + "Average \u2b06\ufe0f": 66.7, + "ARC": 56.57, + "HellaSwag": 81.08, + "MMLU": 69.36, + "TruthfulQA": 52.06, + "Winogrande": 73.48, + "GSM8K": 67.63, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "56eee702d3528c6c29c42640625b5631e5ae9aea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "HIT-SCIR\/Chinese-Mixtral-8x7B", + "Average \u2b06\ufe0f": 66.69, + "ARC": 63.57, + "HellaSwag": 85.98, + "MMLU": 70.95, + "TruthfulQA": 45.86, + "Winogrande": 82.08, + "GSM8K": 51.71, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.91, + "Hub \u2764\ufe0f": 40.0, + "Available on the hub": true, + "Model sha": "58d799575d809c0e80ee6964a546aaa3a8569963", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "internlm\/internlm2-7b", + "Average \u2b06\ufe0f": 66.68, + "ARC": 58.02, + "HellaSwag": 81.24, + "MMLU": 65.24, + "TruthfulQA": 48.73, + "Winogrande": 83.82, + "GSM8K": 63.0, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "aac482e5fbfd5a85daa2a8e3aa3a1c5c97331d58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yanolja\/Bookworm-10.7B-v0.4-DPO", + "Average \u2b06\ufe0f": 66.66, + "ARC": 64.68, + "HellaSwag": 84.43, + "MMLU": 65.12, + "TruthfulQA": 52.38, + "Winogrande": 81.14, + "GSM8K": 52.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.8, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "5807ef01a569e3ecda619af66f98271d6bf872f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Test157t\/Hex-Macaroniac-7b", + "Average \u2b06\ufe0f": 66.64, + "ARC": 65.53, + "HellaSwag": 84.68, + "MMLU": 62.43, + "TruthfulQA": 55.93, + "Winogrande": 78.3, + "GSM8K": 52.99, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ae590a93adc146935da5fae38c3cdc7d5d86e16e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Danielbrdz\/Barcenas-10.7b", + "Average \u2b06\ufe0f": 66.63, + "ARC": 64.16, + "HellaSwag": 83.6, + "MMLU": 65.22, + "TruthfulQA": 46.59, + "Winogrande": 82.0, + "GSM8K": 58.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a6ffe3b262cad3a2aee5fd36420f1b36933a7159", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Pallas-0.5-LASER-0.6", + "Average \u2b06\ufe0f": 66.62, + "ARC": 62.46, + "HellaSwag": 81.6, + "MMLU": 74.25, + "TruthfulQA": 54.39, + "Winogrande": 78.45, + "GSM8K": 48.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "0dc221753dbe63c4f5f5727adfe0f35cf05909f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ArianAskari\/NeuralHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 66.62, + "ARC": 64.68, + "HellaSwag": 84.28, + "MMLU": 63.71, + "TruthfulQA": 52.23, + "Winogrande": 77.98, + "GSM8K": 56.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "10017fe004ada8720559ca3ee2339972c4f15eca", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uni-tianyan\/Uni-TianYan", + "Average \u2b06\ufe0f": 66.61, + "ARC": 72.1, + "HellaSwag": 87.4, + "MMLU": 69.91, + "TruthfulQA": 65.81, + "Winogrande": 82.32, + "GSM8K": 22.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 48.0, + "Available on the hub": true, + "Model sha": "46b78b9a10e78283e59c28b56cb59c2f33b0816a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "WizardLM\/WizardMath-7B-V1.1", + "Average \u2b06\ufe0f": 66.61, + "ARC": 61.86, + "HellaSwag": 84.5, + "MMLU": 61.53, + "TruthfulQA": 47.04, + "Winogrande": 77.35, + "GSM8K": 67.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 61.0, + "Available on the hub": false, + "Model sha": "366a19a3a8e64aea2fc77d648bec5738fb1f89ce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yanolja\/Bookworm-10.7B-v0.4-DPO", + "Average \u2b06\ufe0f": 66.59, + "ARC": 64.76, + "HellaSwag": 84.4, + "MMLU": 64.96, + "TruthfulQA": 52.31, + "Winogrande": 80.9, + "GSM8K": 52.24, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.8, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "5807ef01a569e3ecda619af66f98271d6bf872f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Ba2han\/HermesStar-OrcaWind-Synth-11B", + "Average \u2b06\ufe0f": 66.59, + "ARC": 65.27, + "HellaSwag": 83.69, + "MMLU": 65.31, + "TruthfulQA": 48.55, + "Winogrande": 80.11, + "GSM8K": 56.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "61aefa2ac956ce0e8ce40aa2521bdb5634452766", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decapoda-research\/Adrastea-7b-v1.0-dpo", + "Average \u2b06\ufe0f": 66.59, + "ARC": 63.31, + "HellaSwag": 82.3, + "MMLU": 62.26, + "TruthfulQA": 53.1, + "Winogrande": 76.56, + "GSM8K": 62.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cf8ccdae24f5b008c2f29cacadd05dd58e95da54", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yhyu13\/LMCocktail-Mistral-7B-v1", + "Average \u2b06\ufe0f": 66.58, + "ARC": 66.21, + "HellaSwag": 85.69, + "MMLU": 61.64, + "TruthfulQA": 61.37, + "Winogrande": 77.35, + "GSM8K": 47.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "a4563de72fd5fe07b4fcec736e9efe83431df25a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/NeuralPaca-7b", + "Average \u2b06\ufe0f": 66.57, + "ARC": 62.8, + "HellaSwag": 83.01, + "MMLU": 63.02, + "TruthfulQA": 48.32, + "Winogrande": 81.69, + "GSM8K": 60.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4e02c1c08c3ce16db8df2a07db559eaab46a3ac4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NExtNewChattingAI\/shark_tank_ai_7b_v2", + "Average \u2b06\ufe0f": 66.55, + "ARC": 67.75, + "HellaSwag": 87.06, + "MMLU": 58.79, + "TruthfulQA": 62.15, + "Winogrande": 78.45, + "GSM8K": 45.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b0796cb9cd42de2f66f652f162c29fdc57de2332", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-10.7B-v1.5", + "Average \u2b06\ufe0f": 66.55, + "ARC": 65.02, + "HellaSwag": 84.07, + "MMLU": 65.09, + "TruthfulQA": 47.43, + "Winogrande": 83.35, + "GSM8K": 54.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "634a8454c84e415721e7cab1373e0fe8daf0e944", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NExtNewChattingAI\/shark_tank_ai_7b_v2", + "Average \u2b06\ufe0f": 66.54, + "ARC": 67.58, + "HellaSwag": 87.02, + "MMLU": 58.88, + "TruthfulQA": 62.21, + "Winogrande": 78.69, + "GSM8K": 44.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b0796cb9cd42de2f66f652f162c29fdc57de2332", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "shahzebnaveed\/NeuralHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 66.53, + "ARC": 64.85, + "HellaSwag": 84.29, + "MMLU": 63.81, + "TruthfulQA": 52.29, + "Winogrande": 77.98, + "GSM8K": 55.95, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c5026f2abc8876d3a61095f023c39b18c8c685d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/dpopenhermes-alpha-v0", + "Average \u2b06\ufe0f": 66.52, + "ARC": 65.02, + "HellaSwag": 83.96, + "MMLU": 63.67, + "TruthfulQA": 51.75, + "Winogrande": 78.85, + "GSM8K": 55.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "81ce4a9354d3b73276a0fa96b95d384f66d2de3d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Eurdem\/Voltran-1.0-MoE-2x7B", + "Average \u2b06\ufe0f": 66.51, + "ARC": 64.08, + "HellaSwag": 83.74, + "MMLU": 61.26, + "TruthfulQA": 57.48, + "Winogrande": 76.56, + "GSM8K": 55.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0bc5dd29fd96a869293757ab5a56b9a3522eb6dd", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "soniox\/Soniox-7B-v1.0", + "Average \u2b06\ufe0f": 66.5, + "ARC": 63.91, + "HellaSwag": 82.55, + "MMLU": 64.38, + "TruthfulQA": 53.84, + "Winogrande": 78.06, + "GSM8K": 56.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7f93ea62910145552d9332eec2fe824612cddf31", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kevin009\/Llamafia", + "Average \u2b06\ufe0f": 66.49, + "ARC": 66.13, + "HellaSwag": 82.08, + "MMLU": 61.81, + "TruthfulQA": 47.94, + "Winogrande": 80.11, + "GSM8K": 60.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0de1702faa89250ae329b3989c487fb0feb9e3f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "sonthenguyen\/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-original-v2", + "Average \u2b06\ufe0f": 66.47, + "ARC": 64.93, + "HellaSwag": 84.54, + "MMLU": 63.63, + "TruthfulQA": 52.4, + "Winogrande": 77.9, + "GSM8K": 55.42, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9bb10d7285e28a5b8696c704da0e55d11816f77c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rombodawg\/Leaderboard-killer-MoE_4x7b", + "Average \u2b06\ufe0f": 66.47, + "ARC": 63.65, + "HellaSwag": 81.97, + "MMLU": 64.9, + "TruthfulQA": 50.75, + "Winogrande": 75.37, + "GSM8K": 62.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "391ad4593c4fdff7a90271954649a373b80d13d4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "v2ray\/LLaMA-2-Wizard-70B-QLoRA", + "Average \u2b06\ufe0f": 66.47, + "ARC": 67.58, + "HellaSwag": 87.52, + "MMLU": 69.11, + "TruthfulQA": 61.79, + "Winogrande": 82.32, + "GSM8K": 30.48, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4bff676fe29f56d31961794c062aebc36312446e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rishiraj\/uncensored", + "Average \u2b06\ufe0f": 66.46, + "ARC": 66.04, + "HellaSwag": 84.8, + "MMLU": 61.23, + "TruthfulQA": 59.14, + "Winogrande": 79.32, + "GSM8K": 48.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7d2b64d29e68792172d809c51518c9092b5eea72", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/A13", + "Average \u2b06\ufe0f": 66.45, + "ARC": 61.09, + "HellaSwag": 81.7, + "MMLU": 69.62, + "TruthfulQA": 53.25, + "Winogrande": 80.35, + "GSM8K": 52.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c9b20b6f34269c27e56759888c5d42bd045e6da7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "simonveitner\/Math-OpenHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 66.42, + "ARC": 63.05, + "HellaSwag": 83.07, + "MMLU": 63.21, + "TruthfulQA": 50.91, + "Winogrande": 77.19, + "GSM8K": 61.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "db052d375f389aa264bacac47aeb07538698122d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Brillibits\/Instruct_Llama70B_Dolly15k", + "Average \u2b06\ufe0f": 66.42, + "ARC": 68.34, + "HellaSwag": 87.21, + "MMLU": 69.52, + "TruthfulQA": 46.46, + "Winogrande": 84.29, + "GSM8K": 42.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "45444ac60488594e0700e6c7313ff444b4468240", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "maywell\/PiVoT-SOLAR-10.7B-RP", + "Average \u2b06\ufe0f": 66.42, + "ARC": 65.1, + "HellaSwag": 81.83, + "MMLU": 64.26, + "TruthfulQA": 56.54, + "Winogrande": 76.95, + "GSM8K": 53.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "348a5ccfc4c8c9032ae6234a8fca72110ed4e5ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yash21\/OpenMistral-MoE", + "Average \u2b06\ufe0f": 66.42, + "ARC": 64.08, + "HellaSwag": 83.99, + "MMLU": 60.69, + "TruthfulQA": 54.57, + "Winogrande": 76.8, + "GSM8K": 58.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4c212c0361b002474b192010cdd49338e2db7d13", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "rxavier\/Taurus-1.0-Mistral-7B", + "Average \u2b06\ufe0f": 66.4, + "ARC": 63.57, + "HellaSwag": 83.64, + "MMLU": 63.5, + "TruthfulQA": 50.21, + "Winogrande": 78.14, + "GSM8K": 59.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7576d3a7e138017e3da7dd8721c34684f9f8311f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rxavier\/Taurus-7B-1.0", + "Average \u2b06\ufe0f": 66.4, + "ARC": 63.57, + "HellaSwag": 83.64, + "MMLU": 63.5, + "TruthfulQA": 50.21, + "Winogrande": 78.14, + "GSM8K": 59.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "76ed64a2a381a5bffca52d336e1481dce83e16fa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "openaccess-ai-collective\/openhermes-2_5-dpo-no-robots", + "Average \u2b06\ufe0f": 66.4, + "ARC": 64.93, + "HellaSwag": 84.3, + "MMLU": 63.86, + "TruthfulQA": 52.12, + "Winogrande": 77.9, + "GSM8K": 55.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "bee345f7da9816e459846b6bc3dbea6c69850855", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "cris177\/Orca-Hermes-7B-slerp", + "Average \u2b06\ufe0f": 66.39, + "ARC": 64.08, + "HellaSwag": 84.44, + "MMLU": 63.56, + "TruthfulQA": 52.84, + "Winogrande": 77.9, + "GSM8K": 55.5, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1c80f2f1ab153a6926005697fa23617c6de45a2f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "freeCS-dot-org\/OpenAGI-testing-intelDPO-2", + "Average \u2b06\ufe0f": 66.36, + "ARC": 62.8, + "HellaSwag": 84.63, + "MMLU": 62.65, + "TruthfulQA": 58.28, + "Winogrande": 78.85, + "GSM8K": 50.95, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d160d65b1155a68c70ed75838c2bdc7f5ce511e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "paulilioaica\/MoEstral-2x2B", + "Average \u2b06\ufe0f": 66.34, + "ARC": 65.1, + "HellaSwag": 84.82, + "MMLU": 61.62, + "TruthfulQA": 62.72, + "Winogrande": 78.37, + "GSM8K": 45.41, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fa00d779934bc7907f6031c318852b1faa513bf6", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "SC99\/Mistral-7B-privatemix-base-ia", + "Average \u2b06\ufe0f": 66.34, + "ARC": 62.8, + "HellaSwag": 84.85, + "MMLU": 60.54, + "TruthfulQA": 68.76, + "Winogrande": 77.03, + "GSM8K": 44.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e2761606e477ff1540a501dc89b39f65ff16c652", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zangs3011\/mixtral_8x7b_MonsterInstruct", + "Average \u2b06\ufe0f": 66.34, + "ARC": 65.19, + "HellaSwag": 85.81, + "MMLU": 70.15, + "TruthfulQA": 48.47, + "Winogrande": 80.27, + "GSM8K": 48.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5252c3d68fcd69d14cc76488d689e0adb76d881f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "sethuiyer\/CodeCalc-Mistral-7B", + "Average \u2b06\ufe0f": 66.33, + "ARC": 61.95, + "HellaSwag": 83.64, + "MMLU": 62.78, + "TruthfulQA": 47.79, + "Winogrande": 78.3, + "GSM8K": 63.53, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e03e7b8e6ea737f565848caaf3467b75b646c878", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "snorkelai\/Snorkel-Mistral-PairRM-DPO", + "Average \u2b06\ufe0f": 66.31, + "ARC": 66.04, + "HellaSwag": 85.64, + "MMLU": 60.83, + "TruthfulQA": 70.86, + "Winogrande": 77.74, + "GSM8K": 36.77, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": true, + "Model sha": "e4110a5689e146bc07296218f84ae09129168868", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "augtoma\/qCammel-70-x", + "Average \u2b06\ufe0f": 66.31, + "ARC": 68.34, + "HellaSwag": 87.87, + "MMLU": 70.18, + "TruthfulQA": 57.47, + "Winogrande": 84.29, + "GSM8K": 29.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "augtoma\/qCammel-70v1", + "Average \u2b06\ufe0f": 66.31, + "ARC": 68.34, + "HellaSwag": 87.87, + "MMLU": 70.18, + "TruthfulQA": 57.47, + "Winogrande": 84.29, + "GSM8K": 29.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "augtoma\/qCammel-70x", + "Average \u2b06\ufe0f": 66.31, + "ARC": 68.34, + "HellaSwag": 87.87, + "MMLU": 70.18, + "TruthfulQA": 57.47, + "Winogrande": 84.29, + "GSM8K": 29.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "augtoma\/qCammel-70", + "Average \u2b06\ufe0f": 66.31, + "ARC": 68.34, + "HellaSwag": 87.87, + "MMLU": 70.18, + "TruthfulQA": 57.47, + "Winogrande": 84.29, + "GSM8K": 29.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "augtoma\/qCammel70", + "Average \u2b06\ufe0f": 66.31, + "ARC": 68.34, + "HellaSwag": 87.87, + "MMLU": 70.18, + "TruthfulQA": 57.47, + "Winogrande": 84.29, + "GSM8K": 29.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cf1e917e42fd1e56ee1edef7ee1a98cbe705c18c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "garage-bAInd\/Platypus2-70B", + "Average \u2b06\ufe0f": 66.28, + "ARC": 70.65, + "HellaSwag": 87.15, + "MMLU": 70.08, + "TruthfulQA": 52.37, + "Winogrande": 84.37, + "GSM8K": 33.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "16b6583ad58313331f86be18e531ab03f1857695", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Doctor-Shotgun\/mythospice-limarp-70b", + "Average \u2b06\ufe0f": 66.27, + "ARC": 69.2, + "HellaSwag": 87.46, + "MMLU": 70.14, + "TruthfulQA": 55.86, + "Winogrande": 82.72, + "GSM8K": 32.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "agpl-3.0", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ff29fed2a33fc050fd20d0e25b5b23c4a101b074", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fzzhang\/Marcoroni-neural-chat-7B-v2_gsm8k_quantized_mergedfloat_s", + "Average \u2b06\ufe0f": 66.24, + "ARC": 64.08, + "HellaSwag": 84.12, + "MMLU": 61.14, + "TruthfulQA": 54.77, + "Winogrande": 76.95, + "GSM8K": 56.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d1a30161bd58ed7506ad0ad22fea7f186e065776", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xwin-LM\/Xwin-LM-70B-V0.1", + "Average \u2b06\ufe0f": 66.2, + "ARC": 70.22, + "HellaSwag": 87.25, + "MMLU": 69.77, + "TruthfulQA": 59.86, + "Winogrande": 82.87, + "GSM8K": 27.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 209.0, + "Available on the hub": true, + "Model sha": "d6c803a180e3d46c371f8d3cb3848b861596ccbc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Test-Raw-Solar-v1", + "Average \u2b06\ufe0f": 66.2, + "ARC": 63.23, + "HellaSwag": 84.82, + "MMLU": 65.52, + "TruthfulQA": 48.99, + "Winogrande": 84.06, + "GSM8K": 50.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5289b48902b793c5fbff4b596c6ffc8b657639a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "snorkelai\/Snorkel-Mistral-PairRM-DPO", + "Average \u2b06\ufe0f": 66.18, + "ARC": 65.96, + "HellaSwag": 85.63, + "MMLU": 60.85, + "TruthfulQA": 70.91, + "Winogrande": 77.58, + "GSM8K": 36.16, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": true, + "Model sha": "e4110a5689e146bc07296218f84ae09129168868", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Doctor-Shotgun\/mythospice-70b", + "Average \u2b06\ufe0f": 66.17, + "ARC": 69.28, + "HellaSwag": 87.53, + "MMLU": 70.1, + "TruthfulQA": 56.76, + "Winogrande": 83.27, + "GSM8K": 30.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "b00992c26604c9cd496bc41472a05e4c01cd2008", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beowolx\/MistralHermes-CodePro-7B-v1", + "Average \u2b06\ufe0f": 66.17, + "ARC": 62.46, + "HellaSwag": 82.68, + "MMLU": 63.44, + "TruthfulQA": 49.67, + "Winogrande": 77.9, + "GSM8K": 60.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "a74a9fa5797b75262187fffa173948f1c03e2af4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "quantumaikr\/llama-2-70b-fb16-orca-chat-10k", + "Average \u2b06\ufe0f": 66.16, + "ARC": 68.09, + "HellaSwag": 87.07, + "MMLU": 69.21, + "TruthfulQA": 61.56, + "Winogrande": 84.14, + "GSM8K": 26.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "697aaeb8eb9905c9b25bebb736d1905444c774a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Luminex-72B-v0.1", + "Average \u2b06\ufe0f": 66.15, + "ARC": 43.43, + "HellaSwag": 86.66, + "MMLU": 73.36, + "TruthfulQA": 41.85, + "Winogrande": 76.16, + "GSM8K": 75.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "73491b7bda948e0755f5a6cd655238e0ba73fad6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder45\/Mistral-7b-instruct-v0.2-summ-sft-dpo-e1", + "Average \u2b06\ufe0f": 66.15, + "ARC": 62.71, + "HellaSwag": 85.3, + "MMLU": 60.6, + "TruthfulQA": 70.76, + "Winogrande": 77.11, + "GSM8K": 40.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9ecd757a87134736f311e7b6e8c6c89b00343364", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/mistral-11b-slimorca", + "Average \u2b06\ufe0f": 66.12, + "ARC": 64.25, + "HellaSwag": 83.81, + "MMLU": 63.66, + "TruthfulQA": 54.66, + "Winogrande": 77.98, + "GSM8K": 52.39, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "1feb0fe36c9db1a4ea6cca32acae9ff07a12b9c5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "amazingvince\/where-llambo-7b", + "Average \u2b06\ufe0f": 66.08, + "ARC": 58.45, + "HellaSwag": 82.06, + "MMLU": 62.61, + "TruthfulQA": 49.61, + "Winogrande": 78.53, + "GSM8K": 65.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "554d9c7bab7ea6deabef0266aef17aa98f758543", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Gille\/StrangeMerges_13-7B-slerp", + "Average \u2b06\ufe0f": 66.06, + "ARC": 63.82, + "HellaSwag": 84.95, + "MMLU": 64.9, + "TruthfulQA": 48.62, + "Winogrande": 79.87, + "GSM8K": 54.21, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "26787521ec76c6fb81caffbba3d3fd75e9ce8e26", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "sonthenguyen\/NeuralHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 66.06, + "ARC": 67.58, + "HellaSwag": 85.69, + "MMLU": 63.43, + "TruthfulQA": 55.98, + "Winogrande": 77.98, + "GSM8K": 45.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d7b9a63eb3e086e16b669b7ff59d9b35d0908b03", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder45\/Mistral-7b-instruct-v0.2-summ-dpo-e3", + "Average \u2b06\ufe0f": 66.06, + "ARC": 62.63, + "HellaSwag": 85.31, + "MMLU": 60.76, + "TruthfulQA": 70.59, + "Winogrande": 77.35, + "GSM8K": 39.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b407df1ea1d6cc3c7cc183053fea8d728eb8365b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/llama-2-70b-Guanaco-QLoRA-fp16", + "Average \u2b06\ufe0f": 66.05, + "ARC": 68.26, + "HellaSwag": 88.32, + "MMLU": 70.23, + "TruthfulQA": 55.69, + "Winogrande": 83.98, + "GSM8K": 29.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 54.0, + "Available on the hub": true, + "Model sha": "54b0e39d5e9aee7b323f50b0a26db15295c3d5c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "seungduk\/KoSOLAR-10.7B-v0.1", + "Average \u2b06\ufe0f": 66.04, + "ARC": 62.03, + "HellaSwag": 84.54, + "MMLU": 65.56, + "TruthfulQA": 45.03, + "Winogrande": 83.58, + "GSM8K": 55.5, + "Type": "base merges and moerges", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a4ddde9b0d06f340ff9c29777b4bfd883700c6cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "upstage\/SOLAR-10.7B-v1.0", + "Average \u2b06\ufe0f": 66.04, + "ARC": 61.95, + "HellaSwag": 84.6, + "MMLU": 65.48, + "TruthfulQA": 45.04, + "Winogrande": 83.66, + "GSM8K": 55.5, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 194.0, + "Available on the hub": true, + "Model sha": "6e2783822f35c376ea96852fe479faa6a8bf09cb", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "TokenBender\/pic_7B_mistral_Full_v0.1", + "Average \u2b06\ufe0f": 66.0, + "ARC": 63.91, + "HellaSwag": 83.7, + "MMLU": 63.3, + "TruthfulQA": 54.51, + "Winogrande": 77.9, + "GSM8K": 52.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "64f7a800327466b76697c1f81d88b008274c8861", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "s1ghhh\/medllama-2-70b-qlora-1.1", + "Average \u2b06\ufe0f": 65.99, + "ARC": 69.03, + "HellaSwag": 87.17, + "MMLU": 71.04, + "TruthfulQA": 52.41, + "Winogrande": 84.21, + "GSM8K": 32.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d55e05e9d67418c639933c85a5b9d17c6f531a92", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder45\/Mistral-7b-instruct-v0.2-summ-dpo-e1", + "Average \u2b06\ufe0f": 65.98, + "ARC": 62.46, + "HellaSwag": 85.23, + "MMLU": 60.67, + "TruthfulQA": 70.56, + "Winogrande": 76.95, + "GSM8K": 40.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1b40e1f4f27fd0bc0430640df5fee7c0ca5f3668", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/longcat-10.7B", + "Average \u2b06\ufe0f": 65.98, + "ARC": 64.59, + "HellaSwag": 85.85, + "MMLU": 61.77, + "TruthfulQA": 61.42, + "Winogrande": 76.16, + "GSM8K": 46.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c79c121d00a7edce5decc7189c32a4411ab26311", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Qwen\/Qwen1.5-72B-Chat", + "Average \u2b06\ufe0f": 65.98, + "ARC": 68.26, + "HellaSwag": 86.47, + "MMLU": 77.46, + "TruthfulQA": 63.84, + "Winogrande": 78.93, + "GSM8K": 20.92, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bc11a298a0c6a5cd737064db62c6ad20ec6331be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/Bageluccine-7B-slerp", + "Average \u2b06\ufe0f": 65.97, + "ARC": 65.1, + "HellaSwag": 85.06, + "MMLU": 61.75, + "TruthfulQA": 60.33, + "Winogrande": 77.35, + "GSM8K": 46.25, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "87133b08a358596babe4760427bef748e1dd6d7f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "nisten\/shqiponja-59b-v1", + "Average \u2b06\ufe0f": 65.97, + "ARC": 70.05, + "HellaSwag": 84.06, + "MMLU": 75.54, + "TruthfulQA": 70.43, + "Winogrande": 80.27, + "GSM8K": 15.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 58.94, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a2dd71db32b23412fcea0ad8a36ee32e0641b9fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder67\/Mistral-7b-instruct-v0.2-summ-sft-dpo-e3", + "Average \u2b06\ufe0f": 65.97, + "ARC": 62.54, + "HellaSwag": 85.34, + "MMLU": 60.54, + "TruthfulQA": 70.69, + "Winogrande": 77.35, + "GSM8K": 39.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "18cb6af4611f6838a65f4517e03d82b1aa1d7a06", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder45\/Mistral-7b-instruct-v0.2-summ-dpo-e2", + "Average \u2b06\ufe0f": 65.97, + "ARC": 62.54, + "HellaSwag": 85.3, + "MMLU": 60.71, + "TruthfulQA": 70.54, + "Winogrande": 77.66, + "GSM8K": 39.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "22057329aaf003c9b32f7bc30b292d035972086c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/model_51", + "Average \u2b06\ufe0f": 65.96, + "ARC": 68.43, + "HellaSwag": 86.71, + "MMLU": 69.31, + "TruthfulQA": 57.18, + "Winogrande": 81.77, + "GSM8K": 32.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9542702011bf4d282f4b0f0bd79229f5822b6313", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dddsaty\/SOLAR_Merge_Adapter_DPO_Orca", + "Average \u2b06\ufe0f": 65.96, + "ARC": 63.91, + "HellaSwag": 84.58, + "MMLU": 63.18, + "TruthfulQA": 51.49, + "Winogrande": 82.0, + "GSM8K": 50.57, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0d1d423bab515ce5aee7e7029f86cfabfc26b4d9", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder67\/Mistral-7b-instruct-v0.2-summ-sft-dpo-e2", + "Average \u2b06\ufe0f": 65.95, + "ARC": 62.46, + "HellaSwag": 85.31, + "MMLU": 60.56, + "TruthfulQA": 70.77, + "Winogrande": 77.19, + "GSM8K": 39.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "803a3e7f24f61e8cd53ef4133ae22c3ce2568a78", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FusionNet_passthrough", + "Average \u2b06\ufe0f": 65.94, + "ARC": 69.45, + "HellaSwag": 87.72, + "MMLU": 65.28, + "TruthfulQA": 67.65, + "Winogrande": 81.29, + "GSM8K": 24.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 21.2, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fee459c6a29f7157394f62484eacf0417fee718a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "liminerity\/Blured-Ties-7B", + "Average \u2b06\ufe0f": 65.92, + "ARC": 63.99, + "HellaSwag": 83.56, + "MMLU": 63.19, + "TruthfulQA": 58.12, + "Winogrande": 79.72, + "GSM8K": 46.93, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "46faa4a8bad44e10b7840930bd4d7e3a281f1b90", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/14B-DPO-alpha", + "Average \u2b06\ufe0f": 65.91, + "ARC": 58.11, + "HellaSwag": 79.38, + "MMLU": 66.62, + "TruthfulQA": 54.15, + "Winogrande": 74.51, + "GSM8K": 62.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "wtfpl", + "#Params (B)": 14.0, + "Hub \u2764\ufe0f": 98.0, + "Available on the hub": true, + "Model sha": "34bc2dd73ae5f8738e5bcaaa5591427675f7801f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yunconglong\/Mixtral_7Bx2_MoE_13B_DPO", + "Average \u2b06\ufe0f": 65.89, + "ARC": 65.44, + "HellaSwag": 84.01, + "MMLU": 62.14, + "TruthfulQA": 61.76, + "Winogrande": 78.45, + "GSM8K": 43.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "88635724f75a6728bdc13165da4d5784f84c8b49", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Mixtral-4x7B-DPO-RPChat", + "Average \u2b06\ufe0f": 65.88, + "ARC": 64.59, + "HellaSwag": 85.36, + "MMLU": 63.57, + "TruthfulQA": 49.87, + "Winogrande": 78.77, + "GSM8K": 53.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "406aeb5ce848dfefbca65d69022ce1de36f9fde4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "RaduGabriel\/SirUkrainian2.0DPO", + "Average \u2b06\ufe0f": 65.87, + "ARC": 63.91, + "HellaSwag": 83.52, + "MMLU": 61.17, + "TruthfulQA": 65.08, + "Winogrande": 79.64, + "GSM8K": 41.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cc7f95d454989d6b7c96efb1ba7f89826bb56f3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen-14B", + "Average \u2b06\ufe0f": 65.86, + "ARC": 58.28, + "HellaSwag": 83.99, + "MMLU": 67.7, + "TruthfulQA": 49.43, + "Winogrande": 76.8, + "GSM8K": 58.98, + "Type": "pretrained", + "Architecture": "QWenLMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 194.0, + "Available on the hub": false, + "Model sha": "5eda9482e32a8ea7ed2dc47178f3b491eb207939", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-falcon-180b-v13-preview0", + "Average \u2b06\ufe0f": 65.85, + "ARC": 65.1, + "HellaSwag": 86.19, + "MMLU": 64.6, + "TruthfulQA": 54.97, + "Winogrande": 82.64, + "GSM8K": 41.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 180.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "7d7b93ffd67d1b0c39f3503050dbbcc951948120", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-7B-v2.03-128k", + "Average \u2b06\ufe0f": 65.83, + "ARC": 64.68, + "HellaSwag": 84.56, + "MMLU": 63.02, + "TruthfulQA": 51.16, + "Winogrande": 81.06, + "GSM8K": 50.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "22bb3c15b2770dfe91e239573b6c35b475a43cbe", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC99\/Mistral-7B-summ-lora-tuned-8h", + "Average \u2b06\ufe0f": 65.83, + "ARC": 63.05, + "HellaSwag": 85.17, + "MMLU": 60.39, + "TruthfulQA": 69.8, + "Winogrande": 77.35, + "GSM8K": 39.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "58d912c7d4dcbf788f4215ea927d0cfca8239368", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "macadeliccc\/laser-polyglot-4x7b", + "Average \u2b06\ufe0f": 65.79, + "ARC": 64.16, + "HellaSwag": 84.98, + "MMLU": 63.88, + "TruthfulQA": 55.47, + "Winogrande": 77.82, + "GSM8K": 48.45, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3402a470e7fca09eb5aa5f7dcf2876449a05a4f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SCE\/Mistral-7B-summ-lora-tuned", + "Average \u2b06\ufe0f": 65.79, + "ARC": 62.8, + "HellaSwag": 85.19, + "MMLU": 60.58, + "TruthfulQA": 70.18, + "Winogrande": 77.19, + "GSM8K": 38.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "95a4a8b60197ffe2e0cabca25a0eec2ea050a562", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "meta-math\/MetaMath-Mistral-7B", + "Average \u2b06\ufe0f": 65.78, + "ARC": 60.67, + "HellaSwag": 82.58, + "MMLU": 61.95, + "TruthfulQA": 44.89, + "Winogrande": 75.77, + "GSM8K": 68.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 67.0, + "Available on the hub": true, + "Model sha": "016a7bb03bfcd953860357e1a16d5b333b887d26", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kaitchup\/Maixtchup-4x7b", + "Average \u2b06\ufe0f": 65.77, + "ARC": 62.54, + "HellaSwag": 83.83, + "MMLU": 61.28, + "TruthfulQA": 56.13, + "Winogrande": 76.01, + "GSM8K": 54.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "56e8ed399a3198c7f02c30ac48361e690aad8d8f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "sonthenguyen\/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-reversed_corrupted", + "Average \u2b06\ufe0f": 65.76, + "ARC": 64.42, + "HellaSwag": 83.95, + "MMLU": 63.61, + "TruthfulQA": 51.65, + "Winogrande": 77.74, + "GSM8K": 53.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0b6fe472592fbb8f3086d85938bac591f8153e58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SCE\/Mistral-7B-math-ia3-pruned20", + "Average \u2b06\ufe0f": 65.76, + "ARC": 63.05, + "HellaSwag": 84.42, + "MMLU": 60.55, + "TruthfulQA": 67.74, + "Winogrande": 76.87, + "GSM8K": 41.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3a2ccd35edf2dad09efb591699de46cc3a31adc4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/model_420", + "Average \u2b06\ufe0f": 65.76, + "ARC": 70.14, + "HellaSwag": 87.73, + "MMLU": 70.35, + "TruthfulQA": 54.0, + "Winogrande": 83.74, + "GSM8K": 28.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "13c7b5f403c0f2af9bf7fce2d4a32deb9054c083", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FusionNet_passthrough_v0.1", + "Average \u2b06\ufe0f": 65.74, + "ARC": 69.45, + "HellaSwag": 87.79, + "MMLU": 65.2, + "TruthfulQA": 67.67, + "Winogrande": 81.53, + "GSM8K": 22.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 21.2, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0466e92dff5927724966ed3815432b4569d6d19e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tokyotech-llm\/Swallow-70b-instruct-hf", + "Average \u2b06\ufe0f": 65.74, + "ARC": 66.21, + "HellaSwag": 85.14, + "MMLU": 67.08, + "TruthfulQA": 48.0, + "Winogrande": 82.08, + "GSM8K": 45.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 69.16, + "Hub \u2764\ufe0f": 33.0, + "Available on the hub": true, + "Model sha": "feba815b847806df03f23a375f3d4d07fa251134", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishekchohan\/mistral-7B-forest-merge", + "Average \u2b06\ufe0f": 65.74, + "ARC": 63.65, + "HellaSwag": 84.41, + "MMLU": 59.98, + "TruthfulQA": 57.48, + "Winogrande": 77.74, + "GSM8K": 51.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dea087d73edf6019e72bfd5e98bc1fc93cb5136f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Mistral-7B-Instruct-v0.2-attention-sparsity-20", + "Average \u2b06\ufe0f": 65.74, + "ARC": 62.88, + "HellaSwag": 84.84, + "MMLU": 60.81, + "TruthfulQA": 68.26, + "Winogrande": 77.9, + "GSM8K": 39.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "17604249cd95a3454146c6de2729915fb6018e10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nextai-team\/Moe-4x7b-reason-code-qa", + "Average \u2b06\ufe0f": 65.73, + "ARC": 62.54, + "HellaSwag": 83.87, + "MMLU": 61.2, + "TruthfulQA": 56.12, + "Winogrande": 76.09, + "GSM8K": 54.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "6a88e94af88e8ab9386cd9f3d3694a68b2428952", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "Plaban81\/Moe-4x7b-math-reason-code", + "Average \u2b06\ufe0f": 65.73, + "ARC": 62.54, + "HellaSwag": 83.87, + "MMLU": 61.2, + "TruthfulQA": 56.12, + "Winogrande": 76.09, + "GSM8K": 54.59, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 24.15, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "630daafebf8b8fd6f3959b2e924b49598e8ee2d3", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "HenryJJ\/dolphin-2.6-mistral-7b-dpo-orca-v2", + "Average \u2b06\ufe0f": 65.72, + "ARC": 66.13, + "HellaSwag": 84.9, + "MMLU": 62.64, + "TruthfulQA": 62.39, + "Winogrande": 78.61, + "GSM8K": 39.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b1c44f6b0e9191a633837603c1053366868fc945", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "dfurman\/llama-2-70b-dolphin-peft", + "Average \u2b06\ufe0f": 65.72, + "ARC": 69.62, + "HellaSwag": 86.82, + "MMLU": 69.18, + "TruthfulQA": 57.43, + "Winogrande": 83.9, + "GSM8K": 27.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1190dee60b5854e80d340958dc3cc956bc56f68", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mistralai\/Mistral-7B-Instruct-v0.2", + "Average \u2b06\ufe0f": 65.71, + "ARC": 63.14, + "HellaSwag": 84.88, + "MMLU": 60.78, + "TruthfulQA": 68.26, + "Winogrande": 77.19, + "GSM8K": 40.03, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 979.0, + "Available on the hub": true, + "Model sha": "c72e5d1908b1e2929ec8fc4c8820e9706af1f80f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC44\/Mistral-7B-private-spnf", + "Average \u2b06\ufe0f": 65.7, + "ARC": 63.05, + "HellaSwag": 84.9, + "MMLU": 60.82, + "TruthfulQA": 68.34, + "Winogrande": 77.43, + "GSM8K": 39.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b517b17cdec49dfa1dbb1927cfcac97eec020a59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SCE\/Mistral-7B-math-ia3-pruned10", + "Average \u2b06\ufe0f": 65.7, + "ARC": 63.14, + "HellaSwag": 84.71, + "MMLU": 60.72, + "TruthfulQA": 68.16, + "Winogrande": 77.35, + "GSM8K": 40.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c49a49e078cee2c0ed152f32b80f1d992f806f67", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Bucharest-0.3", + "Average \u2b06\ufe0f": 65.69, + "ARC": 63.99, + "HellaSwag": 84.46, + "MMLU": 65.61, + "TruthfulQA": 46.19, + "Winogrande": 82.72, + "GSM8K": 51.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "11ba37297a32f302c27c653b58546eca9812dd6e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC44\/Mistral-7B-private-spef", + "Average \u2b06\ufe0f": 65.64, + "ARC": 63.23, + "HellaSwag": 84.93, + "MMLU": 60.8, + "TruthfulQA": 68.35, + "Winogrande": 77.27, + "GSM8K": 39.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bb29794e86ff6a39f77185f547c6bb335d2f5649", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "notbdq\/alooowso", + "Average \u2b06\ufe0f": 65.63, + "ARC": 62.97, + "HellaSwag": 84.87, + "MMLU": 60.78, + "TruthfulQA": 68.18, + "Winogrande": 77.43, + "GSM8K": 39.58, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "420f54afd10959bb1c86b485245349cd437960b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Mistral-7B-Instruct-v0.2-2x7B-MoE", + "Average \u2b06\ufe0f": 65.6, + "ARC": 62.97, + "HellaSwag": 84.88, + "MMLU": 60.74, + "TruthfulQA": 68.18, + "Winogrande": 77.43, + "GSM8K": 39.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "46a2d11c1025e6ddec0fe35093d39e2e16170ca2", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "v2ray\/LLaMA-2-Jannie-70B-QLoRA", + "Average \u2b06\ufe0f": 65.6, + "ARC": 68.94, + "HellaSwag": 86.9, + "MMLU": 69.37, + "TruthfulQA": 53.67, + "Winogrande": 82.95, + "GSM8K": 31.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e552ddca841a2b86e36bbe5f99840afedfdbcd14", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ENERGY-DRINK-LOVE\/SOLAR_merge2_dpo", + "Average \u2b06\ufe0f": 65.6, + "ARC": 64.42, + "HellaSwag": 82.73, + "MMLU": 64.57, + "TruthfulQA": 51.28, + "Winogrande": 81.77, + "GSM8K": 48.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "be7ad2d338fe4d3867b598776c24a4344a6c0d8a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "garage-bAInd\/Camel-Platypus2-70B", + "Average \u2b06\ufe0f": 65.59, + "ARC": 71.08, + "HellaSwag": 87.6, + "MMLU": 70.04, + "TruthfulQA": 58.09, + "Winogrande": 83.82, + "GSM8K": 22.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "b9f8de09ab860ee8ba570db7227c5444020ea056", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishekchohan\/mistral-7B-forest-merge", + "Average \u2b06\ufe0f": 65.58, + "ARC": 63.4, + "HellaSwag": 84.38, + "MMLU": 60.08, + "TruthfulQA": 57.57, + "Winogrande": 77.51, + "GSM8K": 50.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dea087d73edf6019e72bfd5e98bc1fc93cb5136f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JosephusCheung\/Yee-34B-200K-Chat", + "Average \u2b06\ufe0f": 65.56, + "ARC": 65.61, + "HellaSwag": 84.33, + "MMLU": 74.91, + "TruthfulQA": 53.88, + "Winogrande": 79.79, + "GSM8K": 34.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "94bc30449e41628f59dd965cb7d9a8eb53ce9a45", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Delcos\/Velara-11B-V2", + "Average \u2b06\ufe0f": 65.55, + "ARC": 63.82, + "HellaSwag": 85.85, + "MMLU": 63.62, + "TruthfulQA": 58.83, + "Winogrande": 77.82, + "GSM8K": 43.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 11.39, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "629ff26017b5adf0bc0c20d1c3f475491feb2b7a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wang7776\/Mistral-7B-Instruct-v0.2-sparsity-20-v0.1", + "Average \u2b06\ufe0f": 65.54, + "ARC": 62.29, + "HellaSwag": 84.9, + "MMLU": 60.63, + "TruthfulQA": 67.66, + "Winogrande": 77.66, + "GSM8K": 40.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7fcb7c43ea470c1c990472432e1a82fb0ae17646", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NurtureAI\/neural-chat-11b-v3-2", + "Average \u2b06\ufe0f": 65.52, + "ARC": 66.64, + "HellaSwag": 82.12, + "MMLU": 62.37, + "TruthfulQA": 60.22, + "Winogrande": 79.64, + "GSM8K": 42.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8821b441a4a07ec7c45e1c13bead93e99ad2f099", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "pankajmathur\/Lima_Unchained_70b", + "Average \u2b06\ufe0f": 65.51, + "ARC": 68.26, + "HellaSwag": 87.65, + "MMLU": 70.0, + "TruthfulQA": 48.76, + "Winogrande": 83.66, + "GSM8K": 34.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "7dadf059a03bdfec2eb4f4a47666545875c68e49", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/model_42_70b", + "Average \u2b06\ufe0f": 65.51, + "ARC": 68.26, + "HellaSwag": 87.65, + "MMLU": 70.0, + "TruthfulQA": 48.76, + "Winogrande": 83.66, + "GSM8K": 34.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ca3789cd6b683e97dcd6a5f0367f90a63d7a4e7b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "notadib\/Mistral-7B-Instruct-v0.2-attention-sparsity-30", + "Average \u2b06\ufe0f": 65.51, + "ARC": 62.97, + "HellaSwag": 84.71, + "MMLU": 60.49, + "TruthfulQA": 67.49, + "Winogrande": 77.98, + "GSM8K": 39.42, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "464534c288dbd5e6c495fac6273e5c91ea40cd5a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jordiclive\/Llama-2-70b-oasst-1-200", + "Average \u2b06\ufe0f": 65.5, + "ARC": 67.66, + "HellaSwag": 87.24, + "MMLU": 69.95, + "TruthfulQA": 51.28, + "Winogrande": 84.14, + "GSM8K": 32.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "153b209007e688d713cd670c9972f2827c597b45", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "RaduGabriel\/SirUkrainian2.0", + "Average \u2b06\ufe0f": 65.5, + "ARC": 63.65, + "HellaSwag": 83.26, + "MMLU": 61.22, + "TruthfulQA": 64.24, + "Winogrande": 79.64, + "GSM8K": 41.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "952c34cfb588ac4fe955b324ce263b91982f2ce9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/bagel-7b-v0.1", + "Average \u2b06\ufe0f": 65.49, + "ARC": 63.91, + "HellaSwag": 83.14, + "MMLU": 64.56, + "TruthfulQA": 52.65, + "Winogrande": 80.58, + "GSM8K": 48.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "10ac045905d13da0e2be8e647cfe3e5ac8444894", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/Synatra-10.7B-v0.4", + "Average \u2b06\ufe0f": 65.48, + "ARC": 64.93, + "HellaSwag": 82.47, + "MMLU": 62.5, + "TruthfulQA": 51.11, + "Winogrande": 81.85, + "GSM8K": 50.04, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "ae32ccb01cc971cfb36370876bf8981db243b2a3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "notadib\/Mistral-7B-Instruct-v0.2-attention-sparsity-10-v0.1", + "Average \u2b06\ufe0f": 65.48, + "ARC": 63.05, + "HellaSwag": 84.88, + "MMLU": 60.84, + "TruthfulQA": 68.11, + "Winogrande": 77.11, + "GSM8K": 38.89, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "228a9d4a23b0d9fa05c4f744c1163af49c0ba468", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/fiction.live-Kimiko-V2-70B-fp16", + "Average \u2b06\ufe0f": 65.48, + "ARC": 67.66, + "HellaSwag": 87.65, + "MMLU": 69.82, + "TruthfulQA": 49.28, + "Winogrande": 83.9, + "GSM8K": 34.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "6b0c2cb654133cad2d4920e7da2e3f6cb1c4f7fd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Mistral-7B-Instruct-v0.2-sparsity-10", + "Average \u2b06\ufe0f": 65.48, + "ARC": 62.88, + "HellaSwag": 84.85, + "MMLU": 60.87, + "TruthfulQA": 67.93, + "Winogrande": 77.51, + "GSM8K": 38.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9f83457d019d7b1471f09a1e967b15cd748f3e77", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishekchohan\/mistral-7B-forest-merge-v0.1", + "Average \u2b06\ufe0f": 65.47, + "ARC": 62.8, + "HellaSwag": 84.32, + "MMLU": 60.05, + "TruthfulQA": 58.53, + "Winogrande": 77.19, + "GSM8K": 49.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "89d2636a0077334335dce498f9b0324d1f6bb9f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "tiiuae\/falcon-180B", + "Average \u2b06\ufe0f": 65.46, + "ARC": 69.2, + "HellaSwag": 88.89, + "MMLU": 69.59, + "TruthfulQA": 45.16, + "Winogrande": 86.74, + "GSM8K": 33.21, + "Type": "pretrained", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 179.52, + "Hub \u2764\ufe0f": 1044.0, + "Available on the hub": true, + "Model sha": "71a1a70b629e9963f7b4601e82f3f9079d48011e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Metis-0.3", + "Average \u2b06\ufe0f": 65.44, + "ARC": 62.71, + "HellaSwag": 84.8, + "MMLU": 60.92, + "TruthfulQA": 67.56, + "Winogrande": 77.27, + "GSM8K": 39.35, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d5b89820d04640d217aa3c174fa1d1ad5553419a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jingyeom\/KoSoLAR-10.7B-v0.2_1.3_dedup_p", + "Average \u2b06\ufe0f": 65.43, + "ARC": 63.05, + "HellaSwag": 83.63, + "MMLU": 64.61, + "TruthfulQA": 52.69, + "Winogrande": 80.51, + "GSM8K": 48.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "df5c63764f04e2d5863724ce9723d6cad2451e42", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PistachioAlt\/Noromaid-Bagel-7B-Slerp", + "Average \u2b06\ufe0f": 65.42, + "ARC": 64.51, + "HellaSwag": 84.58, + "MMLU": 64.3, + "TruthfulQA": 52.88, + "Winogrande": 79.4, + "GSM8K": 46.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "07ec589199b9368c755c9d67f316336c5ef8b2c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EmbeddedLLM\/Mistral-7B-Merge-14-v0.3-ft-step-15936", + "Average \u2b06\ufe0f": 65.42, + "ARC": 62.54, + "HellaSwag": 82.14, + "MMLU": 62.58, + "TruthfulQA": 55.11, + "Winogrande": 75.77, + "GSM8K": 54.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2e53a73f2315a5ef111aa4a3a445a4a6682b031c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SCE\/Mistral-7B-summ-ia3-pruned10", + "Average \u2b06\ufe0f": 65.41, + "ARC": 63.05, + "HellaSwag": 84.88, + "MMLU": 59.67, + "TruthfulQA": 68.1, + "Winogrande": 77.51, + "GSM8K": 39.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c88d20e1763e41c1f1a77095b670221a568ca343", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "garage-bAInd\/Camel-Platypus2-70B", + "Average \u2b06\ufe0f": 65.39, + "ARC": 70.14, + "HellaSwag": 87.71, + "MMLU": 69.83, + "TruthfulQA": 57.77, + "Winogrande": 82.95, + "GSM8K": 23.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "6f958a1063fe1e6075f6e379fae621ff5a1d98c6", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenLemur\/lemur-70b-chat-v1", + "Average \u2b06\ufe0f": 65.38, + "ARC": 66.98, + "HellaSwag": 85.73, + "MMLU": 65.99, + "TruthfulQA": 56.58, + "Winogrande": 81.69, + "GSM8K": 35.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 68.0, + "Available on the hub": true, + "Model sha": "33da87ba6d90662c6a00535bd628e5b39b3afd3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/Mistroll-7B-v0.2-16bit", + "Average \u2b06\ufe0f": 65.36, + "ARC": 62.2, + "HellaSwag": 84.85, + "MMLU": 60.37, + "TruthfulQA": 67.65, + "Winogrande": 76.87, + "GSM8K": 40.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ef54ac95b46b9a9dd1fbd2164ed97a5d8657072", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "robinsmits\/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit", + "Average \u2b06\ufe0f": 65.34, + "ARC": 62.12, + "HellaSwag": 84.55, + "MMLU": 60.66, + "TruthfulQA": 67.29, + "Winogrande": 77.11, + "GSM8K": 40.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.86, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "4d104982c9759ae57fa482280c50b1950e51fd48", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-7B-v2.03", + "Average \u2b06\ufe0f": 65.34, + "ARC": 63.82, + "HellaSwag": 84.73, + "MMLU": 63.05, + "TruthfulQA": 48.53, + "Winogrande": 80.9, + "GSM8K": 51.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "73641ebe6ba450a83f6e80ed919fba48cc5f2837", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "01-ai\/Yi-34B-Chat", + "Average \u2b06\ufe0f": 65.32, + "ARC": 65.44, + "HellaSwag": 84.16, + "MMLU": 74.9, + "TruthfulQA": 55.37, + "Winogrande": 80.11, + "GSM8K": 31.92, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 274.0, + "Available on the hub": true, + "Model sha": "a99ec35331cbfc9da596af7d4538fe2efecff03c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/Mistroll-7B-v0.3-16bit", + "Average \u2b06\ufe0f": 65.3, + "ARC": 62.12, + "HellaSwag": 84.83, + "MMLU": 60.45, + "TruthfulQA": 67.65, + "Winogrande": 76.87, + "GSM8K": 39.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b0daf2beea9085c2388b7589572ac7fb6e05f0ef", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "liuxiang886\/llama2-70B-qlora-gpt4", + "Average \u2b06\ufe0f": 65.29, + "ARC": 70.31, + "HellaSwag": 86.39, + "MMLU": 69.29, + "TruthfulQA": 54.02, + "Winogrande": 82.87, + "GSM8K": 28.89, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "08115ee077953e9c01c6a40f5086def3ecf9f5f0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FPHam\/Writing_Partner_Mistral_7B", + "Average \u2b06\ufe0f": 65.29, + "ARC": 64.59, + "HellaSwag": 84.59, + "MMLU": 62.55, + "TruthfulQA": 48.55, + "Winogrande": 76.87, + "GSM8K": 54.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "d71b744e4d7432301d891409a05710bf2e4fa4c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "llm-agents\/tora-70b-v1.0", + "Average \u2b06\ufe0f": 65.28, + "ARC": 67.58, + "HellaSwag": 85.82, + "MMLU": 69.13, + "TruthfulQA": 51.76, + "Winogrande": 82.16, + "GSM8K": 35.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "e95fd7daf017e7c414ec07ebef4ddf013c16f9a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/neural-chat-7b-v3-3-wizardmath-dare-me", + "Average \u2b06\ufe0f": 65.28, + "ARC": 59.64, + "HellaSwag": 82.63, + "MMLU": 58.13, + "TruthfulQA": 62.6, + "Winogrande": 71.67, + "GSM8K": 57.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1d86275bacb3229e3de6069a98123c6252c7b471", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wang7776\/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1", + "Average \u2b06\ufe0f": 65.28, + "ARC": 63.31, + "HellaSwag": 84.37, + "MMLU": 60.24, + "TruthfulQA": 66.28, + "Winogrande": 78.06, + "GSM8K": 39.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "39566bcb48deecc1a3b830c5de9e70527d394c4f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "orangetin\/OpenHermes-Mixtral-8x7B", + "Average \u2b06\ufe0f": 65.27, + "ARC": 63.91, + "HellaSwag": 84.14, + "MMLU": 64.29, + "TruthfulQA": 59.53, + "Winogrande": 74.03, + "GSM8K": 45.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "a55b010d3918ef61267d34e9ab47d9f554e3b11c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Fredithefish\/MadMix-v0.1", + "Average \u2b06\ufe0f": 65.26, + "ARC": 64.93, + "HellaSwag": 84.37, + "MMLU": 64.37, + "TruthfulQA": 51.05, + "Winogrande": 77.19, + "GSM8K": 49.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "71773ca4ca1fd76a00bd695a52b96b43b8fd78ff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AIGeekLabs\/radiantloom-mixtral-8x7b-fusion", + "Average \u2b06\ufe0f": 65.24, + "ARC": 63.48, + "HellaSwag": 83.65, + "MMLU": 60.03, + "TruthfulQA": 54.76, + "Winogrande": 76.09, + "GSM8K": 53.45, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "93b3807b8fa38b9c95267117d25055bbd3eab29b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "simonveitner\/MathHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 65.24, + "ARC": 64.76, + "HellaSwag": 84.19, + "MMLU": 63.59, + "TruthfulQA": 51.95, + "Winogrande": 77.66, + "GSM8K": 49.28, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2a6ee2674304f91d1dcc772695deded76d4c32bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/Mistroll-7B-v0.1-16bit", + "Average \u2b06\ufe0f": 65.23, + "ARC": 62.2, + "HellaSwag": 84.81, + "MMLU": 60.34, + "TruthfulQA": 67.67, + "Winogrande": 76.8, + "GSM8K": 39.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "db9f03ed4f6d5e8c8ccdcb7ad1e66d527dfcf5fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/Wistral-7B-Instruct-v0.3", + "Average \u2b06\ufe0f": 65.23, + "ARC": 62.2, + "HellaSwag": 84.81, + "MMLU": 60.34, + "TruthfulQA": 67.67, + "Winogrande": 76.8, + "GSM8K": 39.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "541d36b0dcaf8e0e9c791c0b54e5358fafd1aebb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/Lucie-7b-3e-5", + "Average \u2b06\ufe0f": 65.23, + "ARC": 62.2, + "HellaSwag": 84.81, + "MMLU": 60.34, + "TruthfulQA": 67.67, + "Winogrande": 76.8, + "GSM8K": 39.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "38901d0e7baa164636a8ab30a0b54eafcecc7b93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/Wistral-7B-Instruct-v0.4", + "Average \u2b06\ufe0f": 65.23, + "ARC": 62.2, + "HellaSwag": 84.81, + "MMLU": 60.34, + "TruthfulQA": 67.67, + "Winogrande": 76.8, + "GSM8K": 39.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6f75a5559ef6008886b9abbcf5df998db43edc00", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/Lucie-7b", + "Average \u2b06\ufe0f": 65.23, + "ARC": 62.2, + "HellaSwag": 84.81, + "MMLU": 60.34, + "TruthfulQA": 67.67, + "Winogrande": 76.8, + "GSM8K": 39.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ffbb35e5ad00d0c51a626d122ce07a5fbf7759ad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "quantumaikr\/llama-2-70b-fb16-korean", + "Average \u2b06\ufe0f": 65.23, + "ARC": 67.15, + "HellaSwag": 86.78, + "MMLU": 69.29, + "TruthfulQA": 56.5, + "Winogrande": 82.64, + "GSM8K": 29.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 36.0, + "Available on the hub": false, + "Model sha": "fd57855006c15c4121feccab1cbeee8107de5b5a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/Wistral-7B-Instruct-v0.3", + "Average \u2b06\ufe0f": 65.23, + "ARC": 62.2, + "HellaSwag": 84.77, + "MMLU": 60.32, + "TruthfulQA": 67.62, + "Winogrande": 76.8, + "GSM8K": 39.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "68c0bd31c15387f45a956281d91eb12885f0a160", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SCE\/Mistral-7B-summ-ia3-pruned20", + "Average \u2b06\ufe0f": 65.23, + "ARC": 62.88, + "HellaSwag": 84.77, + "MMLU": 60.09, + "TruthfulQA": 67.84, + "Winogrande": 76.95, + "GSM8K": 38.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "14b2da3b2905056d0837730e0dccd82101bd8d27", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kwchoi\/DPO_mistral_7b_ultra_0129_1k", + "Average \u2b06\ufe0f": 65.2, + "ARC": 64.16, + "HellaSwag": 85.54, + "MMLU": 61.04, + "TruthfulQA": 68.34, + "Winogrande": 77.19, + "GSM8K": 34.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c682cc66f92fc213ea9025557d0078503f3e461b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/MiquMaid-v2-70B", + "Average \u2b06\ufe0f": 65.19, + "ARC": 70.48, + "HellaSwag": 87.49, + "MMLU": 75.18, + "TruthfulQA": 57.62, + "Winogrande": 84.77, + "GSM8K": 15.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "bd19912eb652fd76165938179abd3b54cacb85fa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DreadPoor\/ToppyEvil-7B-slerp", + "Average \u2b06\ufe0f": 65.16, + "ARC": 63.65, + "HellaSwag": 84.29, + "MMLU": 63.6, + "TruthfulQA": 46.06, + "Winogrande": 77.58, + "GSM8K": 55.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6c032a15a05cc8c639de2c36c761b35f1955a3af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "cloudyu\/Mixtral_7Bx2_MoE_13B", + "Average \u2b06\ufe0f": 65.14, + "ARC": 64.85, + "HellaSwag": 83.92, + "MMLU": 62.27, + "TruthfulQA": 57.55, + "Winogrande": 77.9, + "GSM8K": 44.35, + "Type": "base merges and moerges", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5ea651448fbeb313665d66187416233b865db7f1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "amazingvince\/openhermes-7b-dpo", + "Average \u2b06\ufe0f": 65.14, + "ARC": 65.78, + "HellaSwag": 84.94, + "MMLU": 63.66, + "TruthfulQA": 57.01, + "Winogrande": 77.51, + "GSM8K": 41.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c191ac2d33de8bb5f1454e95c50fab40dc52974e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "KnutJaegersberg\/internlm-20b-llama", + "Average \u2b06\ufe0f": 65.09, + "ARC": 61.35, + "HellaSwag": 82.08, + "MMLU": 61.59, + "TruthfulQA": 57.71, + "Winogrande": 76.72, + "GSM8K": 51.1, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0c4e862aeb22eaf2854ea06b6f8b1e3824591e3c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BlueNipples\/SnowLotus-v2-10.7B", + "Average \u2b06\ufe0f": 65.09, + "ARC": 64.76, + "HellaSwag": 85.28, + "MMLU": 64.1, + "TruthfulQA": 45.54, + "Winogrande": 82.08, + "GSM8K": 48.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "5027a7a14e7f224e2fbdd0268a3a4ae75439229f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Epiculous\/Fett-uccine-7B", + "Average \u2b06\ufe0f": 65.08, + "ARC": 63.23, + "HellaSwag": 86.09, + "MMLU": 60.03, + "TruthfulQA": 69.47, + "Winogrande": 75.06, + "GSM8K": 36.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "agpl-3.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "823e103126393a0ba4a9cc6d082ab4cda54413ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Sina-Loki-7b-Merge", + "Average \u2b06\ufe0f": 65.03, + "ARC": 59.13, + "HellaSwag": 81.96, + "MMLU": 64.71, + "TruthfulQA": 53.84, + "Winogrande": 78.14, + "GSM8K": 52.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5977c691a13280715c15559f2d90cb3142f74881", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Tiger-7b-v0.1", + "Average \u2b06\ufe0f": 65.02, + "ARC": 59.98, + "HellaSwag": 83.21, + "MMLU": 61.42, + "TruthfulQA": 61.03, + "Winogrande": 77.66, + "GSM8K": 46.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "365162149ed8e18c1cbf2d9728707f4b03ae4a62", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/dolphin-2.2.1-mistral-7b", + "Average \u2b06\ufe0f": 65.01, + "ARC": 63.23, + "HellaSwag": 83.8, + "MMLU": 63.16, + "TruthfulQA": 53.14, + "Winogrande": 78.61, + "GSM8K": 48.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 165.0, + "Available on the hub": true, + "Model sha": "2022924c0bb13588308d429e0b7f51568c07629c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/OpenOrca-Zephyr-7B", + "Average \u2b06\ufe0f": 64.97, + "ARC": 64.08, + "HellaSwag": 83.82, + "MMLU": 62.46, + "TruthfulQA": 54.31, + "Winogrande": 78.93, + "GSM8K": 46.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "2a2c7d287a46243cccf3ff6628375d0d190394ac", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-70b-gpt4-1.4.1", + "Average \u2b06\ufe0f": 64.97, + "ARC": 70.39, + "HellaSwag": 87.82, + "MMLU": 70.31, + "TruthfulQA": 55.2, + "Winogrande": 83.58, + "GSM8K": 22.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 48.0, + "Available on the hub": true, + "Model sha": "ea98153fa721ed7110c77e73388e3b6f3996f2bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Radu1999\/Mistral-Instruct-Ukrainian-slerp", + "Average \u2b06\ufe0f": 64.96, + "ARC": 62.03, + "HellaSwag": 84.35, + "MMLU": 61.35, + "TruthfulQA": 63.49, + "Winogrande": 76.87, + "GSM8K": 41.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "166cd3537a1eab8f189e232243d675d431dc71f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Hermes-Instruct-7B-100K", + "Average \u2b06\ufe0f": 64.96, + "ARC": 61.52, + "HellaSwag": 82.84, + "MMLU": 60.95, + "TruthfulQA": 63.62, + "Winogrande": 76.87, + "GSM8K": 43.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0dd712293d5b914d53f1e1f35922cd023ba98047", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Mistral-7B-Instruct-v0.2-Neural-Story", + "Average \u2b06\ufe0f": 64.96, + "ARC": 64.08, + "HellaSwag": 83.97, + "MMLU": 60.67, + "TruthfulQA": 66.89, + "Winogrande": 75.85, + "GSM8K": 38.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "8f3198a3e235d7c1ae56befbe8fb14a974acdf69", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/dolphin-2.2.1-mistral-7b", + "Average \u2b06\ufe0f": 64.93, + "ARC": 63.31, + "HellaSwag": 83.76, + "MMLU": 63.17, + "TruthfulQA": 53.11, + "Winogrande": 78.14, + "GSM8K": 48.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "001b48e9aebffb395c698af47b6b48364cc3cbe8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bn22\/OpenHermes-2.5-Mistral-7B-MISALIGNED", + "Average \u2b06\ufe0f": 64.92, + "ARC": 65.36, + "HellaSwag": 84.67, + "MMLU": 63.74, + "TruthfulQA": 52.85, + "Winogrande": 77.66, + "GSM8K": 45.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d366f84cef3a084c6c3dc87b304f0937080c2a6d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/dolphin-2.6-mistral-7b", + "Average \u2b06\ufe0f": 64.92, + "ARC": 63.05, + "HellaSwag": 84.05, + "MMLU": 63.2, + "TruthfulQA": 55.67, + "Winogrande": 77.66, + "GSM8K": 45.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 94.0, + "Available on the hub": true, + "Model sha": "61981ccfb93bad331c8d3da97aafeb13596afc9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Nous-Puffin-70B", + "Average \u2b06\ufe0f": 64.91, + "ARC": 67.41, + "HellaSwag": 87.37, + "MMLU": 69.77, + "TruthfulQA": 46.77, + "Winogrande": 83.9, + "GSM8K": 34.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": [ + "mit" + ], + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "129e0af93d04b1b9cc85ea48bbb300f1ccb44210", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/dolphin-2.6-mistral-7b", + "Average \u2b06\ufe0f": 64.91, + "ARC": 62.88, + "HellaSwag": 84.06, + "MMLU": 63.19, + "TruthfulQA": 55.65, + "Winogrande": 77.58, + "GSM8K": 46.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 94.0, + "Available on the hub": true, + "Model sha": "61981ccfb93bad331c8d3da97aafeb13596afc9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Panda-7B-v0.1", + "Average \u2b06\ufe0f": 64.89, + "ARC": 62.97, + "HellaSwag": 83.76, + "MMLU": 60.73, + "TruthfulQA": 66.97, + "Winogrande": 76.24, + "GSM8K": 38.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "7d8702ad9d9da7871492ce8843fdb7308a42b3f4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jarradh\/llama2_70b_chat_uncensored", + "Average \u2b06\ufe0f": 64.88, + "ARC": 68.43, + "HellaSwag": 86.77, + "MMLU": 68.76, + "TruthfulQA": 52.5, + "Winogrande": 82.56, + "GSM8K": 30.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 56.0, + "Available on the hub": true, + "Model sha": "34b23982a9a996adc8f45c4c2eac7245c4e251b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TeeZee\/Kyllene-v1.0", + "Average \u2b06\ufe0f": 64.86, + "ARC": 64.85, + "HellaSwag": 84.51, + "MMLU": 73.33, + "TruthfulQA": 57.89, + "Winogrande": 78.22, + "GSM8K": 30.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 56.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "27db149dad28401a81a7207f8cf3f8ff5aad9f4c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/bagel-7b-v0.4", + "Average \u2b06\ufe0f": 64.82, + "ARC": 63.57, + "HellaSwag": 82.67, + "MMLU": 62.25, + "TruthfulQA": 54.2, + "Winogrande": 78.93, + "GSM8K": 47.31, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "365a4a895d052d2eb4263be0c4e2ed75a08513b4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "INSAIT-Institute\/BgGPT-7B-Instruct-v0.1", + "Average \u2b06\ufe0f": 64.82, + "ARC": 60.24, + "HellaSwag": 81.6, + "MMLU": 59.66, + "TruthfulQA": 53.68, + "Winogrande": 77.03, + "GSM8K": 56.71, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.29, + "Hub \u2764\ufe0f": 32.0, + "Available on the hub": true, + "Model sha": "9c96e8cefc1079ef566cc46fc9b60b52dc36f583", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Hermes-Instruct-7B-217K", + "Average \u2b06\ufe0f": 64.81, + "ARC": 61.01, + "HellaSwag": 82.64, + "MMLU": 61.23, + "TruthfulQA": 61.81, + "Winogrande": 77.66, + "GSM8K": 44.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "25d52e51192738ddfc875e70dbaf1602ad4afd8f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/DarkSapling-7B-v1.1", + "Average \u2b06\ufe0f": 64.8, + "ARC": 63.48, + "HellaSwag": 85.09, + "MMLU": 64.47, + "TruthfulQA": 52.04, + "Winogrande": 78.53, + "GSM8K": 45.19, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0064fc89ee6ce11c01d9061845e1d6498a91ab1a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "yanolja\/KoSOLAR-10.7B-v0.3", + "Average \u2b06\ufe0f": 64.76, + "ARC": 62.8, + "HellaSwag": 83.73, + "MMLU": 64.51, + "TruthfulQA": 44.57, + "Winogrande": 82.48, + "GSM8K": 50.49, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4b30efea87be24e22eac00fd45f72388e981576e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Tanuki-7B-v0.1", + "Average \u2b06\ufe0f": 64.74, + "ARC": 62.8, + "HellaSwag": 83.14, + "MMLU": 60.54, + "TruthfulQA": 66.33, + "Winogrande": 75.85, + "GSM8K": 39.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "699ab2535487aee7cfd8d55ad928805b310c4b17", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-mixtral-7bx8-v17.1-32k", + "Average \u2b06\ufe0f": 64.73, + "ARC": 65.53, + "HellaSwag": 75.95, + "MMLU": 70.02, + "TruthfulQA": 42.14, + "Winogrande": 75.69, + "GSM8K": 59.06, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f19e2f221c1ec96f6f0d13566763fc774d78c1a1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "indischepartij\/OpenMia-Indo-Mistral-7b-v4", + "Average \u2b06\ufe0f": 64.73, + "ARC": 64.16, + "HellaSwag": 82.84, + "MMLU": 61.08, + "TruthfulQA": 53.36, + "Winogrande": 79.08, + "GSM8K": 47.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4cded6e49d74571408be7acf13a8e0ad7f5bf79e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "oh-yeontaek\/llama-2-70B-LoRA-assemble-v2", + "Average \u2b06\ufe0f": 64.73, + "ARC": 71.84, + "HellaSwag": 86.89, + "MMLU": 69.37, + "TruthfulQA": 64.79, + "Winogrande": 81.22, + "GSM8K": 14.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "7feeb5b665ab1ecdfd9cc4fe45fadb86b7b91b5b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/HelpSteer-filtered-Solar-Instruct", + "Average \u2b06\ufe0f": 64.73, + "ARC": 63.14, + "HellaSwag": 83.05, + "MMLU": 64.32, + "TruthfulQA": 46.23, + "Winogrande": 80.58, + "GSM8K": 51.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "52b80cc07c0c2a2bb54561a9c3d556231ca7344d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/WizardLM-Math-70B-TIES-v0.1", + "Average \u2b06\ufe0f": 64.72, + "ARC": 68.52, + "HellaSwag": 86.87, + "MMLU": 69.24, + "TruthfulQA": 53.61, + "Winogrande": 82.72, + "GSM8K": 27.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "agpl-3.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1e5a2039c5d48dc1786f18c72e538af06e76a8cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SC99\/Mistral-7B-summ-ia3-tuned-8h", + "Average \u2b06\ufe0f": 64.71, + "ARC": 61.18, + "HellaSwag": 85.14, + "MMLU": 59.89, + "TruthfulQA": 68.31, + "Winogrande": 77.11, + "GSM8K": 36.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "615cde1fef79bc9caa3c475d35e5a076cc629ad0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-mistral-7b-dare-0.85", + "Average \u2b06\ufe0f": 64.69, + "ARC": 63.57, + "HellaSwag": 84.82, + "MMLU": 64.29, + "TruthfulQA": 50.66, + "Winogrande": 79.24, + "GSM8K": 45.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b19e60f64b3be7f41658958658658bc12038c68f", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Steelskull\/Etheria-55b-v0.1", + "Average \u2b06\ufe0f": 64.69, + "ARC": 65.1, + "HellaSwag": 81.93, + "MMLU": 73.66, + "TruthfulQA": 56.16, + "Winogrande": 76.09, + "GSM8K": 35.18, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 55.59, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "ebcddf3a31409c9809ab3876ea390f4fb7f313b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pinkyponky\/Mistral-7b-instruct-v0.2-summ-sft-e2", + "Average \u2b06\ufe0f": 64.67, + "ARC": 61.43, + "HellaSwag": 83.64, + "MMLU": 61.03, + "TruthfulQA": 64.92, + "Winogrande": 76.72, + "GSM8K": 40.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "01a73ccd10a275738304c695d0728a29e8586f47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Euryale-L2-70B", + "Average \u2b06\ufe0f": 64.66, + "ARC": 68.94, + "HellaSwag": 87.07, + "MMLU": 68.84, + "TruthfulQA": 54.49, + "Winogrande": 82.08, + "GSM8K": 26.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "6589310a57ce5d9d6877f353f3d00cda8fa9101c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "smelborp\/MixtralOrochi8x7B", + "Average \u2b06\ufe0f": 64.62, + "ARC": 70.31, + "HellaSwag": 86.1, + "MMLU": 70.13, + "TruthfulQA": 63.99, + "Winogrande": 79.87, + "GSM8K": 17.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "e88684d163fd3e789c40261c5b68244bb72bd706", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Chop-7b", + "Average \u2b06\ufe0f": 64.59, + "ARC": 63.74, + "HellaSwag": 83.04, + "MMLU": 62.04, + "TruthfulQA": 62.19, + "Winogrande": 76.8, + "GSM8K": 39.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "295b0a6dbe8f7cbbcebad706a4a0ee8681f2a0a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Gecko-7B-v0.1", + "Average \u2b06\ufe0f": 64.58, + "ARC": 61.35, + "HellaSwag": 83.36, + "MMLU": 61.05, + "TruthfulQA": 62.6, + "Winogrande": 77.58, + "GSM8K": 41.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "404e501cb4d091e768e12861d50e37ac99d8a8fe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pinkyponky\/Mistral-7b-instruct-v0.2-summ-sft-e1", + "Average \u2b06\ufe0f": 64.58, + "ARC": 60.84, + "HellaSwag": 83.37, + "MMLU": 60.86, + "TruthfulQA": 64.98, + "Winogrande": 77.03, + "GSM8K": 40.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cb20f22f421052e1ca8ea8bd9974fade5ccdfa9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/PiVoT-0.1-early", + "Average \u2b06\ufe0f": 64.58, + "ARC": 62.46, + "HellaSwag": 82.97, + "MMLU": 61.02, + "TruthfulQA": 62.89, + "Winogrande": 73.72, + "GSM8K": 44.43, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "6eeae58a1a292a1d7f989952a07aead6d5da3c69", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "proto-llm\/uniwiz-7B-v0.2", + "Average \u2b06\ufe0f": 64.56, + "ARC": 63.31, + "HellaSwag": 85.07, + "MMLU": 63.7, + "TruthfulQA": 59.91, + "Winogrande": 77.82, + "GSM8K": 37.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "799809bc85c6fb17a636e6d1f67bf959730baefd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-70b-gpt4-m2.0", + "Average \u2b06\ufe0f": 64.56, + "ARC": 70.05, + "HellaSwag": 87.83, + "MMLU": 70.67, + "TruthfulQA": 49.79, + "Winogrande": 83.58, + "GSM8K": 25.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "1cccd0b60a988bf6ddc4e2688895837845afa076", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-mixtral-8x7b-v15.4", + "Average \u2b06\ufe0f": 64.54, + "ARC": 66.47, + "HellaSwag": 71.81, + "MMLU": 70.01, + "TruthfulQA": 55.46, + "Winogrande": 71.67, + "GSM8K": 51.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d7ab397a06644e7b2a2ebd14c25e332dc0d29997", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "pinkyponky\/Mistral-7b-instruct-v0.2-summ-sft-e3", + "Average \u2b06\ufe0f": 64.54, + "ARC": 61.18, + "HellaSwag": 83.72, + "MMLU": 60.93, + "TruthfulQA": 64.94, + "Winogrande": 76.95, + "GSM8K": 39.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5b09e3dd2bf8bcf08b9b3dd0d69e4cc67d782fd3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "genaicore3434\/Mistral-7b-instruct-v0.2-summ-sft-bf16-e2", + "Average \u2b06\ufe0f": 64.52, + "ARC": 60.67, + "HellaSwag": 83.55, + "MMLU": 60.81, + "TruthfulQA": 65.1, + "Winogrande": 77.58, + "GSM8K": 39.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b1fc87ef5eefc5cafe0654bd2f68d0f753c87a53", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Radiantloom\/radiantloom-mixtral-8x7b-fusion-dpo", + "Average \u2b06\ufe0f": 64.52, + "ARC": 63.48, + "HellaSwag": 82.49, + "MMLU": 59.68, + "TruthfulQA": 55.2, + "Winogrande": 76.09, + "GSM8K": 50.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "08812f2f90df6c78b3a653208c25db0eee97714f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Llama-2-70B-fp16", + "Average \u2b06\ufe0f": 64.52, + "ARC": 67.32, + "HellaSwag": 87.33, + "MMLU": 69.83, + "TruthfulQA": 44.92, + "Winogrande": 83.74, + "GSM8K": 33.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 45.0, + "Available on the hub": true, + "Model sha": "b25061ef1b440e970d15d4ac99bc42937cd442a2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AA051610\/Q", + "Average \u2b06\ufe0f": 64.52, + "ARC": 66.98, + "HellaSwag": 85.67, + "MMLU": 75.13, + "TruthfulQA": 59.36, + "Winogrande": 80.03, + "GSM8K": 19.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5cae52b499bc74ee419426fccd935462c2635175", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder45\/Mistral-7b-instruct-v0.2-summ-sft-bf16-e3", + "Average \u2b06\ufe0f": 64.51, + "ARC": 60.32, + "HellaSwag": 83.68, + "MMLU": 60.82, + "TruthfulQA": 65.22, + "Winogrande": 77.82, + "GSM8K": 39.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "718e614895ea1fc1445dd0727751821d2ac14e6e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FinancialSupport\/saiga-7b", + "Average \u2b06\ufe0f": 64.51, + "ARC": 63.14, + "HellaSwag": 83.14, + "MMLU": 61.66, + "TruthfulQA": 54.99, + "Winogrande": 79.01, + "GSM8K": 45.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "08daa40fbe05366466f96c92deb775d1b9b04669", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Steelskull\/VerA-Etheria-55b", + "Average \u2b06\ufe0f": 64.51, + "ARC": 64.25, + "HellaSwag": 81.46, + "MMLU": 73.51, + "TruthfulQA": 52.1, + "Winogrande": 75.93, + "GSM8K": 39.8, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 55.59, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "dc4ed42fc886c3d912fc0aa3b19cf5c92bfb55d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "upstage\/llama-65b-instruct", + "Average \u2b06\ufe0f": 64.51, + "ARC": 68.86, + "HellaSwag": 86.43, + "MMLU": 64.77, + "TruthfulQA": 59.7, + "Winogrande": 81.06, + "GSM8K": 26.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": false, + "Model sha": "b95668861dfb7b0abca44ccdbef2db49b2dd8917", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/openchat-3.5-1210-32k", + "Average \u2b06\ufe0f": 64.49, + "ARC": 64.68, + "HellaSwag": 84.06, + "MMLU": 61.59, + "TruthfulQA": 49.31, + "Winogrande": 79.16, + "GSM8K": 48.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "48fde7a1a1d644f603a828839047ff695165b387", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "VAGOsolutions\/SauerkrautLM-7b-HerO", + "Average \u2b06\ufe0f": 64.49, + "ARC": 63.23, + "HellaSwag": 83.52, + "MMLU": 63.3, + "TruthfulQA": 49.22, + "Winogrande": 78.37, + "GSM8K": 49.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "0aeb810af28e2910a92b929c21b931a5c06073de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/openchat-3.5-1210-32k-8x7b-MoE", + "Average \u2b06\ufe0f": 64.48, + "ARC": 64.59, + "HellaSwag": 84.07, + "MMLU": 61.6, + "TruthfulQA": 49.32, + "Winogrande": 79.16, + "GSM8K": 48.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c24bf500da78e987197055e96dda0dcc496de9ed", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-llama-65b-v8-bf16", + "Average \u2b06\ufe0f": 64.47, + "ARC": 62.8, + "HellaSwag": 83.6, + "MMLU": 62.01, + "TruthfulQA": 55.09, + "Winogrande": 79.95, + "GSM8K": 43.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": false, + "Model sha": "445b77821fac8e6cfb77d0399fb827400b5bb71e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenAssistant\/llama2-70b-oasst-sft-v10", + "Average \u2b06\ufe0f": 64.47, + "ARC": 67.06, + "HellaSwag": 86.38, + "MMLU": 67.7, + "TruthfulQA": 56.45, + "Winogrande": 82.0, + "GSM8K": 27.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 73.0, + "Available on the hub": true, + "Model sha": "e68a8a2888097def3c7f4fe5d443866a18d05c6c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "genaicore3434\/Mistral-7b-instruct-v0.2-summ-sft-lp-e1", + "Average \u2b06\ufe0f": 64.46, + "ARC": 61.01, + "HellaSwag": 83.32, + "MMLU": 60.62, + "TruthfulQA": 64.66, + "Winogrande": 76.95, + "GSM8K": 40.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3a21fabd41c5c558e42f5ee592294ac56369d3d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kwchoi\/DPO_mistral_7b_ultra_0124_v1", + "Average \u2b06\ufe0f": 64.45, + "ARC": 66.13, + "HellaSwag": 86.39, + "MMLU": 59.78, + "TruthfulQA": 69.45, + "Winogrande": 79.48, + "GSM8K": 25.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a448081da7d55c5b45294e13c264dbb0133b2cce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AbacusResearch\/haLLAwa2", + "Average \u2b06\ufe0f": 64.44, + "ARC": 63.31, + "HellaSwag": 84.51, + "MMLU": 63.52, + "TruthfulQA": 47.38, + "Winogrande": 75.85, + "GSM8K": 52.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2ab34884c6ccfb52e625fdb3a5fc4f69fbe226fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NurtureAI\/Starling-LM-11B-alpha-v1", + "Average \u2b06\ufe0f": 64.44, + "ARC": 62.2, + "HellaSwag": 83.24, + "MMLU": 64.03, + "TruthfulQA": 45.7, + "Winogrande": 80.51, + "GSM8K": 50.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b2b3b9fc069a8b5d8be82f68f0f578a6f23e9e5f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hedronstone\/OpenHermes-7B-Symbolic", + "Average \u2b06\ufe0f": 64.44, + "ARC": 63.14, + "HellaSwag": 82.73, + "MMLU": 62.62, + "TruthfulQA": 48.82, + "Winogrande": 75.85, + "GSM8K": 53.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "23eb76553aa37cd48c1f2d8a314d78fd3ead53f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hedronstone\/OpenHermes-7B-Reasoner", + "Average \u2b06\ufe0f": 64.44, + "ARC": 63.14, + "HellaSwag": 82.73, + "MMLU": 62.62, + "TruthfulQA": 48.82, + "Winogrande": 75.85, + "GSM8K": 53.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d26f2defbf9f40a65dbb2ead08c79cd61096ed08", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Medilora\/medilora-mistral-7b", + "Average \u2b06\ufe0f": 64.41, + "ARC": 61.69, + "HellaSwag": 83.13, + "MMLU": 62.22, + "TruthfulQA": 49.91, + "Winogrande": 77.66, + "GSM8K": 51.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b6512d2a2202e685da461ff876a1ffb707034c97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elinas\/chronos-70b-v2", + "Average \u2b06\ufe0f": 64.41, + "ARC": 68.09, + "HellaSwag": 86.5, + "MMLU": 68.28, + "TruthfulQA": 53.7, + "Winogrande": 81.22, + "GSM8K": 28.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "373af41ca0b2855972b8d471fd63e72b63e4c9fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "MRAIRR\/mini_7B_dare_v1", + "Average \u2b06\ufe0f": 64.4, + "ARC": 61.77, + "HellaSwag": 79.91, + "MMLU": 59.55, + "TruthfulQA": 54.64, + "Winogrande": 73.95, + "GSM8K": 56.56, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "49c083289b20fbe14e7002fa71eed01127b2fbf5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xxyyy123\/Mistral-dpo-v1", + "Average \u2b06\ufe0f": 64.39, + "ARC": 63.48, + "HellaSwag": 83.59, + "MMLU": 63.35, + "TruthfulQA": 50.49, + "Winogrande": 79.32, + "GSM8K": 46.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3c677a659bffbccbd8cf5ea75d198541ea2ec990", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "v1olet\/v1olet_merged_dpo_7B_v4", + "Average \u2b06\ufe0f": 64.3, + "ARC": 66.98, + "HellaSwag": 84.09, + "MMLU": 59.02, + "TruthfulQA": 59.43, + "Winogrande": 81.06, + "GSM8K": 35.25, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aa1b6363990ed2f180b2a22986cecc3afa4d12c8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Einstein-bagel-7B", + "Average \u2b06\ufe0f": 64.3, + "ARC": 66.89, + "HellaSwag": 84.81, + "MMLU": 63.48, + "TruthfulQA": 63.33, + "Winogrande": 79.16, + "GSM8K": 28.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d66c858c2f4f24ae867423e6d844b6dc3a1208b1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "google\/gemma-7b", + "Average \u2b06\ufe0f": 64.29, + "ARC": 61.09, + "HellaSwag": 82.47, + "MMLU": 66.03, + "TruthfulQA": 44.91, + "Winogrande": 78.45, + "GSM8K": 52.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 1509.0, + "Available on the hub": true, + "Model sha": "7646584ed746494da9e1058b1be53d1be8b2ee73", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/PiVoT-10.7B-Mistral-v0.2", + "Average \u2b06\ufe0f": 64.25, + "ARC": 63.31, + "HellaSwag": 81.68, + "MMLU": 59.86, + "TruthfulQA": 58.23, + "Winogrande": 80.03, + "GSM8K": 42.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "a496457d0743b6030ffbb96dad2dc6a62d143943", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "manishiitg\/open-aditi-hi-v4", + "Average \u2b06\ufe0f": 64.23, + "ARC": 60.15, + "HellaSwag": 81.84, + "MMLU": 61.32, + "TruthfulQA": 44.89, + "Winogrande": 79.95, + "GSM8K": 57.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b396464b51acb625c8bf1875fb8fb0ebe973e9a3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "genaicore3434\/Mistral-7b-instruct-v0.2-summ-sft-bf16-e1", + "Average \u2b06\ufe0f": 64.22, + "ARC": 60.58, + "HellaSwag": 83.32, + "MMLU": 60.79, + "TruthfulQA": 64.72, + "Winogrande": 76.72, + "GSM8K": 39.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "440decfee1fefa33072e2a99e4190f0a206aba13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/model_420_preview", + "Average \u2b06\ufe0f": 64.22, + "ARC": 67.06, + "HellaSwag": 87.26, + "MMLU": 69.85, + "TruthfulQA": 44.57, + "Winogrande": 83.35, + "GSM8K": 33.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5095384f1b7bb6e23a987f95589e66e21ae854ef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cookinai\/titanbagel", + "Average \u2b06\ufe0f": 64.21, + "ARC": 62.71, + "HellaSwag": 83.36, + "MMLU": 63.12, + "TruthfulQA": 52.49, + "Winogrande": 79.08, + "GSM8K": 44.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dc2dcdfe71a5f9a059d98c8e573df3254ff5bdd0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "yanolja\/KoSOLAR-10.7B-v0.2", + "Average \u2b06\ufe0f": 64.2, + "ARC": 61.35, + "HellaSwag": 82.63, + "MMLU": 64.85, + "TruthfulQA": 47.94, + "Winogrande": 80.74, + "GSM8K": 47.69, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "ca6148593cca082392faa5d1b0b72995b672eddb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Neuronovo\/neuronovo-7B-v0.1", + "Average \u2b06\ufe0f": 64.19, + "ARC": 66.98, + "HellaSwag": 85.07, + "MMLU": 63.33, + "TruthfulQA": 53.95, + "Winogrande": 78.14, + "GSM8K": 37.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ec4f35d96aa47229fb3cab047fb9aedd6b0ad383", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Platyboros-Instruct-7B", + "Average \u2b06\ufe0f": 64.19, + "ARC": 57.76, + "HellaSwag": 82.59, + "MMLU": 62.05, + "TruthfulQA": 60.92, + "Winogrande": 78.14, + "GSM8K": 43.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "166c6ba6e9fb6fcb011d98c5cdbe68d17953d3d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-70b-gpt4-2.0", + "Average \u2b06\ufe0f": 64.14, + "ARC": 68.52, + "HellaSwag": 87.89, + "MMLU": 70.41, + "TruthfulQA": 49.79, + "Winogrande": 83.5, + "GSM8K": 24.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "f16526d9bb814dc10adc911f94e8c7a520beb5b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Einstein-v3-7B", + "Average \u2b06\ufe0f": 64.09, + "ARC": 62.29, + "HellaSwag": 83.01, + "MMLU": 63.32, + "TruthfulQA": 51.18, + "Winogrande": 79.95, + "GSM8K": 44.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "632d22a529a04a16f0297320ba221ef4091a797c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/Einstein-v3-7B", + "Average \u2b06\ufe0f": 64.09, + "ARC": 62.29, + "HellaSwag": 83.01, + "MMLU": 63.32, + "TruthfulQA": 51.18, + "Winogrande": 79.95, + "GSM8K": 44.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "632d22a529a04a16f0297320ba221ef4091a797c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibndias\/NeuralHermes-MoE-2x7B", + "Average \u2b06\ufe0f": 64.08, + "ARC": 62.12, + "HellaSwag": 84.21, + "MMLU": 64.56, + "TruthfulQA": 43.61, + "Winogrande": 78.14, + "GSM8K": 51.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f8a3c8339ea38ce577e0c45aba859ac63b4c3cf3", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "sethuiyer\/Herculoid-2.0", + "Average \u2b06\ufe0f": 64.08, + "ARC": 62.88, + "HellaSwag": 83.93, + "MMLU": 64.03, + "TruthfulQA": 49.61, + "Winogrande": 80.03, + "GSM8K": 43.97, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fd39739fa6569e7020bba9cb49c2920bbdcb7aba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder67\/Mistral-7b-instruct-v0.2-summ-sft-dpo-e1", + "Average \u2b06\ufe0f": 64.05, + "ARC": 59.3, + "HellaSwag": 83.64, + "MMLU": 60.31, + "TruthfulQA": 66.33, + "Winogrande": 76.09, + "GSM8K": 38.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9eae12f70b601824919394f486dcad3fba26ca3e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "robinsmits\/Mistral-Instruct-7B-v0.2-ChatAlpaca-DPO2", + "Average \u2b06\ufe0f": 64.05, + "ARC": 61.86, + "HellaSwag": 83.71, + "MMLU": 59.19, + "TruthfulQA": 64.08, + "Winogrande": 78.45, + "GSM8K": 37.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "32122f2efc944e3b88e502c6c310ce4c70fe1419", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Enoch\/llama-65b-hf", + "Average \u2b06\ufe0f": 63.99, + "ARC": 63.31, + "HellaSwag": 86.09, + "MMLU": 63.84, + "TruthfulQA": 43.43, + "Winogrande": 82.48, + "GSM8K": 44.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LLaMAForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "7a7b897ab10b3d82d1e7e6fbcd2159d70b4586cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Steelskull\/Aurora_base_test", + "Average \u2b06\ufe0f": 63.98, + "ARC": 62.88, + "HellaSwag": 83.99, + "MMLU": 60.24, + "TruthfulQA": 67.84, + "Winogrande": 76.4, + "GSM8K": 32.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "74c799e46cc89e6fdbd5bc88fe3c75a081768e70", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Fewshot-Metamath-Mistral", + "Average \u2b06\ufe0f": 63.96, + "ARC": 57.76, + "HellaSwag": 80.59, + "MMLU": 58.05, + "TruthfulQA": 43.04, + "Winogrande": 76.01, + "GSM8K": 68.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5c6d79d66a84efd6b6e879c2fe4f2e4a21df3a1e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder45\/Mistral-7b-instruct-v0.2-summ-sft-dpo-e3", + "Average \u2b06\ufe0f": 63.95, + "ARC": 58.87, + "HellaSwag": 83.56, + "MMLU": 60.37, + "TruthfulQA": 66.26, + "Winogrande": 76.32, + "GSM8K": 38.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7d5b26e13a4967f25aa53852ff9a3a8ce0348116", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/gemma-7b-ultrachat-sft", + "Average \u2b06\ufe0f": 63.92, + "ARC": 61.26, + "HellaSwag": 80.82, + "MMLU": 64.16, + "TruthfulQA": 54.5, + "Winogrande": 78.14, + "GSM8K": 44.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c4cd06ead3275d15e021423af0b69e59b0e3ec00", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Novocoders\/Mistral-NeuralDPO-v0.4-Laser", + "Average \u2b06\ufe0f": 63.89, + "ARC": 66.89, + "HellaSwag": 85.23, + "MMLU": 63.47, + "TruthfulQA": 50.91, + "Winogrande": 80.27, + "GSM8K": 36.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8726f72ca9decc32df5e74bfae38c8a531f65836", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "silvercoder67\/Mistral-7b-instruct-v0.2-summ-sft-e2m", + "Average \u2b06\ufe0f": 63.86, + "ARC": 59.47, + "HellaSwag": 83.34, + "MMLU": 60.53, + "TruthfulQA": 63.78, + "Winogrande": 76.48, + "GSM8K": 39.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fccef397114fa38158f704557d1f799f1c8a4e52", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Novocoders\/Mistral-NeuralDPO-v0.4", + "Average \u2b06\ufe0f": 63.85, + "ARC": 66.04, + "HellaSwag": 85.18, + "MMLU": 63.57, + "TruthfulQA": 51.32, + "Winogrande": 80.11, + "GSM8K": 36.85, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "76a02dd47c11f8c225d922eb12aa1b4a3c3a74a7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Steelskull\/VerB-Etheria-55b", + "Average \u2b06\ufe0f": 63.83, + "ARC": 65.96, + "HellaSwag": 81.48, + "MMLU": 73.78, + "TruthfulQA": 57.52, + "Winogrande": 75.45, + "GSM8K": 28.81, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 55.59, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "dcab4ed7680a3e5c2f4e3ef36e880cb3b9149dd0", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "openbmb\/UltraLM-65b", + "Average \u2b06\ufe0f": 63.82, + "ARC": 67.06, + "HellaSwag": 84.98, + "MMLU": 63.48, + "TruthfulQA": 53.51, + "Winogrande": 81.14, + "GSM8K": 32.75, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Delta", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Hermes-Instruct-7B-v0.2", + "Average \u2b06\ufe0f": 63.82, + "ARC": 60.92, + "HellaSwag": 82.96, + "MMLU": 60.05, + "TruthfulQA": 61.01, + "Winogrande": 76.87, + "GSM8K": 41.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6675073736e1f611aaf48ef9777076183d233c96", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/14B", + "Average \u2b06\ufe0f": 63.81, + "ARC": 56.66, + "HellaSwag": 79.08, + "MMLU": 65.86, + "TruthfulQA": 47.75, + "Winogrande": 74.9, + "GSM8K": 58.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "wtfpl", + "#Params (B)": 14.0, + "Hub \u2764\ufe0f": 258.0, + "Available on the hub": true, + "Model sha": "2576a37434e2e03804c841d36c669c8a34c729de", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Medilora\/medilora-qwen-14b", + "Average \u2b06\ufe0f": 63.81, + "ARC": 56.66, + "HellaSwag": 79.08, + "MMLU": 65.86, + "TruthfulQA": 47.75, + "Winogrande": 74.9, + "GSM8K": 58.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0649cf49b7a879fe837567a346a3ebbbac77614a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/CausalLM-Platypus-14B", + "Average \u2b06\ufe0f": 63.8, + "ARC": 56.91, + "HellaSwag": 80.06, + "MMLU": 64.98, + "TruthfulQA": 47.57, + "Winogrande": 76.01, + "GSM8K": 57.24, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1659d3cdbb8bb8dba902ab2874f4fa886980fc70", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/mistral-inst-ppo", + "Average \u2b06\ufe0f": 63.79, + "ARC": 62.37, + "HellaSwag": 83.2, + "MMLU": 60.86, + "TruthfulQA": 62.3, + "Winogrande": 76.95, + "GSM8K": 37.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "600c429a86dcd6e18f0285d7cd9189540ccbdc50", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SCE\/Mistral-7B-summ-ia3-tuned", + "Average \u2b06\ufe0f": 63.79, + "ARC": 59.64, + "HellaSwag": 84.71, + "MMLU": 59.48, + "TruthfulQA": 68.6, + "Winogrande": 76.72, + "GSM8K": 33.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4c6c4078bcf01d1c0faf90bd4842c2f0fbd8ebcc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jae24\/openhermes_dpo_norobot_0201", + "Average \u2b06\ufe0f": 63.78, + "ARC": 62.03, + "HellaSwag": 83.4, + "MMLU": 62.4, + "TruthfulQA": 47.44, + "Winogrande": 78.22, + "GSM8K": 49.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "db7b39141559ca4810371593d9caab4361704646", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abhishekchohan\/mistral-7B-med-merge", + "Average \u2b06\ufe0f": 63.75, + "ARC": 64.51, + "HellaSwag": 82.96, + "MMLU": 57.84, + "TruthfulQA": 53.65, + "Winogrande": 78.61, + "GSM8K": 44.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "120987e276831fe6916a86a80c0c39ac3aa5dfb7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "google\/gemma-7b", + "Average \u2b06\ufe0f": 63.75, + "ARC": 61.09, + "HellaSwag": 82.2, + "MMLU": 64.56, + "TruthfulQA": 44.79, + "Winogrande": 79.01, + "GSM8K": 50.87, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 1509.0, + "Available on the hub": true, + "Model sha": "1685d3c30e63630be55aa9a8730531732b3bd93c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "fhai50032\/xLakeChat", + "Average \u2b06\ufe0f": 63.72, + "ARC": 62.37, + "HellaSwag": 82.64, + "MMLU": 59.32, + "TruthfulQA": 52.96, + "Winogrande": 74.74, + "GSM8K": 50.27, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9aa5bda433ab1619afb2fae5d00e8762e2669129", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "TigerResearch\/tigerbot-70b-base", + "Average \u2b06\ufe0f": 63.71, + "ARC": 62.46, + "HellaSwag": 83.61, + "MMLU": 65.49, + "TruthfulQA": 52.76, + "Winogrande": 80.19, + "GSM8K": 37.76, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 68.95, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8af85526293eb8625375f3f7a1bab69825176e48", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "UCLA-AGI\/zephyr-7b-sft-full-SPIN-iter3", + "Average \u2b06\ufe0f": 63.7, + "ARC": 66.13, + "HellaSwag": 85.85, + "MMLU": 61.51, + "TruthfulQA": 57.89, + "Winogrande": 76.64, + "GSM8K": 34.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "f4d6d3b9fce399c73c727eb5f7e68a10ae751ad4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/test_final", + "Average \u2b06\ufe0f": 63.7, + "ARC": 66.13, + "HellaSwag": 85.85, + "MMLU": 61.51, + "TruthfulQA": 57.89, + "Winogrande": 76.64, + "GSM8K": 34.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b996460b9ac3969f2c685c3f3669ba944022b2be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Delcos\/Starling-LM-11B-alpha", + "Average \u2b06\ufe0f": 63.66, + "ARC": 62.97, + "HellaSwag": 84.85, + "MMLU": 63.83, + "TruthfulQA": 54.52, + "Winogrande": 77.82, + "GSM8K": 37.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 11.39, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "16086688b70e4f54e1ba4f54a1a847c30b987a74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/gpt4-alpaca-lora_mlp-65B-HF", + "Average \u2b06\ufe0f": 63.66, + "ARC": 65.02, + "HellaSwag": 86.13, + "MMLU": 62.73, + "TruthfulQA": 59.16, + "Winogrande": 80.66, + "GSM8K": 28.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "664ff8e3e1d446971a16a6c9018ab24de7664684", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Radu1999\/Mistral-Instruct-Ukrainian-SFT-DPO", + "Average \u2b06\ufe0f": 63.64, + "ARC": 60.49, + "HellaSwag": 83.84, + "MMLU": 60.9, + "TruthfulQA": 57.91, + "Winogrande": 76.95, + "GSM8K": 41.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "317a3016054ccd9e90956a7ac587f004b9f64a45", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "monology\/openinstruct-mistral-7b", + "Average \u2b06\ufe0f": 63.64, + "ARC": 59.73, + "HellaSwag": 82.77, + "MMLU": 60.55, + "TruthfulQA": 48.76, + "Winogrande": 79.56, + "GSM8K": 50.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "54f379bf7676ffd09b48b0ff607b7ae6c0a6f688", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Kaiju-A-57B", + "Average \u2b06\ufe0f": 63.64, + "ARC": 58.79, + "HellaSwag": 80.95, + "MMLU": 72.66, + "TruthfulQA": 52.29, + "Winogrande": 78.77, + "GSM8K": 38.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 57.26, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "11fc415ccc69d9f5a72be7f90be0b48b9c782f67", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/xLakeChat", + "Average \u2b06\ufe0f": 63.64, + "ARC": 62.54, + "HellaSwag": 82.66, + "MMLU": 59.19, + "TruthfulQA": 53.02, + "Winogrande": 74.51, + "GSM8K": 49.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9aa5bda433ab1619afb2fae5d00e8762e2669129", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azure99\/blossom-v4-mistral-7b", + "Average \u2b06\ufe0f": 63.61, + "ARC": 62.03, + "HellaSwag": 82.9, + "MMLU": 62.48, + "TruthfulQA": 53.84, + "Winogrande": 77.27, + "GSM8K": 43.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "43d6205b109754c02a4606beee64f42d151067f1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-code-mistral-7b-v1.0", + "Average \u2b06\ufe0f": 63.6, + "ARC": 61.18, + "HellaSwag": 83.77, + "MMLU": 63.4, + "TruthfulQA": 47.9, + "Winogrande": 78.37, + "GSM8K": 47.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "43dea8e97d05f2e4358415b9a95a1b327c1f5804", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/higgs-llama-vicuna-ep25-70b", + "Average \u2b06\ufe0f": 63.6, + "ARC": 62.29, + "HellaSwag": 86.07, + "MMLU": 64.25, + "TruthfulQA": 53.75, + "Winogrande": 80.66, + "GSM8K": 34.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1da59e150f1d0bae67f66400738a01d408a8c45d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hercules-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 63.59, + "ARC": 62.03, + "HellaSwag": 83.79, + "MMLU": 63.49, + "TruthfulQA": 43.44, + "Winogrande": 79.72, + "GSM8K": 49.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "ff62c26031544deeffd9f06250e71fd05fb1169a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Mistral-NeuralDPO-v0.2", + "Average \u2b06\ufe0f": 63.58, + "ARC": 67.06, + "HellaSwag": 85.01, + "MMLU": 62.68, + "TruthfulQA": 48.73, + "Winogrande": 81.29, + "GSM8K": 36.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "8c6e6989261d5223ca613a22660f4ba7df70995a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/test-test", + "Average \u2b06\ufe0f": 63.54, + "ARC": 66.47, + "HellaSwag": 85.82, + "MMLU": 61.48, + "TruthfulQA": 57.75, + "Winogrande": 76.95, + "GSM8K": 32.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "83731d11da3f0878effd3a32e5aea52249de7c81", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KaeriJenti\/Kaori-34B-v1", + "Average \u2b06\ufe0f": 63.52, + "ARC": 64.51, + "HellaSwag": 79.65, + "MMLU": 70.19, + "TruthfulQA": 53.14, + "Winogrande": 76.95, + "GSM8K": 36.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3a03b2aba751680105e027ef096866320bf9bd2b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/zephyr-7b-sft-full-SPIN-iter2", + "Average \u2b06\ufe0f": 63.52, + "ARC": 66.38, + "HellaSwag": 85.84, + "MMLU": 61.22, + "TruthfulQA": 57.82, + "Winogrande": 76.8, + "GSM8K": 33.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "336bff60f5ce904c2ab9633315192df904431afa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/test-test", + "Average \u2b06\ufe0f": 63.52, + "ARC": 66.38, + "HellaSwag": 85.84, + "MMLU": 61.22, + "TruthfulQA": 57.82, + "Winogrande": 76.8, + "GSM8K": 33.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "83731d11da3f0878effd3a32e5aea52249de7c81", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Falkor-16b", + "Average \u2b06\ufe0f": 63.52, + "ARC": 65.96, + "HellaSwag": 82.62, + "MMLU": 63.58, + "TruthfulQA": 62.77, + "Winogrande": 77.9, + "GSM8K": 28.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2365c7af9eb60bfa946b566dadd6802befa122e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SUSTech\/SUS-Chat-72B", + "Average \u2b06\ufe0f": 63.51, + "ARC": 66.3, + "HellaSwag": 84.96, + "MMLU": 76.7, + "TruthfulQA": 60.27, + "Winogrande": 83.43, + "GSM8K": 9.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "869bbd5b18656e74b606bd775e2594809407603c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "alignment-handbook\/zephyr-7b-dpo-qlora", + "Average \u2b06\ufe0f": 63.51, + "ARC": 63.65, + "HellaSwag": 85.35, + "MMLU": 63.82, + "TruthfulQA": 47.14, + "Winogrande": 79.01, + "GSM8K": 42.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b991e934e478e9b406d07840940e9a785a62f0ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "argilla\/notus-7b-v1", + "Average \u2b06\ufe0f": 63.49, + "ARC": 64.59, + "HellaSwag": 84.83, + "MMLU": 63.04, + "TruthfulQA": 54.35, + "Winogrande": 79.56, + "GSM8K": 34.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 106.0, + "Available on the hub": true, + "Model sha": "f23f4cf6cb76402c76e932ead01109191af72a60", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/einstein-v2-test-model", + "Average \u2b06\ufe0f": 63.48, + "ARC": 62.37, + "HellaSwag": 83.46, + "MMLU": 62.08, + "TruthfulQA": 50.52, + "Winogrande": 79.32, + "GSM8K": 43.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2e31cc426945278f93a91b3a93dc5bf524fe0972", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Einstein-v2-7B", + "Average \u2b06\ufe0f": 63.48, + "ARC": 62.37, + "HellaSwag": 83.46, + "MMLU": 62.08, + "TruthfulQA": 50.52, + "Winogrande": 79.32, + "GSM8K": 43.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2e31cc426945278f93a91b3a93dc5bf524fe0972", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tuantran1632001\/Psyfighter2-Orca2-ties", + "Average \u2b06\ufe0f": 63.48, + "ARC": 62.46, + "HellaSwag": 81.74, + "MMLU": 60.31, + "TruthfulQA": 55.4, + "Winogrande": 77.27, + "GSM8K": 43.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e4ab7df425cfa2b2687194837c3b7fba4be7fc74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tuantran1632001\/Psyfighter2-Orca2-13B-ties", + "Average \u2b06\ufe0f": 63.48, + "ARC": 62.46, + "HellaSwag": 81.74, + "MMLU": 60.31, + "TruthfulQA": 55.4, + "Winogrande": 77.27, + "GSM8K": 43.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b858fbc15734cc797f1c9e4acb239bfb6c390f08", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KaeriJenti\/Kaori-34B-v1", + "Average \u2b06\ufe0f": 63.47, + "ARC": 64.42, + "HellaSwag": 79.61, + "MMLU": 70.24, + "TruthfulQA": 53.17, + "Winogrande": 76.72, + "GSM8K": 36.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3a03b2aba751680105e027ef096866320bf9bd2b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishekchohan\/mistral-7B-forest", + "Average \u2b06\ufe0f": 63.47, + "ARC": 65.7, + "HellaSwag": 86.26, + "MMLU": 63.32, + "TruthfulQA": 53.32, + "Winogrande": 79.48, + "GSM8K": 32.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "02c58b0694973815a6d89f29c74f5cb1a4562891", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Stopwolf\/Cerberus-7B-slerp", + "Average \u2b06\ufe0f": 63.46, + "ARC": 69.54, + "HellaSwag": 87.33, + "MMLU": 63.25, + "TruthfulQA": 61.35, + "Winogrande": 81.29, + "GSM8K": 17.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ca54f14a8230e73af3c28a67058838d253564926", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AI-B\/UTENA-7B-NSFW-V2", + "Average \u2b06\ufe0f": 63.45, + "ARC": 63.31, + "HellaSwag": 84.54, + "MMLU": 63.97, + "TruthfulQA": 47.81, + "Winogrande": 78.69, + "GSM8K": 42.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "unlicense", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "2da9543e68e222ca627a22a131772155d5ef9078", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xxyyy123\/Mistral7B_adaptor_v1", + "Average \u2b06\ufe0f": 63.42, + "ARC": 62.97, + "HellaSwag": 83.81, + "MMLU": 63.56, + "TruthfulQA": 49.77, + "Winogrande": 79.16, + "GSM8K": 41.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "23e800094570c22fbaa4279ef7e7f27315ac61af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-16B-v2.01", + "Average \u2b06\ufe0f": 63.42, + "ARC": 65.36, + "HellaSwag": 82.92, + "MMLU": 63.27, + "TruthfulQA": 64.53, + "Winogrande": 79.08, + "GSM8K": 25.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3b723559b550a34e489cc41ec5414e00531ec2ae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "llm-agents\/tora-70b-v1.0", + "Average \u2b06\ufe0f": 63.39, + "ARC": 67.75, + "HellaSwag": 85.83, + "MMLU": 69.22, + "TruthfulQA": 51.79, + "Winogrande": 81.93, + "GSM8K": 23.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "e95fd7daf017e7c414ec07ebef4ddf013c16f9a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/Mini_Synatra_SFT", + "Average \u2b06\ufe0f": 63.39, + "ARC": 62.46, + "HellaSwag": 83.44, + "MMLU": 61.2, + "TruthfulQA": 53.67, + "Winogrande": 74.66, + "GSM8K": 44.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "fc042f671dc0c94b21a6107eda75a6f9c8d44f2d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xxyyy123\/1701221123_Ads_Mistral7B-slimorca_all-Lqv-r4b128", + "Average \u2b06\ufe0f": 63.37, + "ARC": 62.88, + "HellaSwag": 83.99, + "MMLU": 62.89, + "TruthfulQA": 50.55, + "Winogrande": 79.72, + "GSM8K": 40.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2872cd97f88418d6b07082048b316ea5b996982d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xDAN-AI\/xDAN-L1Mix-DeepThinking-v2", + "Average \u2b06\ufe0f": 63.36, + "ARC": 62.37, + "HellaSwag": 82.32, + "MMLU": 59.69, + "TruthfulQA": 55.38, + "Winogrande": 76.4, + "GSM8K": 43.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "47ca647c3bb26b647b1f66c3672b890803de46c8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "liminerity\/Blur-7b-v1.22", + "Average \u2b06\ufe0f": 63.35, + "ARC": 62.29, + "HellaSwag": 82.0, + "MMLU": 58.03, + "TruthfulQA": 68.01, + "Winogrande": 78.61, + "GSM8K": 31.16, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c187e675917fa03b179fa488a9007a803ee8c48b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "malhajar\/Mistral-7B-v0.2-meditron-turkish", + "Average \u2b06\ufe0f": 63.34, + "ARC": 59.56, + "HellaSwag": 81.79, + "MMLU": 60.35, + "TruthfulQA": 66.19, + "Winogrande": 76.24, + "GSM8K": 35.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "906025770a885b26f762b13bb0bc726438e525de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "liminerity\/Blur-7b-v1.22", + "Average \u2b06\ufe0f": 63.3, + "ARC": 62.12, + "HellaSwag": 82.09, + "MMLU": 57.9, + "TruthfulQA": 67.96, + "Winogrande": 78.69, + "GSM8K": 31.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c187e675917fa03b179fa488a9007a803ee8c48b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mobiuslabsgmbh\/aanaphi2-v0.1", + "Average \u2b06\ufe0f": 63.28, + "ARC": 63.91, + "HellaSwag": 77.97, + "MMLU": 57.73, + "TruthfulQA": 51.56, + "Winogrande": 73.64, + "GSM8K": 54.89, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3ccc97066e70b9aa5f686083b7d406c312c490e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishekchohan\/mistral-7B-forest-dpo", + "Average \u2b06\ufe0f": 63.28, + "ARC": 65.02, + "HellaSwag": 86.31, + "MMLU": 63.05, + "TruthfulQA": 55.43, + "Winogrande": 79.56, + "GSM8K": 30.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "49b6d10aa6fde729393be056f8e110345c633342", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pinkyponky\/Mistral-7b-instruct-v0.2-summ-sft-e1", + "Average \u2b06\ufe0f": 63.28, + "ARC": 60.15, + "HellaSwag": 82.59, + "MMLU": 58.92, + "TruthfulQA": 63.13, + "Winogrande": 77.11, + "GSM8K": 37.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cb20f22f421052e1ca8ea8bd9974fade5ccdfa9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vilm\/Quyen-Plus-v0.1", + "Average \u2b06\ufe0f": 63.27, + "ARC": 55.72, + "HellaSwag": 78.52, + "MMLU": 60.45, + "TruthfulQA": 53.6, + "Winogrande": 71.27, + "GSM8K": 60.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "b5bd5bf9c0c0976e18fa7341326a87090d8aa626", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Gecko-7B-v0.1-DPO", + "Average \u2b06\ufe0f": 63.22, + "ARC": 56.74, + "HellaSwag": 82.38, + "MMLU": 60.42, + "TruthfulQA": 57.42, + "Winogrande": 77.35, + "GSM8K": 45.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "7a377ce18d900f287222895973dd866fd53930f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chanwit\/flux-base-optimized", + "Average \u2b06\ufe0f": 63.22, + "ARC": 65.44, + "HellaSwag": 81.74, + "MMLU": 59.74, + "TruthfulQA": 50.02, + "Winogrande": 77.74, + "GSM8K": 44.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ce9f1f49559007d5b81249fd1ca3eb8be088fe43", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Aeryth-7B-v0.1", + "Average \u2b06\ufe0f": 63.19, + "ARC": 60.32, + "HellaSwag": 83.53, + "MMLU": 60.97, + "TruthfulQA": 63.57, + "Winogrande": 74.66, + "GSM8K": 36.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "b7befcbc2e609356efc76c64cee1b1727727d815", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Deci\/DeciLM-7B-instruct", + "Average \u2b06\ufe0f": 63.19, + "ARC": 61.01, + "HellaSwag": 82.37, + "MMLU": 60.24, + "TruthfulQA": 49.75, + "Winogrande": 79.72, + "GSM8K": 46.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "DeciLMForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.04, + "Hub \u2764\ufe0f": 94.0, + "Available on the hub": true, + "Model sha": "24a66a701c10e5d70397f9bfc1624447327a0a08", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "liuda1\/dm7b_sft_gpt88w_merge", + "Average \u2b06\ufe0f": 63.18, + "ARC": 62.29, + "HellaSwag": 82.47, + "MMLU": 61.35, + "TruthfulQA": 53.33, + "Winogrande": 77.58, + "GSM8K": 42.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f4f76170f6fe63e832e32d32be1eb4a1da36f402", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KaeriJenti\/kaori-34b-v3", + "Average \u2b06\ufe0f": 63.18, + "ARC": 64.25, + "HellaSwag": 79.59, + "MMLU": 70.18, + "TruthfulQA": 52.37, + "Winogrande": 76.48, + "GSM8K": 36.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "117dab7fc59bff50279100214e39f5551ba0c593", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "01-ai\/Yi-34B-Chat", + "Average \u2b06\ufe0f": 63.17, + "ARC": 65.1, + "HellaSwag": 84.08, + "MMLU": 74.87, + "TruthfulQA": 55.41, + "Winogrande": 79.79, + "GSM8K": 19.79, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 274.0, + "Available on the hub": true, + "Model sha": "a99ec35331cbfc9da596af7d4538fe2efecff03c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "pinkyponky\/Mistral-7b-instruct-v0.2-summ-sft-e3", + "Average \u2b06\ufe0f": 63.14, + "ARC": 59.98, + "HellaSwag": 82.76, + "MMLU": 59.48, + "TruthfulQA": 63.0, + "Winogrande": 76.24, + "GSM8K": 37.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5b09e3dd2bf8bcf08b9b3dd0d69e4cc67d782fd3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decem\/Dionysus-Mistral-m3-v5", + "Average \u2b06\ufe0f": 63.14, + "ARC": 59.56, + "HellaSwag": 80.99, + "MMLU": 61.18, + "TruthfulQA": 50.93, + "Winogrande": 75.14, + "GSM8K": 51.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7c6a76f284740abd1b262b950aa59d72c65d39e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "genaicore3434\/Mistral-7b-instruct-v0.2-summ-sft-lp-e1", + "Average \u2b06\ufe0f": 63.13, + "ARC": 59.56, + "HellaSwag": 82.27, + "MMLU": 59.12, + "TruthfulQA": 63.26, + "Winogrande": 77.03, + "GSM8K": 37.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3a21fabd41c5c558e42f5ee592294ac56369d3d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kiddyz\/testllm-c2", + "Average \u2b06\ufe0f": 63.13, + "ARC": 60.58, + "HellaSwag": 81.91, + "MMLU": 61.2, + "TruthfulQA": 49.87, + "Winogrande": 77.82, + "GSM8K": 47.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b87c798bc27522824451dfccf5eae50edbd4263b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chanwit\/flux-base-optimized", + "Average \u2b06\ufe0f": 63.12, + "ARC": 65.53, + "HellaSwag": 81.76, + "MMLU": 59.84, + "TruthfulQA": 50.03, + "Winogrande": 77.35, + "GSM8K": 44.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ce9f1f49559007d5b81249fd1ca3eb8be088fe43", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kaitchup\/Maixtchup-4x7b-QLoRA-SFT-UltraChat", + "Average \u2b06\ufe0f": 63.11, + "ARC": 60.92, + "HellaSwag": 83.23, + "MMLU": 60.78, + "TruthfulQA": 53.33, + "Winogrande": 77.19, + "GSM8K": 43.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ee716b901ff5ee52fe20417c6a0a2f6aa28d3f38", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "KnutJaegersberg\/Qwen-14B-Llamafied", + "Average \u2b06\ufe0f": 63.09, + "ARC": 55.2, + "HellaSwag": 82.31, + "MMLU": 66.11, + "TruthfulQA": 45.6, + "Winogrande": 76.56, + "GSM8K": 52.77, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "c53e0ea05664c66346627714f332a9b46cde8fd6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "tourist800\/Marcoro14-7B-slerp", + "Average \u2b06\ufe0f": 63.08, + "ARC": 63.4, + "HellaSwag": 83.77, + "MMLU": 61.18, + "TruthfulQA": 52.08, + "Winogrande": 77.9, + "GSM8K": 40.18, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8722dce4c447d974545f55623788c351a15bc36c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "tourist800\/mistral_2X7b", + "Average \u2b06\ufe0f": 63.08, + "ARC": 63.4, + "HellaSwag": 83.77, + "MMLU": 61.18, + "TruthfulQA": 52.08, + "Winogrande": 77.9, + "GSM8K": 40.18, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8722dce4c447d974545f55623788c351a15bc36c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pinkyponky\/Mistral-7b-instruct-v0.2-summ-sft-e2", + "Average \u2b06\ufe0f": 63.06, + "ARC": 59.47, + "HellaSwag": 82.72, + "MMLU": 59.48, + "TruthfulQA": 62.7, + "Winogrande": 76.64, + "GSM8K": 37.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "01a73ccd10a275738304c695d0728a29e8586f47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-falcon-180b-v12-preview0", + "Average \u2b06\ufe0f": 63.06, + "ARC": 62.29, + "HellaSwag": 83.8, + "MMLU": 55.92, + "TruthfulQA": 53.05, + "Winogrande": 82.08, + "GSM8K": 41.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 180.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4f1aeb136860ee3216f23faec0c598014e5c40a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Novocoders\/Mistral-NeuralDPO-v0.6", + "Average \u2b06\ufe0f": 63.04, + "ARC": 65.87, + "HellaSwag": 84.68, + "MMLU": 62.19, + "TruthfulQA": 48.22, + "Winogrande": 80.27, + "GSM8K": 37.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fb556fe63e21cf60d85106bf3b5c19ad20ff1c18", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "maywell\/PiVoT-MoE", + "Average \u2b06\ufe0f": 63.04, + "ARC": 63.91, + "HellaSwag": 83.52, + "MMLU": 60.71, + "TruthfulQA": 54.64, + "Winogrande": 76.32, + "GSM8K": 39.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 36.1, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "5d1159dd60ec2cc92dbc52508430e620b6adbdaa", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Airoboros-L2-70B-2.1-GPTQ", + "Average \u2b06\ufe0f": 63.04, + "ARC": 70.39, + "HellaSwag": 86.54, + "MMLU": 68.89, + "TruthfulQA": 55.55, + "Winogrande": 81.61, + "GSM8K": 15.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 72.82, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "23ed580cb77ebaee49ea11eb4538fd3ab3795b76", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azure99\/blossom-v3-mistral-7b", + "Average \u2b06\ufe0f": 62.95, + "ARC": 60.49, + "HellaSwag": 81.9, + "MMLU": 61.35, + "TruthfulQA": 50.31, + "Winogrande": 76.95, + "GSM8K": 46.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ec6e84a662c801e248d3bb3a19529155de02bda0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cgato\/Thespis-7b-v0.2-SFTTest-3Epoch", + "Average \u2b06\ufe0f": 62.94, + "ARC": 63.23, + "HellaSwag": 84.39, + "MMLU": 62.59, + "TruthfulQA": 53.9, + "Winogrande": 77.51, + "GSM8K": 36.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e9c6150deb741e6d27cbd947bf6b6c9c472f0750", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-zephyr-code-functionary-7b", + "Average \u2b06\ufe0f": 62.93, + "ARC": 61.52, + "HellaSwag": 83.88, + "MMLU": 64.71, + "TruthfulQA": 44.99, + "Winogrande": 78.69, + "GSM8K": 43.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4ba64c10fb56ade9ce2e0c5a097819b888c0a272", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HenryJJ\/dolphin-2.6-mistral-7b-dpo-orca-v3", + "Average \u2b06\ufe0f": 62.93, + "ARC": 66.3, + "HellaSwag": 84.53, + "MMLU": 62.36, + "TruthfulQA": 61.29, + "Winogrande": 77.58, + "GSM8K": 25.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "370a644bc9e2e4bfccada10a4bc6648102d94efe", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jefferylovely\/AthenaImaniMaven", + "Average \u2b06\ufe0f": 62.92, + "ARC": 62.8, + "HellaSwag": 84.56, + "MMLU": 59.1, + "TruthfulQA": 58.5, + "Winogrande": 77.43, + "GSM8K": 35.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f10a7d6055955eb40424dcac8a76658a11224c86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "teknium\/CollectiveCognition-v1.1-Mistral-7B", + "Average \u2b06\ufe0f": 62.92, + "ARC": 62.12, + "HellaSwag": 84.17, + "MMLU": 62.35, + "TruthfulQA": 57.62, + "Winogrande": 75.37, + "GSM8K": 35.86, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 73.0, + "Available on the hub": true, + "Model sha": "5f57f70ec99450c70da2540e94dd7fd67be4b23c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/test", + "Average \u2b06\ufe0f": 62.86, + "ARC": 65.87, + "HellaSwag": 85.44, + "MMLU": 60.95, + "TruthfulQA": 57.39, + "Winogrande": 76.64, + "GSM8K": 30.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "437d2f9c55aec50ebaedce22df8aaa7fcc0f9ff8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/zephyr-7b-sft-full-spin-iter1", + "Average \u2b06\ufe0f": 62.86, + "ARC": 65.87, + "HellaSwag": 85.44, + "MMLU": 60.95, + "TruthfulQA": 57.39, + "Winogrande": 76.64, + "GSM8K": 30.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9257b6484010acf5eed7e77ff787264b49c1a923", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/zephyr-7b-sft-full-SPIN-iter1", + "Average \u2b06\ufe0f": 62.86, + "ARC": 65.87, + "HellaSwag": 85.44, + "MMLU": 60.95, + "TruthfulQA": 57.39, + "Winogrande": 76.64, + "GSM8K": 30.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d8569aea49f28131ca3d319da343da0777ed4161", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jefferylovely\/AthenaImaniMaven", + "Average \u2b06\ufe0f": 62.85, + "ARC": 62.63, + "HellaSwag": 84.65, + "MMLU": 59.05, + "TruthfulQA": 58.58, + "Winogrande": 77.19, + "GSM8K": 35.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f10a7d6055955eb40424dcac8a76658a11224c86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aari1995\/germeo-7b-laser", + "Average \u2b06\ufe0f": 62.82, + "ARC": 60.75, + "HellaSwag": 82.81, + "MMLU": 60.57, + "TruthfulQA": 53.83, + "Winogrande": 75.61, + "GSM8K": 43.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "b7577f83a0af27e1a380efce4f993c25c33d8b33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "upaya07\/Birbal-7B-V1", + "Average \u2b06\ufe0f": 62.82, + "ARC": 62.88, + "HellaSwag": 84.88, + "MMLU": 63.71, + "TruthfulQA": 45.46, + "Winogrande": 78.53, + "GSM8K": 41.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6623e1ec77f20f7c152e86e99b49e501d0133b13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/MelangeA-70b", + "Average \u2b06\ufe0f": 62.82, + "ARC": 71.25, + "HellaSwag": 87.3, + "MMLU": 70.56, + "TruthfulQA": 60.61, + "Winogrande": 81.53, + "GSM8K": 5.69, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "d48cf79d1ead50154b1e70120779ae91bc5fafb4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/travel-mistral-7B-16b-base", + "Average \u2b06\ufe0f": 62.82, + "ARC": 61.43, + "HellaSwag": 83.51, + "MMLU": 62.55, + "TruthfulQA": 53.23, + "Winogrande": 78.53, + "GSM8K": 37.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ba3ff8d628f9c2039ce88a6f2c5c06ea35580230", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-mixtral-7bx8-v17.3-32k", + "Average \u2b06\ufe0f": 62.81, + "ARC": 64.51, + "HellaSwag": 66.96, + "MMLU": 70.0, + "TruthfulQA": 59.14, + "Winogrande": 68.11, + "GSM8K": 48.14, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "05910dc7113c255ad115d36ca27e9d3f533d9181", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "vince62s\/phi-2-psy", + "Average \u2b06\ufe0f": 62.8, + "ARC": 60.84, + "HellaSwag": 75.52, + "MMLU": 57.57, + "TruthfulQA": 48.22, + "Winogrande": 75.45, + "GSM8K": 59.21, + "Type": "base merges and moerges", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "9a9a31679e597e92dd02af20e94e4cd7fb211112", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "gagan3012\/Multilingual-mistral", + "Average \u2b06\ufe0f": 62.79, + "ARC": 62.29, + "HellaSwag": 81.76, + "MMLU": 61.38, + "TruthfulQA": 55.53, + "Winogrande": 75.53, + "GSM8K": 40.26, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "692fa323156e1d2a81e43adc0dd032700dde7a1a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "huggyllama\/llama-65b", + "Average \u2b06\ufe0f": 62.79, + "ARC": 63.48, + "HellaSwag": 86.09, + "MMLU": 63.93, + "TruthfulQA": 43.43, + "Winogrande": 82.56, + "GSM8K": 37.23, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 65.29, + "Hub \u2764\ufe0f": 68.0, + "Available on the hub": true, + "Model sha": "49707c5313d34d1c5a846e29cf2a2a650c22c8ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/neural-chat-7b-v3-1-dare-0.85", + "Average \u2b06\ufe0f": 62.74, + "ARC": 61.95, + "HellaSwag": 83.84, + "MMLU": 64.43, + "TruthfulQA": 44.9, + "Winogrande": 79.16, + "GSM8K": 42.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3c15d3e2a7790e45501e105daed5eb88b665ceef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Faradaylab\/ARIA-70B-V3", + "Average \u2b06\ufe0f": 62.73, + "ARC": 63.91, + "HellaSwag": 86.21, + "MMLU": 64.75, + "TruthfulQA": 51.32, + "Winogrande": 82.08, + "GSM8K": 28.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6e7fdcd20626786dd744ea86c664a3c088ced39f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mlinmg\/SG-Raccoon-Yi-200k-2.0", + "Average \u2b06\ufe0f": 62.72, + "ARC": 62.54, + "HellaSwag": 80.26, + "MMLU": 73.29, + "TruthfulQA": 53.21, + "Winogrande": 76.32, + "GSM8K": 30.71, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 55.59, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "986706415fcb2118f35626dbc12e054457ec9ad3", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Fredithefish\/MadMix-v0.2", + "Average \u2b06\ufe0f": 62.72, + "ARC": 64.85, + "HellaSwag": 83.54, + "MMLU": 64.02, + "TruthfulQA": 55.79, + "Winogrande": 77.35, + "GSM8K": 30.78, + "Type": "", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "69a3c98c23938a9370c62ae43894eb7723de97dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Mistral-NeuralDPO", + "Average \u2b06\ufe0f": 62.72, + "ARC": 66.04, + "HellaSwag": 84.69, + "MMLU": 63.92, + "TruthfulQA": 43.27, + "Winogrande": 79.64, + "GSM8K": 38.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1b8ecfe53f090c6c7dffcb46a3fade8087ab0767", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "amu\/r-zephyr-7b-beta-qlora", + "Average \u2b06\ufe0f": 62.7, + "ARC": 63.05, + "HellaSwag": 85.38, + "MMLU": 63.1, + "TruthfulQA": 46.32, + "Winogrande": 79.32, + "GSM8K": 39.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3948f437f08ebb9f0bc7da37cdead0cc3dd7a562", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hercules-2.0-Mistral-7B", + "Average \u2b06\ufe0f": 62.69, + "ARC": 61.09, + "HellaSwag": 83.69, + "MMLU": 63.47, + "TruthfulQA": 43.97, + "Winogrande": 79.48, + "GSM8K": 44.43, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "3463e3123ea32116e5aca1a4498c1f8fb5109244", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "chargoddard\/internlm2-base-20b-llama", + "Average \u2b06\ufe0f": 62.69, + "ARC": 63.05, + "HellaSwag": 82.11, + "MMLU": 63.97, + "TruthfulQA": 43.97, + "Winogrande": 78.22, + "GSM8K": 44.81, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.86, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ab228139d9da36acb908b8ff7732b456dfdd57e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "intervitens\/internlm2-base-20b-llama", + "Average \u2b06\ufe0f": 62.69, + "ARC": 62.97, + "HellaSwag": 82.15, + "MMLU": 63.78, + "TruthfulQA": 44.11, + "Winogrande": 78.22, + "GSM8K": 44.88, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "507aadd23e803c4a2204d3d34c7008c6603a86db", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sr5434\/CodegebraGPT-10b", + "Average \u2b06\ufe0f": 62.68, + "ARC": 59.81, + "HellaSwag": 83.42, + "MMLU": 60.2, + "TruthfulQA": 46.57, + "Winogrande": 80.98, + "GSM8K": 45.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "263f3e4c48d6fb001cd556010ee50a0b6918b8cb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/guanaco-65B-HF", + "Average \u2b06\ufe0f": 62.67, + "ARC": 65.44, + "HellaSwag": 86.47, + "MMLU": 62.92, + "TruthfulQA": 52.81, + "Winogrande": 82.4, + "GSM8K": 26.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": true, + "Model sha": "7f83ae526f8b83705ca8434535da8fd8c692f9d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dball\/zephyr-7b-dpo-qlora-no-sft", + "Average \u2b06\ufe0f": 62.67, + "ARC": 62.46, + "HellaSwag": 84.5, + "MMLU": 64.02, + "TruthfulQA": 44.25, + "Winogrande": 79.16, + "GSM8K": 41.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "571698d74a5b4445015cb9c4a3dbe655e96cfcab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-XS-v1-3-yarn-128K", + "Average \u2b06\ufe0f": 62.66, + "ARC": 61.09, + "HellaSwag": 82.95, + "MMLU": 62.15, + "TruthfulQA": 50.13, + "Winogrande": 74.43, + "GSM8K": 45.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "0f5977a5d2fa791359dc92eb1574b6112e709cad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Metis-0.5", + "Average \u2b06\ufe0f": 62.65, + "ARC": 62.63, + "HellaSwag": 83.77, + "MMLU": 62.16, + "TruthfulQA": 49.33, + "Winogrande": 75.14, + "GSM8K": 42.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "87df101c3909e6bc2b22e237d92f74118ab1909c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/llama-2-70b-IA3-guanaco", + "Average \u2b06\ufe0f": 62.61, + "ARC": 68.52, + "HellaSwag": 85.67, + "MMLU": 67.03, + "TruthfulQA": 43.47, + "Winogrande": 82.24, + "GSM8K": 28.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "e3230df22d065b6699096494d1151fa337dde9e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "upaya07\/Birbal-7B-V1", + "Average \u2b06\ufe0f": 62.6, + "ARC": 62.8, + "HellaSwag": 84.83, + "MMLU": 63.59, + "TruthfulQA": 45.34, + "Winogrande": 78.77, + "GSM8K": 40.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6623e1ec77f20f7c152e86e99b49e501d0133b13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-70b-gpt4-2.0", + "Average \u2b06\ufe0f": 62.6, + "ARC": 68.6, + "HellaSwag": 87.53, + "MMLU": 69.37, + "TruthfulQA": 48.52, + "Winogrande": 83.9, + "GSM8K": 17.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "other", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "f16526d9bb814dc10adc911f94e8c7a520beb5b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/VicUnlocked-alpaca-65B-QLoRA-fp16", + "Average \u2b06\ufe0f": 62.58, + "ARC": 65.61, + "HellaSwag": 85.15, + "MMLU": 63.13, + "TruthfulQA": 52.47, + "Winogrande": 81.29, + "GSM8K": 27.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "6cdacfda96970aa144e316b108ab9bc17c99a573", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fzzhang\/mistralv1_gsm8k_merged_s", + "Average \u2b06\ufe0f": 62.57, + "ARC": 62.03, + "HellaSwag": 83.95, + "MMLU": 61.66, + "TruthfulQA": 42.43, + "Winogrande": 77.66, + "GSM8K": 47.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d2c604a23f608864c60c8cd3de29ce9ff336e8e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bartowski\/internlm2-chat-20b-llama", + "Average \u2b06\ufe0f": 62.56, + "ARC": 63.65, + "HellaSwag": 82.58, + "MMLU": 66.89, + "TruthfulQA": 48.74, + "Winogrande": 79.56, + "GSM8K": 33.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "L;l;a;m;a;F;o;r;C;a;u;s;a;l;L;M", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.86, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "af7d5521bf657a2323ad437feaa060969244afab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azure99\/blossom-v3_1-mistral-7b", + "Average \u2b06\ufe0f": 62.53, + "ARC": 60.49, + "HellaSwag": 81.71, + "MMLU": 61.0, + "TruthfulQA": 49.51, + "Winogrande": 75.53, + "GSM8K": 46.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d84e28c169a93933829e10f314f1e3e674df9843", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sr5434\/CodegebraGPT-10b", + "Average \u2b06\ufe0f": 62.53, + "ARC": 59.56, + "HellaSwag": 83.45, + "MMLU": 60.07, + "TruthfulQA": 46.53, + "Winogrande": 81.06, + "GSM8K": 44.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "15e64a7f77eba0367eedbaaacb3560351471093b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-XS-v1-3-yarn-128K", + "Average \u2b06\ufe0f": 62.49, + "ARC": 61.6, + "HellaSwag": 82.96, + "MMLU": 62.1, + "TruthfulQA": 50.2, + "Winogrande": 74.74, + "GSM8K": 43.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "72d393d13f1bd26442e59993c57840b91ff6f6fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jikaixuan\/test_merged_model", + "Average \u2b06\ufe0f": 62.42, + "ARC": 61.6, + "HellaSwag": 83.1, + "MMLU": 63.73, + "TruthfulQA": 48.65, + "Winogrande": 78.45, + "GSM8K": 38.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "611ec6f78292124008a276ce5c2723e53d31a1e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zardos\/Kant-Test-0.1-Mistral-7B", + "Average \u2b06\ufe0f": 62.42, + "ARC": 62.37, + "HellaSwag": 82.84, + "MMLU": 63.38, + "TruthfulQA": 49.62, + "Winogrande": 78.3, + "GSM8K": 37.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5989100fa82aaab0db2f8ed3e37a446126050ef9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "meta-llama\/Llama-2-70b-chat-hf", + "Average \u2b06\ufe0f": 62.4, + "ARC": 64.59, + "HellaSwag": 85.88, + "MMLU": 63.91, + "TruthfulQA": 52.8, + "Winogrande": 80.51, + "GSM8K": 26.69, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 1988.0, + "Available on the hub": false, + "Model sha": "7f54101c0fbb67a8143ca23eb8bd09b71f269c74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SCE\/Mistral-7B-math-ia3-tuned", + "Average \u2b06\ufe0f": 62.39, + "ARC": 57.25, + "HellaSwag": 80.79, + "MMLU": 59.83, + "TruthfulQA": 58.07, + "Winogrande": 76.56, + "GSM8K": 41.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "49e50484f55d4d588f57b9d61becfffd6d5eaffe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/test0", + "Average \u2b06\ufe0f": 62.37, + "ARC": 63.65, + "HellaSwag": 84.44, + "MMLU": 61.01, + "TruthfulQA": 50.48, + "Winogrande": 77.98, + "GSM8K": 36.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e90506303f046ebe6da9d8b41489a7365b455a06", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/zephyr-7b-sft-full-SPIN-iter0", + "Average \u2b06\ufe0f": 62.37, + "ARC": 63.65, + "HellaSwag": 84.44, + "MMLU": 61.01, + "TruthfulQA": 50.48, + "Winogrande": 77.98, + "GSM8K": 36.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "d457f58ca73bd5540dc4e12b70315e4464ea138c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "willyninja30\/ARIA-70B-French", + "Average \u2b06\ufe0f": 62.37, + "ARC": 64.51, + "HellaSwag": 85.87, + "MMLU": 63.88, + "TruthfulQA": 52.8, + "Winogrande": 80.51, + "GSM8K": 26.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d8580d360c51e71fddd27897445e2aa9d1888585", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "gagan3012\/Multirial", + "Average \u2b06\ufe0f": 62.37, + "ARC": 63.23, + "HellaSwag": 79.57, + "MMLU": 61.01, + "TruthfulQA": 54.7, + "Winogrande": 75.3, + "GSM8K": 40.41, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0bf35a998ce26287916c9d1e0575d5f15e6ae0df", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hercules-3.0-Mistral-7B", + "Average \u2b06\ufe0f": 62.36, + "ARC": 61.26, + "HellaSwag": 83.43, + "MMLU": 63.68, + "TruthfulQA": 43.42, + "Winogrande": 79.48, + "GSM8K": 42.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "e9ab8a23f6c641729762f352014c66650b033a71", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "karakuri-ai\/karakuri-lm-70b-chat-v0.1", + "Average \u2b06\ufe0f": 62.36, + "ARC": 61.52, + "HellaSwag": 83.13, + "MMLU": 59.35, + "TruthfulQA": 51.39, + "Winogrande": 78.37, + "GSM8K": 40.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 69.2, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "2646170ac2788259d258de8d16c563e36efce299", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-65b-gpt4-1.2", + "Average \u2b06\ufe0f": 62.36, + "ARC": 65.87, + "HellaSwag": 86.08, + "MMLU": 63.37, + "TruthfulQA": 52.72, + "Winogrande": 79.56, + "GSM8K": 26.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "50ab86e198e1c82ec81aefc628f23501c101d390", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/zephyr-7b-alpha-dare-0.85", + "Average \u2b06\ufe0f": 62.35, + "ARC": 61.18, + "HellaSwag": 83.67, + "MMLU": 64.3, + "TruthfulQA": 44.41, + "Winogrande": 78.45, + "GSM8K": 42.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "afe35301593b4ce2e7b5d1696066724ef1f802eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "huseyinatahaninan\/phi-2-dpo", + "Average \u2b06\ufe0f": 62.33, + "ARC": 63.05, + "HellaSwag": 76.36, + "MMLU": 58.46, + "TruthfulQA": 45.35, + "Winogrande": 74.03, + "GSM8K": 56.71, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e23c721e850052435d5b0c1c664432a11bbbd26e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Half-NSFW_Noromaid-7b", + "Average \u2b06\ufe0f": 62.32, + "ARC": 62.8, + "HellaSwag": 84.82, + "MMLU": 63.76, + "TruthfulQA": 46.05, + "Winogrande": 78.06, + "GSM8K": 38.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "378e5fb671d593432ce6c7ddc19ac8e04a490df8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "UCLA-AGI\/zephyr-7b-sft-full-SPIN-iter0", + "Average \u2b06\ufe0f": 62.32, + "ARC": 63.57, + "HellaSwag": 84.43, + "MMLU": 61.28, + "TruthfulQA": 50.34, + "Winogrande": 77.98, + "GSM8K": 36.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "d457f58ca73bd5540dc4e12b70315e4464ea138c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/mistral-7b-alpaca-sft", + "Average \u2b06\ufe0f": 62.29, + "ARC": 61.69, + "HellaSwag": 83.56, + "MMLU": 61.65, + "TruthfulQA": 53.59, + "Winogrande": 77.19, + "GSM8K": 36.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a23b6bcdff99735543644928f7fa085a8bab51bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "pinkyponky\/Mistral-7B-Instruct-sft-tuned-v0.2", + "Average \u2b06\ufe0f": 62.29, + "ARC": 58.02, + "HellaSwag": 79.26, + "MMLU": 58.78, + "TruthfulQA": 50.45, + "Winogrande": 76.87, + "GSM8K": 50.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "26b1b06ca6ee8db77d915e0ec685b3e999a226d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BlouseJury\/Mistral-7B-Discord-0.1-DPO", + "Average \u2b06\ufe0f": 62.29, + "ARC": 63.23, + "HellaSwag": 83.27, + "MMLU": 62.62, + "TruthfulQA": 55.28, + "Winogrande": 78.93, + "GSM8K": 30.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "3fde20529c9b2e25c9cb7a7a28795410e0b4ac21", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fzzhang\/mistralv1_gsm8k_merged", + "Average \u2b06\ufe0f": 62.28, + "ARC": 61.35, + "HellaSwag": 83.11, + "MMLU": 63.04, + "TruthfulQA": 39.55, + "Winogrande": 78.61, + "GSM8K": 47.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b9cb1edd3a535cabc500ce9fb81d98bbfed0b047", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abdulrahman-nuzha\/finetuned-Mistral-7B-Instruct-v0.2-5000-v2.0", + "Average \u2b06\ufe0f": 62.27, + "ARC": 59.3, + "HellaSwag": 82.65, + "MMLU": 58.45, + "TruthfulQA": 59.54, + "Winogrande": 77.66, + "GSM8K": 36.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b32cd037f8c83d08da8a5e593d3cc29de090af1a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vmajor\/Orca2-13B-selfmerge-26B", + "Average \u2b06\ufe0f": 62.24, + "ARC": 60.84, + "HellaSwag": 79.84, + "MMLU": 60.32, + "TruthfulQA": 56.38, + "Winogrande": 76.87, + "GSM8K": 39.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "ms-pl", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "46cdde5be7e3c48ada1bd3143ad593eecfb641e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vmajor\/Orca2-13B-selfmerge-39B", + "Average \u2b06\ufe0f": 62.24, + "ARC": 60.84, + "HellaSwag": 79.84, + "MMLU": 60.32, + "TruthfulQA": 56.38, + "Winogrande": 76.87, + "GSM8K": 39.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "ms-pl", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7a9e6775716a3947d0e40842b5d61753bc0551ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-7B-v1.4", + "Average \u2b06\ufe0f": 62.19, + "ARC": 60.41, + "HellaSwag": 82.87, + "MMLU": 60.98, + "TruthfulQA": 51.88, + "Winogrande": 74.82, + "GSM8K": 42.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "53a5249ee9e5b2327de81f09c26a4577dea9260b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "andysalerno\/rainbowfish-v7", + "Average \u2b06\ufe0f": 62.18, + "ARC": 61.95, + "HellaSwag": 82.52, + "MMLU": 63.26, + "TruthfulQA": 49.78, + "Winogrande": 78.14, + "GSM8K": 37.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "896039c526d6d5977fb7943743666b4dc2563b3e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Radu1999\/Mistral-Instruct-Ukrainian-SFT", + "Average \u2b06\ufe0f": 62.17, + "ARC": 57.85, + "HellaSwag": 83.12, + "MMLU": 60.95, + "TruthfulQA": 54.14, + "Winogrande": 77.51, + "GSM8K": 39.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "26d1f9e8efdd4a471698cd404ac5d7415e8ac80e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/Orca-2-13b-f16", + "Average \u2b06\ufe0f": 62.14, + "ARC": 60.67, + "HellaSwag": 79.81, + "MMLU": 60.37, + "TruthfulQA": 56.41, + "Winogrande": 76.64, + "GSM8K": 38.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b29c52ea0757c460e83592e55ea89e016cef3549", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v4-qwen1_5-7b", + "Average \u2b06\ufe0f": 62.11, + "ARC": 54.44, + "HellaSwag": 76.11, + "MMLU": 60.43, + "TruthfulQA": 53.69, + "Winogrande": 71.27, + "GSM8K": 56.71, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eb86db987cf43f8d3ca023e2ea3e467eb24fa61b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fionazhang\/mistral-experiment-6-merge", + "Average \u2b06\ufe0f": 62.1, + "ARC": 63.82, + "HellaSwag": 84.25, + "MMLU": 62.91, + "TruthfulQA": 44.99, + "Winogrande": 77.98, + "GSM8K": 38.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2a6525f8b5c6d02ef78e716ccb37c6ef1bb1a26d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hercules-3.1-Mistral-7B", + "Average \u2b06\ufe0f": 62.09, + "ARC": 61.18, + "HellaSwag": 83.55, + "MMLU": 63.65, + "TruthfulQA": 42.83, + "Winogrande": 79.01, + "GSM8K": 42.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "ba7176142c6d3e5b8735b79f68552f16634bbbe7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenLemur\/lemur-70b-v1", + "Average \u2b06\ufe0f": 62.07, + "ARC": 64.33, + "HellaSwag": 85.72, + "MMLU": 65.85, + "TruthfulQA": 44.78, + "Winogrande": 83.03, + "GSM8K": 28.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 45.0, + "Available on the hub": true, + "Model sha": "74432ae16ef50207fe17fb88b2f1c1d32ef3b481", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-mistral-dolphin-orca-platypus-samantha-7b-dare-0.85", + "Average \u2b06\ufe0f": 62.06, + "ARC": 61.69, + "HellaSwag": 83.85, + "MMLU": 64.43, + "TruthfulQA": 43.13, + "Winogrande": 78.93, + "GSM8K": 40.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7a3def1c382793d2b12741896302c31a471b6d1d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andrijdavid\/Macaroni-v2-7b", + "Average \u2b06\ufe0f": 62.05, + "ARC": 67.15, + "HellaSwag": 83.84, + "MMLU": 61.29, + "TruthfulQA": 67.07, + "Winogrande": 79.56, + "GSM8K": 13.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b611850983ecc381c68b4853b1e2aa570ce22330", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/solarized-13B-dpo", + "Average \u2b06\ufe0f": 62.05, + "ARC": 62.71, + "HellaSwag": 81.82, + "MMLU": 59.12, + "TruthfulQA": 66.25, + "Winogrande": 76.01, + "GSM8K": 26.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.48, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a7d6f68c292320161c563bd24232907b6d5f9b21", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Aeala\/Alpaca-elina-65b", + "Average \u2b06\ufe0f": 62.03, + "ARC": 65.27, + "HellaSwag": 85.75, + "MMLU": 63.42, + "TruthfulQA": 47.32, + "Winogrande": 81.37, + "GSM8K": 29.04, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "51ce30a69b3c3363c8cfcd6395bf1df974ba2977", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/PlatYi-34B-200K-Q", + "Average \u2b06\ufe0f": 62.0, + "ARC": 63.91, + "HellaSwag": 83.52, + "MMLU": 75.19, + "TruthfulQA": 44.21, + "Winogrande": 81.06, + "GSM8K": 24.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0f58c270f8f3b82523799dcfd7080b857850bd77", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "athirdpath\/Iambe-20b-DARE-v2", + "Average \u2b06\ufe0f": 61.99, + "ARC": 62.8, + "HellaSwag": 84.53, + "MMLU": 60.45, + "TruthfulQA": 53.85, + "Winogrande": 77.03, + "GSM8K": 33.28, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "02bd8edd30a5ddd1eede94c19a6ae160842a2f9f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishek\/zephyr-beta-math", + "Average \u2b06\ufe0f": 61.99, + "ARC": 56.66, + "HellaSwag": 81.26, + "MMLU": 57.24, + "TruthfulQA": 44.83, + "Winogrande": 75.53, + "GSM8K": 56.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "dd3d070a104d8b36ba98d14a485d88fa95aaab63", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-7B-v3.0", + "Average \u2b06\ufe0f": 61.99, + "ARC": 62.46, + "HellaSwag": 83.79, + "MMLU": 63.9, + "TruthfulQA": 43.85, + "Winogrande": 77.9, + "GSM8K": 40.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "93c2e8b8055b42779f2b68059ebe38af6f2789c4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Novocoders\/Mistral-NeuralDPO-v0.5", + "Average \u2b06\ufe0f": 61.98, + "ARC": 65.44, + "HellaSwag": 84.66, + "MMLU": 62.56, + "TruthfulQA": 42.43, + "Winogrande": 80.27, + "GSM8K": 36.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e37831e09cff71bfa2659430bbfa1a210729ea5a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "microsoft\/Orca-2-13b", + "Average \u2b06\ufe0f": 61.98, + "ARC": 60.92, + "HellaSwag": 79.85, + "MMLU": 60.3, + "TruthfulQA": 56.42, + "Winogrande": 76.56, + "GSM8K": 37.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 624.0, + "Available on the hub": true, + "Model sha": "2539ff53e6baa4cc603774ad5a2d646f4041ea4e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/MelangeC-70b", + "Average \u2b06\ufe0f": 61.96, + "ARC": 71.67, + "HellaSwag": 87.6, + "MMLU": 70.37, + "TruthfulQA": 58.13, + "Winogrande": 83.98, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e54a2b924dec135f3fa2373933ab8485178cde1b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HuggingFaceH4\/zephyr-7b-beta", + "Average \u2b06\ufe0f": 61.95, + "ARC": 62.03, + "HellaSwag": 84.36, + "MMLU": 61.07, + "TruthfulQA": 57.45, + "Winogrande": 77.74, + "GSM8K": 29.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1312.0, + "Available on the hub": true, + "Model sha": "8af01af3d4f9dc9b962447180d6d0f8c5315da86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/zephyr-7b-truthy", + "Average \u2b06\ufe0f": 61.93, + "ARC": 60.75, + "HellaSwag": 84.64, + "MMLU": 59.53, + "TruthfulQA": 63.31, + "Winogrande": 77.9, + "GSM8K": 25.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f2f46ce1de3773a3d90b7006e0d6aa48edd884c5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Faradaylab\/ARIA-70B-V2", + "Average \u2b06\ufe0f": 61.93, + "ARC": 62.12, + "HellaSwag": 85.68, + "MMLU": 63.49, + "TruthfulQA": 49.8, + "Winogrande": 81.69, + "GSM8K": 28.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "2bf026af438d522268533484a85a3e54178e7809", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HenryJJ\/dolphin-2.6-mistral-7b-dpo-orca-v1", + "Average \u2b06\ufe0f": 61.92, + "ARC": 66.04, + "HellaSwag": 84.62, + "MMLU": 62.28, + "TruthfulQA": 59.97, + "Winogrande": 78.3, + "GSM8K": 20.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3b711027ce55f180f050729f08fe7060e4834e87", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "HenryJJ\/dolphin-2.6-mistral-7b-dpo-orca", + "Average \u2b06\ufe0f": 61.92, + "ARC": 66.04, + "HellaSwag": 84.62, + "MMLU": 62.28, + "TruthfulQA": 59.97, + "Winogrande": 78.3, + "GSM8K": 20.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "19c3ad67276aa90341e46e8b0b72e6bf79984153", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "spmurrayzzz\/Mistral-Syndicate-7B", + "Average \u2b06\ufe0f": 61.9, + "ARC": 60.84, + "HellaSwag": 82.91, + "MMLU": 60.83, + "TruthfulQA": 43.71, + "Winogrande": 78.61, + "GSM8K": 44.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d95d34db5d0aa50fd3b3594d1632c6ce69937243", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "andysalerno\/rainbowfish-7B-v10", + "Average \u2b06\ufe0f": 61.88, + "ARC": 61.18, + "HellaSwag": 82.33, + "MMLU": 63.26, + "TruthfulQA": 49.45, + "Winogrande": 78.06, + "GSM8K": 37.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "22a4cd7ecfdafb957ba2233b9c06fccd70663cfa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "proto-llm\/uniwiz-7B-v0.1", + "Average \u2b06\ufe0f": 61.87, + "ARC": 61.77, + "HellaSwag": 84.16, + "MMLU": 64.16, + "TruthfulQA": 44.96, + "Winogrande": 78.85, + "GSM8K": 37.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5ad4b3b5b2648cf841b39fbe8254a1c1fee832f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Winterreise-m7", + "Average \u2b06\ufe0f": 61.86, + "ARC": 61.26, + "HellaSwag": 83.84, + "MMLU": 63.85, + "TruthfulQA": 45.55, + "Winogrande": 79.08, + "GSM8K": 37.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "418129599bdd914f275a44ce9ce5a111c5917b3c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/Noromaid-7b-v0.2", + "Average \u2b06\ufe0f": 61.86, + "ARC": 62.12, + "HellaSwag": 84.92, + "MMLU": 63.1, + "TruthfulQA": 46.09, + "Winogrande": 78.22, + "GSM8K": 36.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "bc35358ec19cf0335642228538a83bb306c0e074", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "AA051611\/A0118", + "Average \u2b06\ufe0f": 61.84, + "ARC": 59.22, + "HellaSwag": 83.79, + "MMLU": 68.28, + "TruthfulQA": 55.79, + "Winogrande": 77.58, + "GSM8K": 26.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6bc6bac459c7a8b679281db8663a96e2a1f3ce2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/bagel-8x7b-v0.2", + "Average \u2b06\ufe0f": 61.83, + "ARC": 68.26, + "HellaSwag": 86.32, + "MMLU": 70.4, + "TruthfulQA": 60.03, + "Winogrande": 81.29, + "GSM8K": 4.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "614649ce0bd9a03fd24963de70655e5f8d4354b0", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "dfurman\/Mistral-7B-Instruct-v0.2", + "Average \u2b06\ufe0f": 61.79, + "ARC": 60.15, + "HellaSwag": 82.79, + "MMLU": 60.07, + "TruthfulQA": 56.06, + "Winogrande": 76.87, + "GSM8K": 34.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "322faff8bb0c72b772762de7635f5aea9864a24a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/Noromaid-7b-v0.2", + "Average \u2b06\ufe0f": 61.78, + "ARC": 62.03, + "HellaSwag": 84.97, + "MMLU": 62.99, + "TruthfulQA": 46.07, + "Winogrande": 78.37, + "GSM8K": 36.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "bc35358ec19cf0335642228538a83bb306c0e074", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jikaixuan\/test", + "Average \u2b06\ufe0f": 61.76, + "ARC": 62.29, + "HellaSwag": 84.42, + "MMLU": 61.07, + "TruthfulQA": 57.51, + "Winogrande": 78.06, + "GSM8K": 27.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e63792701d6136288b95c9c8f24c0030ff5698b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jikaixuan\/test_model", + "Average \u2b06\ufe0f": 61.76, + "ARC": 62.29, + "HellaSwag": 84.42, + "MMLU": 61.07, + "TruthfulQA": 57.51, + "Winogrande": 78.06, + "GSM8K": 27.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2e9d6998ce40ffb43ba1d8636a84bf38bf922892", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen1.5-7B", + "Average \u2b06\ufe0f": 61.76, + "ARC": 54.18, + "HellaSwag": 78.51, + "MMLU": 61.97, + "TruthfulQA": 51.08, + "Winogrande": 71.27, + "GSM8K": 53.53, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "e52fa2ef47411cc8bc9f752d1d8d9072b37742e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "spmurrayzzz\/Mistral-Syndicate-7B", + "Average \u2b06\ufe0f": 61.74, + "ARC": 60.84, + "HellaSwag": 82.88, + "MMLU": 60.52, + "TruthfulQA": 43.73, + "Winogrande": 78.45, + "GSM8K": 44.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d95d34db5d0aa50fd3b3594d1632c6ce69937243", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "AIJUUD\/juud-Mistral-7B", + "Average \u2b06\ufe0f": 61.72, + "ARC": 66.72, + "HellaSwag": 85.0, + "MMLU": 63.38, + "TruthfulQA": 54.12, + "Winogrande": 77.98, + "GSM8K": 23.12, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "0e51981702ee1f4c3162915e4ac5233591821af8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "huangyt\/Mistral-7B-v0.1-Open-Platypus_2.5w-r16-gate_up_down", + "Average \u2b06\ufe0f": 61.71, + "ARC": 61.26, + "HellaSwag": 83.19, + "MMLU": 63.87, + "TruthfulQA": 45.44, + "Winogrande": 77.35, + "GSM8K": 39.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "77f7bf749a6c4561b5364b291152b54ba19a59fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Metabird-7b-DPO", + "Average \u2b06\ufe0f": 61.7, + "ARC": 65.96, + "HellaSwag": 86.29, + "MMLU": 64.46, + "TruthfulQA": 60.3, + "Winogrande": 81.37, + "GSM8K": 11.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5c235db8dcfb564784e6f328ded93205475667ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "fhai50032\/SamChat", + "Average \u2b06\ufe0f": 61.68, + "ARC": 62.2, + "HellaSwag": 81.88, + "MMLU": 59.7, + "TruthfulQA": 52.89, + "Winogrande": 72.14, + "GSM8K": 41.24, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a8b9d9019c12775ce126b49bb25ef63b7cb05a93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Gryphe\/MythoMist-7b", + "Average \u2b06\ufe0f": 61.67, + "ARC": 65.87, + "HellaSwag": 83.55, + "MMLU": 62.32, + "TruthfulQA": 59.98, + "Winogrande": 78.06, + "GSM8K": 20.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 30.0, + "Available on the hub": true, + "Model sha": "3b6c71416d191ab161fd3043117304a10df99716", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NickyNicky\/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2", + "Average \u2b06\ufe0f": 61.65, + "ARC": 60.49, + "HellaSwag": 82.07, + "MMLU": 62.34, + "TruthfulQA": 46.38, + "Winogrande": 78.45, + "GSM8K": 40.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "f01f41dc7c987ad6668931159feaa4469f7dcf3f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "andysalerno\/rainbowfish-v6", + "Average \u2b06\ufe0f": 61.64, + "ARC": 61.95, + "HellaSwag": 82.51, + "MMLU": 62.79, + "TruthfulQA": 48.37, + "Winogrande": 77.9, + "GSM8K": 36.32, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2b62fc1c6f1105c21ec96f958f0d16d2197517cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "athirdpath\/Orca-2-13b-Alpaca-Uncensored", + "Average \u2b06\ufe0f": 61.63, + "ARC": 61.09, + "HellaSwag": 79.27, + "MMLU": 60.13, + "TruthfulQA": 53.59, + "Winogrande": 77.43, + "GSM8K": 38.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "2fdbef532345da9eba9b9f4b8aaef6ea11b664fe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hiyouga\/Qwen-14B-Chat-LLaMAfied", + "Average \u2b06\ufe0f": 61.6, + "ARC": 57.51, + "HellaSwag": 82.11, + "MMLU": 65.57, + "TruthfulQA": 51.99, + "Winogrande": 72.93, + "GSM8K": 39.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 14.17, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "29e92e74dca4a79aa8c2c451287ff97c4dccb323", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Llamix2-MLewd-4x13B", + "Average \u2b06\ufe0f": 61.6, + "ARC": 61.01, + "HellaSwag": 83.17, + "MMLU": 56.32, + "TruthfulQA": 50.35, + "Winogrande": 75.37, + "GSM8K": 43.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 38.5, + "Hub \u2764\ufe0f": 50.0, + "Available on the hub": true, + "Model sha": "19961590ae95ccd9316b13c66098cd61b28a7d5a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Intel\/neural-chat-7b-v3-1", + "Average \u2b06\ufe0f": 61.59, + "ARC": 66.21, + "HellaSwag": 83.64, + "MMLU": 62.37, + "TruthfulQA": 59.65, + "Winogrande": 78.14, + "GSM8K": 19.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 523.0, + "Available on the hub": true, + "Model sha": "3995e9a13d54ce95f0ad55de2eaa92e2dc580174", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Intel\/neural-chat-7b-v3-1", + "Average \u2b06\ufe0f": 61.59, + "ARC": 65.7, + "HellaSwag": 83.54, + "MMLU": 62.12, + "TruthfulQA": 59.48, + "Winogrande": 78.61, + "GSM8K": 20.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 523.0, + "Available on the hub": true, + "Model sha": "af2489cde09e9d2c175622f651875e83824c4b10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "athirdpath\/NSFW_DPO_Noromaid-7b", + "Average \u2b06\ufe0f": 61.59, + "ARC": 62.63, + "HellaSwag": 84.5, + "MMLU": 63.34, + "TruthfulQA": 44.99, + "Winogrande": 78.22, + "GSM8K": 35.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "51b4408a40736e18f69d932cb403811558428378", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HuggingFaceH4\/zephyr-7b-beta", + "Average \u2b06\ufe0f": 61.59, + "ARC": 62.46, + "HellaSwag": 84.35, + "MMLU": 60.7, + "TruthfulQA": 57.83, + "Winogrande": 77.11, + "GSM8K": 27.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1312.0, + "Available on the hub": true, + "Model sha": "0f17b36adfbe7d86ea1c591a9efeeae17b313f48", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Deci\/DeciLM-7B", + "Average \u2b06\ufe0f": 61.55, + "ARC": 59.39, + "HellaSwag": 82.51, + "MMLU": 59.76, + "TruthfulQA": 40.33, + "Winogrande": 79.95, + "GSM8K": 47.38, + "Type": "pretrained", + "Architecture": "DeciLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.04, + "Hub \u2764\ufe0f": 214.0, + "Available on the hub": true, + "Model sha": "b943e32a12bc21df2b8b3c50525c6646acd442bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "tianlinliu0121\/zephyr-7b-dpo-full-beta-0.2", + "Average \u2b06\ufe0f": 61.55, + "ARC": 61.77, + "HellaSwag": 84.04, + "MMLU": 61.79, + "TruthfulQA": 54.72, + "Winogrande": 76.95, + "GSM8K": 30.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "727b63fc1ca6a592072159a7185c22f74cd38480", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/SamChat", + "Average \u2b06\ufe0f": 61.55, + "ARC": 62.03, + "HellaSwag": 81.95, + "MMLU": 59.78, + "TruthfulQA": 52.9, + "Winogrande": 71.98, + "GSM8K": 40.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a8b9d9019c12775ce126b49bb25ef63b7cb05a93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Intel\/neural-chat-7b-v3-1", + "Average \u2b06\ufe0f": 61.54, + "ARC": 66.3, + "HellaSwag": 83.6, + "MMLU": 62.44, + "TruthfulQA": 59.54, + "Winogrande": 77.98, + "GSM8K": 19.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 523.0, + "Available on the hub": true, + "Model sha": "3995e9a13d54ce95f0ad55de2eaa92e2dc580174", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "teknium\/OpenHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 61.52, + "ARC": 64.93, + "HellaSwag": 84.18, + "MMLU": 63.64, + "TruthfulQA": 52.24, + "Winogrande": 78.06, + "GSM8K": 26.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 662.0, + "Available on the hub": true, + "Model sha": "2a54cad766bc90828354db5c4199795aecfd0df1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/DarkSapling-7B-v1.0", + "Average \u2b06\ufe0f": 61.52, + "ARC": 61.6, + "HellaSwag": 82.59, + "MMLU": 62.46, + "TruthfulQA": 45.09, + "Winogrande": 77.19, + "GSM8K": 40.18, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "df6fad2ddb8af14baaffdc731553be7e70cd83e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/SamCoder-TxC", + "Average \u2b06\ufe0f": 61.52, + "ARC": 62.37, + "HellaSwag": 81.93, + "MMLU": 59.68, + "TruthfulQA": 52.37, + "Winogrande": 72.14, + "GSM8K": 40.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "17dcf2e98fa91317316b05f5ff27ae24b31139aa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/Mistral-7B-OpenOrca-lora-merged", + "Average \u2b06\ufe0f": 61.52, + "ARC": 61.77, + "HellaSwag": 83.61, + "MMLU": 64.34, + "TruthfulQA": 42.7, + "Winogrande": 78.53, + "GSM8K": 38.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8a8e4763c3edd0a8e5bb02e4bc865c69a658b428", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/Noromaid-7b-v0.1.1", + "Average \u2b06\ufe0f": 61.49, + "ARC": 62.2, + "HellaSwag": 84.28, + "MMLU": 63.44, + "TruthfulQA": 44.3, + "Winogrande": 77.9, + "GSM8K": 36.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "349a2eb5c61e3e13c2b39d15c7b94f5c31ab6bd5", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/robin-65b-v2-fp16", + "Average \u2b06\ufe0f": 61.48, + "ARC": 61.95, + "HellaSwag": 84.6, + "MMLU": 62.51, + "TruthfulQA": 52.31, + "Winogrande": 80.51, + "GSM8K": 26.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "40edb31ba93045d673735361bc98f56125bbc77b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fionazhang\/fine-tune-mistral-long-merge", + "Average \u2b06\ufe0f": 61.47, + "ARC": 62.88, + "HellaSwag": 83.62, + "MMLU": 63.39, + "TruthfulQA": 43.94, + "Winogrande": 78.93, + "GSM8K": 36.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2675e1e670ebe54c733ed27fb32d8610644eefca", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "walebadr\/Mistral-7B-v0.1-DPO", + "Average \u2b06\ufe0f": 61.47, + "ARC": 61.26, + "HellaSwag": 83.94, + "MMLU": 63.76, + "TruthfulQA": 42.68, + "Winogrande": 78.77, + "GSM8K": 38.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Delta", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bab460c2c68fca377bcc778031d51340104e2dc1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/DarkForest-20B-v1.2", + "Average \u2b06\ufe0f": 61.46, + "ARC": 63.57, + "HellaSwag": 86.42, + "MMLU": 59.77, + "TruthfulQA": 56.31, + "Winogrande": 77.74, + "GSM8K": 24.94, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d38fadc604321e5d4cbaa93b247f939f2f5d5a1d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "teknium\/OpenHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 61.45, + "ARC": 64.93, + "HellaSwag": 84.3, + "MMLU": 63.82, + "TruthfulQA": 52.31, + "Winogrande": 77.9, + "GSM8K": 25.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 662.0, + "Available on the hub": true, + "Model sha": "2a54cad766bc90828354db5c4199795aecfd0df1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fhai50032\/SamCoder-TxC", + "Average \u2b06\ufe0f": 61.44, + "ARC": 62.12, + "HellaSwag": 81.85, + "MMLU": 59.83, + "TruthfulQA": 52.39, + "Winogrande": 72.38, + "GSM8K": 40.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "17dcf2e98fa91317316b05f5ff27ae24b31139aa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "andysalerno\/rainbowfish-7B-v9", + "Average \u2b06\ufe0f": 61.42, + "ARC": 61.77, + "HellaSwag": 82.43, + "MMLU": 63.0, + "TruthfulQA": 48.82, + "Winogrande": 77.66, + "GSM8K": 34.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c1b344f0efaacd2309d22dcbe4358a00bdd50f15", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GritLM\/GritLM-7B", + "Average \u2b06\ufe0f": 61.41, + "ARC": 58.11, + "HellaSwag": 80.97, + "MMLU": 60.29, + "TruthfulQA": 45.86, + "Winogrande": 78.22, + "GSM8K": 45.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "13f00a0e36500c80ce12870ea513846a066004af", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "NeuralNovel\/Ember-7B-v0.1", + "Average \u2b06\ufe0f": 61.39, + "ARC": 68.43, + "HellaSwag": 85.52, + "MMLU": 64.1, + "TruthfulQA": 63.29, + "Winogrande": 82.32, + "GSM8K": 4.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "49f578bccc5884c7e33b7e7ab3a47591373de76c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "osanseviero\/mistral-instruct-moe-experimental", + "Average \u2b06\ufe0f": 61.39, + "ARC": 61.01, + "HellaSwag": 81.55, + "MMLU": 58.22, + "TruthfulQA": 60.4, + "Winogrande": 76.09, + "GSM8K": 31.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e926f4f97f89c54806547df1b65cb1e6f0c6b26e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "fionazhang\/fine-tune-mistral-environment-merge", + "Average \u2b06\ufe0f": 61.39, + "ARC": 62.63, + "HellaSwag": 83.66, + "MMLU": 63.88, + "TruthfulQA": 43.97, + "Winogrande": 78.93, + "GSM8K": 35.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "162b38e3aea3c55fef316ab7f42af3af3a440c07", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "smelborp\/MixtralOrochi8x7B-Alt", + "Average \u2b06\ufe0f": 61.38, + "ARC": 67.92, + "HellaSwag": 86.25, + "MMLU": 70.06, + "TruthfulQA": 64.03, + "Winogrande": 80.03, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2cbe1e99144674ff0570a6a38b75c4666ed16087", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-llama2-13b", + "Average \u2b06\ufe0f": 61.36, + "ARC": 62.03, + "HellaSwag": 81.82, + "MMLU": 58.69, + "TruthfulQA": 55.66, + "Winogrande": 76.01, + "GSM8K": 33.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "c6362c4fc0dc03420e3c08454b2e7689e4e32d3a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "tianlinliu0121\/zephyr-7b-dpo-full-beta-0.2", + "Average \u2b06\ufe0f": 61.36, + "ARC": 61.86, + "HellaSwag": 83.98, + "MMLU": 61.85, + "TruthfulQA": 54.78, + "Winogrande": 76.95, + "GSM8K": 28.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "727b63fc1ca6a592072159a7185c22f74cd38480", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Metis-0.3-merged", + "Average \u2b06\ufe0f": 61.34, + "ARC": 62.2, + "HellaSwag": 84.0, + "MMLU": 62.65, + "TruthfulQA": 59.24, + "Winogrande": 78.14, + "GSM8K": 21.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dbcf2c1f7cbea0bacd756f7d8251b5bb037e28d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Metis-0.4", + "Average \u2b06\ufe0f": 61.34, + "ARC": 62.2, + "HellaSwag": 84.0, + "MMLU": 62.65, + "TruthfulQA": 59.24, + "Winogrande": 78.14, + "GSM8K": 21.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c2b149c7df2806add971b2c2ec27288abc18f312", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/alpaca-lora-65B-HF", + "Average \u2b06\ufe0f": 61.33, + "ARC": 64.85, + "HellaSwag": 85.59, + "MMLU": 63.11, + "TruthfulQA": 45.15, + "Winogrande": 81.22, + "GSM8K": 28.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "113b61b37a2862b950ada68620e57acafbcefe13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "microsoft\/phi-2", + "Average \u2b06\ufe0f": 61.33, + "ARC": 61.09, + "HellaSwag": 75.11, + "MMLU": 58.11, + "TruthfulQA": 44.47, + "Winogrande": 74.35, + "GSM8K": 54.81, + "Type": "pretrained", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 2847.0, + "Available on the hub": true, + "Model sha": "d3186761bf5c4409f7679359284066c25ab668ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "walebadr\/Mistral-7B-v0.1-DPO", + "Average \u2b06\ufe0f": 61.3, + "ARC": 60.32, + "HellaSwag": 83.69, + "MMLU": 64.01, + "TruthfulQA": 43.53, + "Winogrande": 79.01, + "GSM8K": 37.23, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e1fa6fa7e272027d648c92873c06a42064b483ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Deacon-20B", + "Average \u2b06\ufe0f": 61.28, + "ARC": 60.75, + "HellaSwag": 81.74, + "MMLU": 60.7, + "TruthfulQA": 58.49, + "Winogrande": 76.8, + "GSM8K": 29.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 20.09, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dabbb1675c4bfe6fed3fd8fecc7f2d887e697fa7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Metis-0.4", + "Average \u2b06\ufe0f": 61.28, + "ARC": 62.29, + "HellaSwag": 83.91, + "MMLU": 62.7, + "TruthfulQA": 59.2, + "Winogrande": 77.35, + "GSM8K": 22.21, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c2b149c7df2806add971b2c2ec27288abc18f312", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dball\/zephyr-7b-dpo-qlora", + "Average \u2b06\ufe0f": 61.27, + "ARC": 63.82, + "HellaSwag": 84.92, + "MMLU": 62.28, + "TruthfulQA": 44.03, + "Winogrande": 78.61, + "GSM8K": 33.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8fef86af4ca1c140559450cace2fd1839f979020", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NickyNicky\/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3", + "Average \u2b06\ufe0f": 61.26, + "ARC": 60.58, + "HellaSwag": 83.34, + "MMLU": 61.53, + "TruthfulQA": 48.21, + "Winogrande": 77.74, + "GSM8K": 36.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "43abfcab8bf532a2601ed6e61e0c3614272b7df9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "amu\/dpo-phi2", + "Average \u2b06\ufe0f": 61.26, + "ARC": 61.69, + "HellaSwag": 75.13, + "MMLU": 58.1, + "TruthfulQA": 43.99, + "Winogrande": 74.19, + "GSM8K": 54.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "46d19a6f4e37644a426b0a6917959cf4bb388ef1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Phi-2-DPO", + "Average \u2b06\ufe0f": 61.25, + "ARC": 60.75, + "HellaSwag": 75.03, + "MMLU": 57.75, + "TruthfulQA": 44.46, + "Winogrande": 73.64, + "GSM8K": 55.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "f6df7b39876d53893e4f8dcdf50939225b38d08c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "WizardLM\/WizardLM-70B-V1.0", + "Average \u2b06\ufe0f": 61.25, + "ARC": 65.44, + "HellaSwag": 84.41, + "MMLU": 64.05, + "TruthfulQA": 54.81, + "Winogrande": 80.82, + "GSM8K": 17.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 218.0, + "Available on the hub": true, + "Model sha": "6dae38060d70b82dcfe787a612d04aaf0adf0738", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_3.5", + "Average \u2b06\ufe0f": 61.24, + "ARC": 63.91, + "HellaSwag": 84.79, + "MMLU": 64.94, + "TruthfulQA": 46.38, + "Winogrande": 80.58, + "GSM8K": 26.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1051.0, + "Available on the hub": true, + "Model sha": "5b874a33a91d63023055e6cb2d5d86afe883b4ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Minirecord\/Mini_DPO_test02", + "Average \u2b06\ufe0f": 61.23, + "ARC": 59.73, + "HellaSwag": 83.89, + "MMLU": 61.9, + "TruthfulQA": 48.47, + "Winogrande": 78.37, + "GSM8K": 35.03, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cd417467644c4178100083e342bad88a3f968be6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_3.5", + "Average \u2b06\ufe0f": 61.22, + "ARC": 63.82, + "HellaSwag": 84.8, + "MMLU": 64.98, + "TruthfulQA": 46.39, + "Winogrande": 80.74, + "GSM8K": 26.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1051.0, + "Available on the hub": true, + "Model sha": "5b874a33a91d63023055e6cb2d5d86afe883b4ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "robinsmits\/Mistral-Instruct-7B-v0.2-ChatAlpaca", + "Average \u2b06\ufe0f": 61.21, + "ARC": 56.74, + "HellaSwag": 80.82, + "MMLU": 59.1, + "TruthfulQA": 55.86, + "Winogrande": 77.11, + "GSM8K": 37.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "730fe06d2e388636cf59d56d3473239305796fc8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-65b-gpt4-2.0", + "Average \u2b06\ufe0f": 61.2, + "ARC": 66.64, + "HellaSwag": 86.66, + "MMLU": 63.18, + "TruthfulQA": 49.11, + "Winogrande": 80.74, + "GSM8K": 20.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ea4bdd0221f77de9b0343cd8291cbd0fd6033ca8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "huggingface\/llama-65b", + "Average \u2b06\ufe0f": 61.19, + "ARC": 63.48, + "HellaSwag": 86.09, + "MMLU": 63.93, + "TruthfulQA": 43.43, + "Winogrande": 82.56, + "GSM8K": 27.67, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 65.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4ae2e56610e8b9b9a78472708390668e9096b4f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/mistral-7b-slimorcaboros", + "Average \u2b06\ufe0f": 61.18, + "ARC": 63.65, + "HellaSwag": 83.7, + "MMLU": 63.46, + "TruthfulQA": 55.81, + "Winogrande": 77.03, + "GSM8K": 23.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c06e1a6b6c0fe764117f9ec7611ce31e796e602a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-mistral-hermes-code-7b", + "Average \u2b06\ufe0f": 61.16, + "ARC": 59.39, + "HellaSwag": 78.55, + "MMLU": 59.88, + "TruthfulQA": 51.26, + "Winogrande": 77.27, + "GSM8K": 40.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "12afe40d27008de12bb786795229174f3d6ab8d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/jackalope-7b", + "Average \u2b06\ufe0f": 61.16, + "ARC": 63.4, + "HellaSwag": 83.29, + "MMLU": 63.5, + "TruthfulQA": 50.06, + "Winogrande": 78.06, + "GSM8K": 28.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 29.0, + "Available on the hub": true, + "Model sha": "5ba23522319a51d0af23b336a6a83c72ae3780e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mrm8488\/mistral-7b-ft-h4-no_robots_instructions", + "Average \u2b06\ufe0f": 61.16, + "ARC": 60.92, + "HellaSwag": 83.17, + "MMLU": 63.37, + "TruthfulQA": 43.63, + "Winogrande": 78.85, + "GSM8K": 37.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "785446da9a53ceae48795069bf7ccaf46a91a5ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mrm8488\/mistral-7b-ft-h4-no_robots_instructions", + "Average \u2b06\ufe0f": 61.16, + "ARC": 60.92, + "HellaSwag": 83.24, + "MMLU": 63.74, + "TruthfulQA": 43.64, + "Winogrande": 78.69, + "GSM8K": 36.69, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "785446da9a53ceae48795069bf7ccaf46a91a5ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kwchoi\/DPO_mistral_7b_alpaca_0124_v1", + "Average \u2b06\ufe0f": 61.15, + "ARC": 63.4, + "HellaSwag": 73.2, + "MMLU": 60.51, + "TruthfulQA": 66.76, + "Winogrande": 77.19, + "GSM8K": 25.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "76a91af140da0dcc1733a0bc575e51400ae50fcc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/PlatYi-34B-Llama-Q-v3", + "Average \u2b06\ufe0f": 61.15, + "ARC": 64.33, + "HellaSwag": 84.88, + "MMLU": 74.98, + "TruthfulQA": 51.8, + "Winogrande": 84.21, + "GSM8K": 6.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "2d04b9e3a6c86a718c33e0686c0b5f4e46feb364", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-65b-gpt4-2.0", + "Average \u2b06\ufe0f": 61.14, + "ARC": 66.81, + "HellaSwag": 86.66, + "MMLU": 63.41, + "TruthfulQA": 49.17, + "Winogrande": 80.27, + "GSM8K": 20.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ea4bdd0221f77de9b0343cd8291cbd0fd6033ca8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/mistral-7b-openhermes-2.5-sft", + "Average \u2b06\ufe0f": 61.14, + "ARC": 59.47, + "HellaSwag": 83.2, + "MMLU": 61.32, + "TruthfulQA": 48.52, + "Winogrande": 78.37, + "GSM8K": 35.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3fa4dfd0f915897f6ec559e6095cdcc064ec04df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/dolphin-2.1-mistral-7b", + "Average \u2b06\ufe0f": 61.12, + "ARC": 64.42, + "HellaSwag": 84.92, + "MMLU": 63.32, + "TruthfulQA": 55.56, + "Winogrande": 77.74, + "GSM8K": 20.77, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aa5bd48c8b3040d1155a8fd59328df160aa63680", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zardos\/Kant-Test-0.1-Mistral-7B", + "Average \u2b06\ufe0f": 61.1, + "ARC": 61.77, + "HellaSwag": 82.89, + "MMLU": 62.86, + "TruthfulQA": 49.4, + "Winogrande": 78.53, + "GSM8K": 31.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5989100fa82aaab0db2f8ed3e37a446126050ef9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "pinkyponky\/Mistral-7B-Instruct-Sft-Tuned-V0.2", + "Average \u2b06\ufe0f": 61.08, + "ARC": 57.34, + "HellaSwag": 78.95, + "MMLU": 57.9, + "TruthfulQA": 50.66, + "Winogrande": 76.16, + "GSM8K": 45.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "826783eb0e7f2fc471ab9dfeea59acd112a6ecc3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aihub-app\/ZySec-7B-v1", + "Average \u2b06\ufe0f": 61.08, + "ARC": 63.48, + "HellaSwag": 85.01, + "MMLU": 60.14, + "TruthfulQA": 56.49, + "Winogrande": 78.14, + "GSM8K": 23.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "458f098e529e7ec670a02cc7b75a1a74496984a8", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Dans-DiscountModels\/Dans-07YahooAnswers-7b", + "Average \u2b06\ufe0f": 61.07, + "ARC": 61.52, + "HellaSwag": 83.69, + "MMLU": 63.52, + "TruthfulQA": 41.84, + "Winogrande": 78.53, + "GSM8K": 37.3, + "Type": "", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a9d5e333dd7752b689b97bc7e0cfbd530536a06e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "TencentARC\/Mistral_Pro_8B_v0.1", + "Average \u2b06\ufe0f": 61.06, + "ARC": 62.2, + "HellaSwag": 82.13, + "MMLU": 61.74, + "TruthfulQA": 49.32, + "Winogrande": 76.8, + "GSM8K": 34.19, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 48.0, + "Available on the hub": true, + "Model sha": "acae0ffeb040f1ee654068403a0305263e932ee0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kimwooglae\/AISquare-Instruct-SOLAR-10.7b-v0.5.31", + "Average \u2b06\ufe0f": 61.05, + "ARC": 60.67, + "HellaSwag": 84.2, + "MMLU": 52.86, + "TruthfulQA": 51.35, + "Winogrande": 82.95, + "GSM8K": 34.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a8ef130719aa323afa1fec4ce4ebb9236a1d57a0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "venkycs\/ZySec-7B-Adapter", + "Average \u2b06\ufe0f": 61.04, + "ARC": 63.48, + "HellaSwag": 85.0, + "MMLU": 60.22, + "TruthfulQA": 56.49, + "Winogrande": 78.14, + "GSM8K": 22.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d8245dbd4ff60ff6ab9683eeec6b9c3f9aa9ba64", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-mistral-hermes-code-7b", + "Average \u2b06\ufe0f": 61.01, + "ARC": 59.39, + "HellaSwag": 78.59, + "MMLU": 59.95, + "TruthfulQA": 51.33, + "Winogrande": 77.51, + "GSM8K": 39.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "12afe40d27008de12bb786795229174f3d6ab8d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/dolphin-2.1-mistral-7b", + "Average \u2b06\ufe0f": 61.0, + "ARC": 63.99, + "HellaSwag": 85.0, + "MMLU": 63.44, + "TruthfulQA": 55.57, + "Winogrande": 77.9, + "GSM8K": 20.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aa5bd48c8b3040d1155a8fd59328df160aa63680", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Cartinoe5930\/Llama2_init_Mistral", + "Average \u2b06\ufe0f": 60.98, + "ARC": 60.07, + "HellaSwag": 83.3, + "MMLU": 64.09, + "TruthfulQA": 42.15, + "Winogrande": 78.37, + "GSM8K": 37.91, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e6d5223e089c417e29f56c5750a91e26e8fd5e01", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "mistralai\/Mistral-7B-v0.1", + "Average \u2b06\ufe0f": 60.97, + "ARC": 59.98, + "HellaSwag": 83.31, + "MMLU": 64.16, + "TruthfulQA": 42.15, + "Winogrande": 78.37, + "GSM8K": 37.83, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2845.0, + "Available on the hub": true, + "Model sha": "e836d8f71b5812f9fee65618453dc537c66bd82a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Ichsan2895\/Merak-7B-v5-PROTOTYPE1", + "Average \u2b06\ufe0f": 60.96, + "ARC": 62.2, + "HellaSwag": 82.07, + "MMLU": 60.97, + "TruthfulQA": 45.41, + "Winogrande": 77.9, + "GSM8K": 37.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "abe6a0e87f3f90efddd5f8762188e0d59f60335b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ddyuudd\/mistral_dmbr03_32_sig", + "Average \u2b06\ufe0f": 60.95, + "ARC": 59.98, + "HellaSwag": 83.22, + "MMLU": 61.22, + "TruthfulQA": 47.9, + "Winogrande": 78.06, + "GSM8K": 35.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "860f9cde13943b70bbea7d54975148005efa1b0a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mihaiii\/Pallas-0.5-frankenmerge", + "Average \u2b06\ufe0f": 60.95, + "ARC": 61.77, + "HellaSwag": 80.36, + "MMLU": 67.62, + "TruthfulQA": 54.07, + "Winogrande": 77.74, + "GSM8K": 24.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 36.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b72731a305b62fd9fbcd7c1e99e18d6530600ca9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-falcon-40b-v16.1-4k", + "Average \u2b06\ufe0f": 60.94, + "ARC": 60.58, + "HellaSwag": 83.86, + "MMLU": 56.05, + "TruthfulQA": 50.57, + "Winogrande": 77.82, + "GSM8K": 36.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 41.35, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4531abf8028eea1e94ad33697ff25cc53a6b10c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Reverb\/Mistral-7B-LoreWeaver", + "Average \u2b06\ufe0f": 60.93, + "ARC": 59.98, + "HellaSwag": 83.29, + "MMLU": 64.12, + "TruthfulQA": 42.15, + "Winogrande": 78.37, + "GSM8K": 37.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1e1796b7230cd5ba6146d748a90db15493465f22", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-mistral-moloras-7b", + "Average \u2b06\ufe0f": 60.93, + "ARC": 59.98, + "HellaSwag": 83.29, + "MMLU": 64.12, + "TruthfulQA": 42.15, + "Winogrande": 78.37, + "GSM8K": 37.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "7ef22bee2557aab8a29331653965b3fca22c9a97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "andysalerno\/mistral-sft-v3", + "Average \u2b06\ufe0f": 60.93, + "ARC": 61.35, + "HellaSwag": 82.23, + "MMLU": 63.4, + "TruthfulQA": 48.49, + "Winogrande": 77.66, + "GSM8K": 32.45, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "48beb1e9490732abc6f85d92579d407d85e2cf5d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rizla\/rizla55b", + "Average \u2b06\ufe0f": 60.93, + "ARC": 60.32, + "HellaSwag": 80.42, + "MMLU": 63.54, + "TruthfulQA": 55.59, + "Winogrande": 78.85, + "GSM8K": 26.84, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nd-4.0", + "#Params (B)": 55.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "814ea2c4ddaf2c1b6e4780ff061f899b684a8275", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ddyuudd\/mistral_nucleus09_32_sig", + "Average \u2b06\ufe0f": 60.93, + "ARC": 59.73, + "HellaSwag": 83.14, + "MMLU": 61.42, + "TruthfulQA": 46.37, + "Winogrande": 78.06, + "GSM8K": 36.85, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "49774a1df696b8c8c539f615422518233d21675d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "huseyinatahaninan\/phi-2-instruction", + "Average \u2b06\ufe0f": 60.92, + "ARC": 61.35, + "HellaSwag": 74.73, + "MMLU": 57.77, + "TruthfulQA": 44.96, + "Winogrande": 74.19, + "GSM8K": 52.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "120e8a957f9889b744ae4d5fcf871f57f6bb4264", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-mistral-7b-v17.1-32k", + "Average \u2b06\ufe0f": 60.92, + "ARC": 55.55, + "HellaSwag": 77.95, + "MMLU": 58.29, + "TruthfulQA": 56.06, + "Winogrande": 74.98, + "GSM8K": 42.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.28, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "43f9853350f222b3802d6df332d026d344626aee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CallComply\/openchat-3.5-0106-11b", + "Average \u2b06\ufe0f": 60.91, + "ARC": 63.65, + "HellaSwag": 78.64, + "MMLU": 62.54, + "TruthfulQA": 48.07, + "Winogrande": 78.06, + "GSM8K": 34.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ea960b3343ec36e7f130d45d140fe192acf344b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "upstage\/llama-30b-instruct-2048", + "Average \u2b06\ufe0f": 60.91, + "ARC": 64.93, + "HellaSwag": 84.94, + "MMLU": 61.9, + "TruthfulQA": 56.3, + "Winogrande": 79.56, + "GSM8K": 17.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 103.0, + "Available on the hub": false, + "Model sha": "be44a37814a20e790063086703f570732597887a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HiTZ\/alpaca-lora-65b-en-pt-es-ca", + "Average \u2b06\ufe0f": 60.89, + "ARC": 65.02, + "HellaSwag": 84.88, + "MMLU": 62.19, + "TruthfulQA": 46.06, + "Winogrande": 80.51, + "GSM8K": 26.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aa5bd88bd132925cf2dd5c44eceafdb5ed5e5be4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "AIJUUD\/juud-Mistral-7B-dpo", + "Average \u2b06\ufe0f": 60.89, + "ARC": 66.81, + "HellaSwag": 84.89, + "MMLU": 63.03, + "TruthfulQA": 53.51, + "Winogrande": 78.3, + "GSM8K": 18.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b428f21995854f143b497a36d210276439ae0b87", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "huseyinatahaninan\/phi-2-instruction", + "Average \u2b06\ufe0f": 60.86, + "ARC": 61.09, + "HellaSwag": 74.68, + "MMLU": 57.81, + "TruthfulQA": 45.1, + "Winogrande": 74.82, + "GSM8K": 51.63, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "120e8a957f9889b744ae4d5fcf871f57f6bb4264", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ddyuudd\/mistral_dmbr05_32_sig", + "Average \u2b06\ufe0f": 60.85, + "ARC": 59.9, + "HellaSwag": 83.28, + "MMLU": 60.86, + "TruthfulQA": 49.69, + "Winogrande": 77.19, + "GSM8K": 34.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c09c32edf2cfc817d3aeb010e5a43a530ad5cd62", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/mistral-7b-dolphin-sft", + "Average \u2b06\ufe0f": 60.84, + "ARC": 57.25, + "HellaSwag": 83.01, + "MMLU": 62.59, + "TruthfulQA": 48.91, + "Winogrande": 77.51, + "GSM8K": 35.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7f378f4989df82fee8b4971263aadf9cd2de4bd4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/SlimOpenOrca-Mistral-7B", + "Average \u2b06\ufe0f": 60.84, + "ARC": 62.97, + "HellaSwag": 83.49, + "MMLU": 62.3, + "TruthfulQA": 57.39, + "Winogrande": 77.43, + "GSM8K": 21.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "b0134a7512444dfbb60a2e2d81469a5bbbb18026", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Einstein-7B", + "Average \u2b06\ufe0f": 60.81, + "ARC": 61.6, + "HellaSwag": 84.35, + "MMLU": 62.87, + "TruthfulQA": 42.55, + "Winogrande": 77.51, + "GSM8K": 36.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "36f6450a618d8e665097df2891f30e0dcbcf82ce", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "CalderaAI\/30B-Epsilon", + "Average \u2b06\ufe0f": 60.8, + "ARC": 63.05, + "HellaSwag": 83.59, + "MMLU": 56.89, + "TruthfulQA": 59.03, + "Winogrande": 77.66, + "GSM8K": 24.56, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": false, + "Model sha": "6962638c2b0368ad496af6e20e46e3de97a7772b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-mistral-dolphin-orca-platypus-samantha-7b", + "Average \u2b06\ufe0f": 60.79, + "ARC": 64.33, + "HellaSwag": 84.4, + "MMLU": 63.72, + "TruthfulQA": 52.52, + "Winogrande": 78.37, + "GSM8K": 21.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "d4039b40e842df7f6b8de50532444c8944ea5791", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-65b-gpt4-m2.0", + "Average \u2b06\ufe0f": 60.79, + "ARC": 65.02, + "HellaSwag": 86.35, + "MMLU": 64.37, + "TruthfulQA": 46.66, + "Winogrande": 80.19, + "GSM8K": 22.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fa081d52619b35d7016fb40ce855187d6a8e7e4c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishekchohan\/mistral-7B-forest-v0.1", + "Average \u2b06\ufe0f": 60.79, + "ARC": 60.58, + "HellaSwag": 83.13, + "MMLU": 63.69, + "TruthfulQA": 43.7, + "Winogrande": 78.06, + "GSM8K": 35.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3d07a56be8c1911d1eae3ff5dcaee134e400286c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ddyuudd\/mistral_mbr_32_sig", + "Average \u2b06\ufe0f": 60.79, + "ARC": 59.64, + "HellaSwag": 83.1, + "MMLU": 61.43, + "TruthfulQA": 46.31, + "Winogrande": 78.14, + "GSM8K": 36.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4dcd4403589a336c689164613576b83860f4602c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ddyuudd\/mistral_kmmbr_32_sig", + "Average \u2b06\ufe0f": 60.78, + "ARC": 58.96, + "HellaSwag": 82.84, + "MMLU": 61.39, + "TruthfulQA": 46.2, + "Winogrande": 77.74, + "GSM8K": 37.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "257fbb05778a72079d3ef3b881335c24bc37c3f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddyEA\/openbuddy-llama-30b-v7.1-bf16", + "Average \u2b06\ufe0f": 60.76, + "ARC": 62.37, + "HellaSwag": 82.29, + "MMLU": 58.18, + "TruthfulQA": 52.6, + "Winogrande": 77.51, + "GSM8K": 31.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.35, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "85f7ad9d6ff016312262a47d45ffd07dee54aab0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-mistral-six-in-one-7b", + "Average \u2b06\ufe0f": 60.76, + "ARC": 62.97, + "HellaSwag": 84.6, + "MMLU": 63.29, + "TruthfulQA": 57.77, + "Winogrande": 77.51, + "GSM8K": 18.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "41e912e0f79094a80687f88ca5555f84aa9d307f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "MetaIX\/GPT4-X-Alpasta-30b", + "Average \u2b06\ufe0f": 60.76, + "ARC": 63.05, + "HellaSwag": 83.56, + "MMLU": 57.71, + "TruthfulQA": 51.52, + "Winogrande": 78.22, + "GSM8K": 30.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 65.0, + "Available on the hub": false, + "Model sha": "1a0d1d72a40946463fb4a9780207da19bfecc38b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Mistral-NeuralDPO-v0.3", + "Average \u2b06\ufe0f": 60.75, + "ARC": 61.6, + "HellaSwag": 83.15, + "MMLU": 61.6, + "TruthfulQA": 45.31, + "Winogrande": 77.98, + "GSM8K": 34.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "dba42d919d7c2f6ccc2e42a4e75d4225e2725d00", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Yhyu13\/oasst-rlhf-2-llama-30b-7k-steps-hf", + "Average \u2b06\ufe0f": 60.74, + "ARC": 61.35, + "HellaSwag": 83.8, + "MMLU": 57.89, + "TruthfulQA": 51.18, + "Winogrande": 78.77, + "GSM8K": 31.46, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "e04207847429af03c4780f5ac85c726536217981", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Venomia-m7", + "Average \u2b06\ufe0f": 60.74, + "ARC": 63.14, + "HellaSwag": 84.0, + "MMLU": 60.06, + "TruthfulQA": 49.08, + "Winogrande": 75.77, + "GSM8K": 32.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "46d997c522776af0236b254bd4c5f071b39a06a0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddyEA\/openbuddy-llama-30b-v7.1-bf16", + "Average \u2b06\ufe0f": 60.71, + "ARC": 62.46, + "HellaSwag": 82.3, + "MMLU": 58.15, + "TruthfulQA": 52.57, + "Winogrande": 77.82, + "GSM8K": 30.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.35, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "85f7ad9d6ff016312262a47d45ffd07dee54aab0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "duoqi\/Nanbeige-16B-Base-Llama", + "Average \u2b06\ufe0f": 60.7, + "ARC": 56.48, + "HellaSwag": 78.97, + "MMLU": 63.34, + "TruthfulQA": 42.6, + "Winogrande": 75.77, + "GSM8K": 47.01, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 15.83, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "183d749c4556abc66f6fd0d821d1d193e80053c1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-mistral-7b-v17.1-32k", + "Average \u2b06\ufe0f": 60.69, + "ARC": 55.38, + "HellaSwag": 78.0, + "MMLU": 58.08, + "TruthfulQA": 56.07, + "Winogrande": 75.22, + "GSM8K": 41.39, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.28, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "43f9853350f222b3802d6df332d026d344626aee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-65b-gpt4-m2.0", + "Average \u2b06\ufe0f": 60.68, + "ARC": 65.1, + "HellaSwag": 86.34, + "MMLU": 64.32, + "TruthfulQA": 46.63, + "Winogrande": 80.11, + "GSM8K": 21.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fa081d52619b35d7016fb40ce855187d6a8e7e4c", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "jondurbin\/airoboros-65b-gpt4-1.4", + "Average \u2b06\ufe0f": 60.67, + "ARC": 65.78, + "HellaSwag": 85.83, + "MMLU": 62.27, + "TruthfulQA": 52.45, + "Winogrande": 79.64, + "GSM8K": 18.04, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "ae256799615c16443f9c423c653ed9f60577e99e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-65b-gpt4-1.4-peft", + "Average \u2b06\ufe0f": 60.67, + "ARC": 65.78, + "HellaSwag": 85.83, + "MMLU": 62.27, + "TruthfulQA": 52.45, + "Winogrande": 79.64, + "GSM8K": 18.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "85ae3b595c6b8415df87000c22bc14ea18c174f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Tijmen2\/cosmosage_v2", + "Average \u2b06\ufe0f": 60.66, + "ARC": 59.73, + "HellaSwag": 80.9, + "MMLU": 59.57, + "TruthfulQA": 50.98, + "Winogrande": 75.93, + "GSM8K": 36.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c7e3ab1a424aabd7b3386050b8ef8045983c1fba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TeeZee\/2xbagel-dpo-34b-v0.2", + "Average \u2b06\ufe0f": 60.66, + "ARC": 65.27, + "HellaSwag": 79.35, + "MMLU": 73.64, + "TruthfulQA": 67.15, + "Winogrande": 76.4, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 56.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9d7e28d41f1f3221d5fefc48ed495eb921ad4be6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "paulilioaica\/Collin-7B-dare", + "Average \u2b06\ufe0f": 60.65, + "ARC": 65.87, + "HellaSwag": 82.08, + "MMLU": 51.86, + "TruthfulQA": 65.2, + "Winogrande": 77.9, + "GSM8K": 21.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c8cc55a64ad062fe5ea9b6268c4affadc0975219", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/mistral-7b-slimorca-sft", + "Average \u2b06\ufe0f": 60.63, + "ARC": 58.53, + "HellaSwag": 83.16, + "MMLU": 60.71, + "TruthfulQA": 50.18, + "Winogrande": 78.93, + "GSM8K": 32.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "45c7963f6177f7fa1e07987264817b50611650e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Zephyrus-L1-33B", + "Average \u2b06\ufe0f": 60.61, + "ARC": 64.51, + "HellaSwag": 84.15, + "MMLU": 57.37, + "TruthfulQA": 53.87, + "Winogrande": 80.19, + "GSM8K": 23.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "679aae34440d576456b283070371b2a15dbb948b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "indischepartij\/OpenMia-Indo-Mistral-7b-v2", + "Average \u2b06\ufe0f": 60.6, + "ARC": 60.32, + "HellaSwag": 83.11, + "MMLU": 62.7, + "TruthfulQA": 44.35, + "Winogrande": 78.3, + "GSM8K": 34.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9e702a205749747a66aa94d4e4baed2824aac9d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-65b-gpt4-1.4", + "Average \u2b06\ufe0f": 60.59, + "ARC": 65.53, + "HellaSwag": 85.77, + "MMLU": 61.95, + "TruthfulQA": 52.43, + "Winogrande": 79.79, + "GSM8K": 18.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "ae256799615c16443f9c423c653ed9f60577e99e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Walmart-the-bag\/Influxient-4x13B", + "Average \u2b06\ufe0f": 60.57, + "ARC": 61.26, + "HellaSwag": 83.42, + "MMLU": 57.25, + "TruthfulQA": 54.1, + "Winogrande": 74.35, + "GSM8K": 33.06, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-3.0", + "#Params (B)": 38.5, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a06acd48979617eb1af25ede71b937767889218b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/Synatra-7B-v0.3-dpo", + "Average \u2b06\ufe0f": 60.55, + "ARC": 62.8, + "HellaSwag": 82.58, + "MMLU": 61.46, + "TruthfulQA": 56.46, + "Winogrande": 76.24, + "GSM8K": 23.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "405a4f1e6513cd1b8de5eb4e003bb49cc86d1f8a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/dolphin-2.2.1-mistral-7b", + "Average \u2b06\ufe0f": 60.54, + "ARC": 63.48, + "HellaSwag": 83.86, + "MMLU": 63.28, + "TruthfulQA": 53.17, + "Winogrande": 78.37, + "GSM8K": 21.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "001b48e9aebffb395c698af47b6b48364cc3cbe8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "indischepartij\/OpenMia-Indo-Mistral-7b", + "Average \u2b06\ufe0f": 60.54, + "ARC": 59.64, + "HellaSwag": 83.18, + "MMLU": 62.75, + "TruthfulQA": 45.26, + "Winogrande": 77.82, + "GSM8K": 34.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6e58648fdfd147ede34d9e26ed70e4b8be302e58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "acrastt\/kalomaze-stuff", + "Average \u2b06\ufe0f": 60.53, + "ARC": 59.64, + "HellaSwag": 83.55, + "MMLU": 63.41, + "TruthfulQA": 41.64, + "Winogrande": 78.61, + "GSM8K": 36.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7752f615d76e515aa956335ba8d2705c2cbc297b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Mistral-11B-TestBench9", + "Average \u2b06\ufe0f": 60.52, + "ARC": 64.08, + "HellaSwag": 84.24, + "MMLU": 64.0, + "TruthfulQA": 56.19, + "Winogrande": 78.45, + "GSM8K": 16.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4ff48527af8c3907129c06160c7f7b7b786a5a79", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/WizardLM-70B-V1.0-GPTQ", + "Average \u2b06\ufe0f": 60.5, + "ARC": 63.82, + "HellaSwag": 83.85, + "MMLU": 63.68, + "TruthfulQA": 54.54, + "Winogrande": 78.61, + "GSM8K": 18.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 72.82, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": true, + "Model sha": "c234d7c9c0fd26efb55757fdbfb604d549539fe0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "prince-canuma\/Damysus-2.7B-Chat", + "Average \u2b06\ufe0f": 60.49, + "ARC": 59.81, + "HellaSwag": 74.52, + "MMLU": 56.33, + "TruthfulQA": 46.74, + "Winogrande": 74.9, + "GSM8K": 50.64, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "d805640fae5928607626d5c89b66a9aaf98da752", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "traversaal-ai\/traversaal-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 60.48, + "ARC": 66.21, + "HellaSwag": 85.02, + "MMLU": 63.24, + "TruthfulQA": 54.0, + "Winogrande": 77.9, + "GSM8K": 16.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f5403d78d43d34f90d6a0aab0b61985d48f20738", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Dolphin2.1-OpenOrca-7B", + "Average \u2b06\ufe0f": 60.47, + "ARC": 63.91, + "HellaSwag": 84.26, + "MMLU": 62.66, + "TruthfulQA": 53.84, + "Winogrande": 78.22, + "GSM8K": 19.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "076c0f7de93307e8fb3ad3bd820fb5f73325ca70", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "InnerI\/A-I-0xtom-7B-slerp", + "Average \u2b06\ufe0f": 60.46, + "ARC": 58.19, + "HellaSwag": 77.64, + "MMLU": 58.74, + "TruthfulQA": 54.78, + "Winogrande": 73.24, + "GSM8K": 40.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e7299eec852381a17aa9c0720322c1db065753f4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/Mistral-7B-Alpaca-52k-v0.1", + "Average \u2b06\ufe0f": 60.46, + "ARC": 60.92, + "HellaSwag": 82.13, + "MMLU": 63.41, + "TruthfulQA": 41.5, + "Winogrande": 77.35, + "GSM8K": 37.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "6ea2490bdb8511490f21188e4a2368ea37557ebd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/mistral-7b-metamathqa-sft", + "Average \u2b06\ufe0f": 60.46, + "ARC": 58.45, + "HellaSwag": 80.44, + "MMLU": 61.28, + "TruthfulQA": 44.73, + "Winogrande": 77.66, + "GSM8K": 40.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c16588b550a4238a113c1b56f6e7e2825491236d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Stellaris-internlm2-20b-r512", + "Average \u2b06\ufe0f": 60.46, + "ARC": 63.82, + "HellaSwag": 84.0, + "MMLU": 66.34, + "TruthfulQA": 49.51, + "Winogrande": 84.45, + "GSM8K": 14.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "237a0fc03af85eb4624ef5f367b6125ea0aaa83f", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TehVenom\/oasst-sft-6-llama-33b-xor-MERGED-16bit", + "Average \u2b06\ufe0f": 60.45, + "ARC": 61.52, + "HellaSwag": 83.5, + "MMLU": 57.43, + "TruthfulQA": 50.7, + "Winogrande": 79.08, + "GSM8K": 30.48, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "62f92ddab8b37eaeda15cf5ecb5605141a0525eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HenryJJ\/Instruct_Mistral-7B-v0.1_Dolly15K", + "Average \u2b06\ufe0f": 60.45, + "ARC": 59.39, + "HellaSwag": 82.62, + "MMLU": 62.71, + "TruthfulQA": 43.56, + "Winogrande": 79.32, + "GSM8K": 35.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c1d04418a3f404a9500c8292ec912e2b00694f45", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "ddyuudd\/mistral_dmbr20_32_sig", + "Average \u2b06\ufe0f": 60.43, + "ARC": 58.7, + "HellaSwag": 82.54, + "MMLU": 61.41, + "TruthfulQA": 44.75, + "Winogrande": 77.58, + "GSM8K": 37.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2f6b2e47ddcde6ae6d7b690c2c2ff1d7be9d3e1b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aeala\/GPT4-x-AlpacaDente-30b", + "Average \u2b06\ufe0f": 60.43, + "ARC": 62.12, + "HellaSwag": 82.78, + "MMLU": 56.19, + "TruthfulQA": 52.68, + "Winogrande": 78.69, + "GSM8K": 30.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "ee76c821f861f0ab0276f9f429dd06565f1f2051", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "WizardLM\/WizardMath-70B-V1.0", + "Average \u2b06\ufe0f": 60.42, + "ARC": 68.17, + "HellaSwag": 86.49, + "MMLU": 68.89, + "TruthfulQA": 52.69, + "Winogrande": 82.32, + "GSM8K": 3.94, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 111.0, + "Available on the hub": true, + "Model sha": "e85b43e53c5379e35393b970c66d76c2d1060381", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "WizardLM\/WizardMath-70B-V1.0", + "Average \u2b06\ufe0f": 60.41, + "ARC": 67.92, + "HellaSwag": 86.46, + "MMLU": 68.92, + "TruthfulQA": 52.77, + "Winogrande": 82.32, + "GSM8K": 4.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 111.0, + "Available on the hub": true, + "Model sha": "e85b43e53c5379e35393b970c66d76c2d1060381", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "Xenon1\/Xenon-4", + "Average \u2b06\ufe0f": 60.39, + "ARC": 60.15, + "HellaSwag": 83.07, + "MMLU": 60.08, + "TruthfulQA": 61.31, + "Winogrande": 77.03, + "GSM8K": 20.7, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "371a4b6038a84c9a887a156a78e165d70f67b2d2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/SlimOrca-13B", + "Average \u2b06\ufe0f": 60.39, + "ARC": 60.15, + "HellaSwag": 81.4, + "MMLU": 57.04, + "TruthfulQA": 49.37, + "Winogrande": 74.43, + "GSM8K": 39.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "75427e93dc99a5e1d8b9aefa106ad36fc750b744", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "speechlessai\/speechless-mistral-7b-dare-0.85", + "Average \u2b06\ufe0f": 60.39, + "ARC": 63.31, + "HellaSwag": 84.93, + "MMLU": 64.22, + "TruthfulQA": 50.68, + "Winogrande": 79.32, + "GSM8K": 19.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5eefd1b560cd65aec2f689880476f909b46d306c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Dolphin2.1-OpenOrca-7B", + "Average \u2b06\ufe0f": 60.38, + "ARC": 64.16, + "HellaSwag": 84.25, + "MMLU": 62.7, + "TruthfulQA": 53.83, + "Winogrande": 77.66, + "GSM8K": 19.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "076c0f7de93307e8fb3ad3bd820fb5f73325ca70", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "marcel\/phi-2-openhermes-30k", + "Average \u2b06\ufe0f": 60.37, + "ARC": 61.01, + "HellaSwag": 74.72, + "MMLU": 57.17, + "TruthfulQA": 45.38, + "Winogrande": 74.9, + "GSM8K": 49.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e09a1fa39a807edf8b3f644d81cd2c91984dfd10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Open-Orca\/Mistral-7B-SlimOrca", + "Average \u2b06\ufe0f": 60.37, + "ARC": 62.54, + "HellaSwag": 83.86, + "MMLU": 62.77, + "TruthfulQA": 54.23, + "Winogrande": 77.43, + "GSM8K": 21.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 29.0, + "Available on the hub": true, + "Model sha": "a9744d8cf9ce4230678a891bcf8bba7cbc0aaece", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EmbeddedLLM\/Mistral-7B-Merge-14-v0.3-ft-step-9984", + "Average \u2b06\ufe0f": 60.37, + "ARC": 62.54, + "HellaSwag": 82.18, + "MMLU": 62.92, + "TruthfulQA": 53.7, + "Winogrande": 75.61, + "GSM8K": 25.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4bb10bcc0f7dfc5039658eb5e6b36c8555d94e66", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Obrolin\/Kesehatan-7B-v0.1", + "Average \u2b06\ufe0f": 60.37, + "ARC": 60.32, + "HellaSwag": 82.54, + "MMLU": 59.94, + "TruthfulQA": 50.68, + "Winogrande": 76.48, + "GSM8K": 32.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a05db4c08e78668ac7249f41be98ffa866c6bf5a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BlouseJury\/Mistral-7B-Discord-0.1", + "Average \u2b06\ufe0f": 60.28, + "ARC": 60.24, + "HellaSwag": 83.13, + "MMLU": 62.82, + "TruthfulQA": 44.1, + "Winogrande": 78.93, + "GSM8K": 32.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "090a440c18ac262ecc045b798b72f99ba9a22c9c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Xenon1\/Xenon-3", + "Average \u2b06\ufe0f": 60.27, + "ARC": 58.87, + "HellaSwag": 83.39, + "MMLU": 59.79, + "TruthfulQA": 61.99, + "Winogrande": 77.51, + "GSM8K": 20.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "36a1fdbcf8ec629dbe143221712d2f01e4b9b3cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "diffnamehard\/Psyfighter2-Noromaid-ties-Capybara-13B", + "Average \u2b06\ufe0f": 60.27, + "ARC": 62.29, + "HellaSwag": 83.87, + "MMLU": 56.59, + "TruthfulQA": 51.44, + "Winogrande": 77.03, + "GSM8K": 30.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a7fa1f27d0a9123ce9dc415a5573b9e0525c69f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_3.5", + "Average \u2b06\ufe0f": 60.26, + "ARC": 62.46, + "HellaSwag": 83.96, + "MMLU": 62.89, + "TruthfulQA": 45.43, + "Winogrande": 81.06, + "GSM8K": 25.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1051.0, + "Available on the hub": true, + "Model sha": "5b874a33a91d63023055e6cb2d5d86afe883b4ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/SlimOpenOrca-Mistral-7B-v2", + "Average \u2b06\ufe0f": 60.25, + "ARC": 62.88, + "HellaSwag": 83.41, + "MMLU": 62.05, + "TruthfulQA": 56.65, + "Winogrande": 77.58, + "GSM8K": 18.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7cd030ccdb169c2685fe028bb4380b91ad74920f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Mistral-11B-TestBench11", + "Average \u2b06\ufe0f": 60.25, + "ARC": 64.42, + "HellaSwag": 83.93, + "MMLU": 63.82, + "TruthfulQA": 56.68, + "Winogrande": 77.74, + "GSM8K": 14.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9aae2b156b24557bb98e515f3a90c7865529d2e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "prince-canuma\/Damysus-2.7B-Chat", + "Average \u2b06\ufe0f": 60.25, + "ARC": 59.13, + "HellaSwag": 74.36, + "MMLU": 56.34, + "TruthfulQA": 46.45, + "Winogrande": 75.06, + "GSM8K": 50.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "d805640fae5928607626d5c89b66a9aaf98da752", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MisterRid\/wendigo-14b-alpha4", + "Average \u2b06\ufe0f": 60.25, + "ARC": 59.3, + "HellaSwag": 79.65, + "MMLU": 59.85, + "TruthfulQA": 54.98, + "Winogrande": 74.74, + "GSM8K": 32.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ea3ecf4418cf3655cf5093a8feb045b47b92c331", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vihangd\/smartyplats-7b-v2", + "Average \u2b06\ufe0f": 60.24, + "ARC": 57.94, + "HellaSwag": 80.76, + "MMLU": 58.16, + "TruthfulQA": 50.26, + "Winogrande": 75.53, + "GSM8K": 38.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "99049eb184b9b3ef074043d6e626fe3db09f5a19", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lilloukas\/GPlatty-30B", + "Average \u2b06\ufe0f": 60.23, + "ARC": 65.78, + "HellaSwag": 84.79, + "MMLU": 63.49, + "TruthfulQA": 52.45, + "Winogrande": 80.98, + "GSM8K": 13.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "836cf4dcd60ebe2ff09415c72f809d94639e8d35", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "argilla\/notus-7b-v1", + "Average \u2b06\ufe0f": 60.22, + "ARC": 64.59, + "HellaSwag": 84.78, + "MMLU": 63.03, + "TruthfulQA": 54.37, + "Winogrande": 79.4, + "GSM8K": 15.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 106.0, + "Available on the hub": true, + "Model sha": "89f594b32aea9bf5de0abe3877f20ff302549934", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SicariusSicariiStuff\/Tenebra_30B_Alpha01_FP16", + "Average \u2b06\ufe0f": 60.18, + "ARC": 64.51, + "HellaSwag": 84.79, + "MMLU": 54.29, + "TruthfulQA": 54.22, + "Winogrande": 78.61, + "GSM8K": 24.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ad31f850f8c061d79a05aaa2419ec0f0baf62034", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Open-Orca\/Mistral-7B-OpenOrca", + "Average \u2b06\ufe0f": 60.17, + "ARC": 64.08, + "HellaSwag": 83.99, + "MMLU": 62.24, + "TruthfulQA": 53.05, + "Winogrande": 77.74, + "GSM8K": 19.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 609.0, + "Available on the hub": true, + "Model sha": "7233ac83317946d05c474b71cc1379f49eb74c14", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CallComply\/SOLAR-10.7B-Instruct-v1.0-128k", + "Average \u2b06\ufe0f": 60.16, + "ARC": 65.96, + "HellaSwag": 84.35, + "MMLU": 57.63, + "TruthfulQA": 65.42, + "Winogrande": 80.51, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "bf951ef22381c0dbeb69959fb3c06e772adc2426", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-65b-gpt4-1.3", + "Average \u2b06\ufe0f": 60.15, + "ARC": 66.13, + "HellaSwag": 85.99, + "MMLU": 63.89, + "TruthfulQA": 51.32, + "Winogrande": 79.95, + "GSM8K": 13.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4373e66135c6fb4a6063777c4270a34509e7e932", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-zephyr-6x7b-lora", + "Average \u2b06\ufe0f": 60.13, + "ARC": 61.01, + "HellaSwag": 82.8, + "MMLU": 60.09, + "TruthfulQA": 48.84, + "Winogrande": 77.03, + "GSM8K": 31.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ebf239f263dc1bfb7cf2030c96f0e967683e5946", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MisterRid\/wendigo-14b-alpha3", + "Average \u2b06\ufe0f": 60.1, + "ARC": 59.39, + "HellaSwag": 79.51, + "MMLU": 59.72, + "TruthfulQA": 55.12, + "Winogrande": 74.74, + "GSM8K": 32.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "01c9ec549ddc830eaa6639e7e89b6337c51586e3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MexIvanov\/zephyr-python-ru-merged", + "Average \u2b06\ufe0f": 60.1, + "ARC": 56.06, + "HellaSwag": 82.06, + "MMLU": 60.2, + "TruthfulQA": 52.81, + "Winogrande": 76.95, + "GSM8K": 32.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "046d180301dd6b764fc5def83f39c8b4aa62782f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "teknium\/CollectiveCognition-v1-Mistral-7B", + "Average \u2b06\ufe0f": 60.1, + "ARC": 62.37, + "HellaSwag": 85.5, + "MMLU": 62.76, + "TruthfulQA": 54.48, + "Winogrande": 77.58, + "GSM8K": 17.89, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "58777f0563610fa770c4fa252c0350de71d4ab9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "MexIvanov\/zephyr-python-ru", + "Average \u2b06\ufe0f": 60.08, + "ARC": 56.14, + "HellaSwag": 82.03, + "MMLU": 60.18, + "TruthfulQA": 52.8, + "Winogrande": 76.8, + "GSM8K": 32.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "64a1984f1cba96880047c8f93a83fde9f5b1df35", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishek\/ccy0-2g7e-wqsa-0", + "Average \u2b06\ufe0f": 60.07, + "ARC": 58.19, + "HellaSwag": 82.19, + "MMLU": 59.59, + "TruthfulQA": 49.99, + "Winogrande": 78.22, + "GSM8K": 32.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1cd1158f3104fa8ed8469e2b09d674b997e229b4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-zephyr-6x7b", + "Average \u2b06\ufe0f": 60.06, + "ARC": 60.75, + "HellaSwag": 82.8, + "MMLU": 60.03, + "TruthfulQA": 48.84, + "Winogrande": 77.03, + "GSM8K": 30.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 35.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8d7ffe152c8dd278fbd8f29a80dfa13b024f3e52", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jingyeom\/freeze_KoSoLAR-10.7B-v0.2_1.4_dedup", + "Average \u2b06\ufe0f": 60.06, + "ARC": 58.45, + "HellaSwag": 81.26, + "MMLU": 64.83, + "TruthfulQA": 44.5, + "Winogrande": 79.08, + "GSM8K": 32.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f090bee9157ddc907f747408ec39098c8d676d22", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/llama-30b-2048-instruct-PL-lora_unload", + "Average \u2b06\ufe0f": 60.03, + "ARC": 63.82, + "HellaSwag": 84.7, + "MMLU": 61.49, + "TruthfulQA": 52.49, + "Winogrande": 79.79, + "GSM8K": 17.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b15f4310ea37fef99e4f16372a4b1f2342e27613", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Mihaiii\/Metis-0.1", + "Average \u2b06\ufe0f": 60.02, + "ARC": 60.15, + "HellaSwag": 82.85, + "MMLU": 61.42, + "TruthfulQA": 45.24, + "Winogrande": 77.27, + "GSM8K": 33.21, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ead51068b4208b37c37733109570b445d086551e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Delcos\/Velara", + "Average \u2b06\ufe0f": 60.01, + "ARC": 58.96, + "HellaSwag": 82.83, + "MMLU": 59.45, + "TruthfulQA": 44.7, + "Winogrande": 73.8, + "GSM8K": 40.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 11.39, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "0fad8e711563d3a5a4631500d6a1d6b87f10d396", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "ehartford\/WizardLM-33B-V1.0-Uncensored", + "Average \u2b06\ufe0f": 59.99, + "ARC": 63.65, + "HellaSwag": 83.84, + "MMLU": 59.36, + "TruthfulQA": 56.8, + "Winogrande": 77.66, + "GSM8K": 18.65, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3eca9fdee0ce28d6a4a635a6f19d9a413caee3e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/zephyr-dpo-v2", + "Average \u2b06\ufe0f": 59.99, + "ARC": 57.85, + "HellaSwag": 82.72, + "MMLU": 58.61, + "TruthfulQA": 56.16, + "Winogrande": 74.35, + "GSM8K": 30.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8276bfec42e8fed1d8d67e8ee8b2e4fa594addb0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "codellama\/CodeLlama-70b-Instruct-hf", + "Average \u2b06\ufe0f": 59.98, + "ARC": 55.03, + "HellaSwag": 77.24, + "MMLU": 56.4, + "TruthfulQA": 50.44, + "Winogrande": 74.51, + "GSM8K": 46.25, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 178.0, + "Available on the hub": true, + "Model sha": "6b762a8d3c16e4397aaa4f4627ebfda5db098831", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jebcarter\/psyonic-cetacean-20B", + "Average \u2b06\ufe0f": 59.97, + "ARC": 63.57, + "HellaSwag": 86.2, + "MMLU": 59.66, + "TruthfulQA": 57.55, + "Winogrande": 78.14, + "GSM8K": 14.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "298d2086a949d53af06096d229f64f4719261698", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Novocode7b", + "Average \u2b06\ufe0f": 59.96, + "ARC": 58.79, + "HellaSwag": 80.51, + "MMLU": 56.5, + "TruthfulQA": 62.77, + "Winogrande": 78.14, + "GSM8K": 23.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a4cf91cc879937c3a45ca0f10aecd335c3919063", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xenon1\/Zenith-7B-dpo-v1", + "Average \u2b06\ufe0f": 59.95, + "ARC": 60.75, + "HellaSwag": 82.97, + "MMLU": 60.55, + "TruthfulQA": 60.71, + "Winogrande": 77.51, + "GSM8K": 17.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "907891fc0660b02f0e37749291696d1a26a88b58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ericpolewski\/AIRIC-The-Mistral", + "Average \u2b06\ufe0f": 59.95, + "ARC": 59.98, + "HellaSwag": 82.98, + "MMLU": 60.67, + "TruthfulQA": 48.24, + "Winogrande": 76.95, + "GSM8K": 30.86, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "b491a2e09079cfd8d388a5a65e2c44910b10aad4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Novocode7b-v3", + "Average \u2b06\ufe0f": 59.94, + "ARC": 57.51, + "HellaSwag": 81.17, + "MMLU": 61.91, + "TruthfulQA": 48.29, + "Winogrande": 74.51, + "GSM8K": 36.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0b6cba6cc3071b54e70c91d1d9e5463f1aa9c942", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Xenon1\/Xenon-2", + "Average \u2b06\ufe0f": 59.93, + "ARC": 57.51, + "HellaSwag": 83.28, + "MMLU": 60.25, + "TruthfulQA": 60.92, + "Winogrande": 78.22, + "GSM8K": 19.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "84b328258928f6e9f4b4fede000f58a4df8fabb5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xriminact\/TarsChattyBasev0.0", + "Average \u2b06\ufe0f": 59.92, + "ARC": 64.93, + "HellaSwag": 84.57, + "MMLU": 58.04, + "TruthfulQA": 61.71, + "Winogrande": 78.61, + "GSM8K": 11.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2a690b0b6f9b88390b06c1b0f07f6f5993c374e1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CallComply\/Starling-LM-11B-alpha", + "Average \u2b06\ufe0f": 59.92, + "ARC": 61.26, + "HellaSwag": 81.99, + "MMLU": 61.5, + "TruthfulQA": 41.53, + "Winogrande": 78.06, + "GSM8K": 35.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "db8cffdb7d63b88239c3b27b5afe1b433400e72f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Intel\/neural-chat-7b-v3-1", + "Average \u2b06\ufe0f": 59.9, + "ARC": 64.25, + "HellaSwag": 82.49, + "MMLU": 60.79, + "TruthfulQA": 56.4, + "Winogrande": 77.35, + "GSM8K": 18.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 523.0, + "Available on the hub": true, + "Model sha": "3995e9a13d54ce95f0ad55de2eaa92e2dc580174", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Walmart-the-bag\/Yi-6B-Infinity-Chat", + "Average \u2b06\ufe0f": 59.83, + "ARC": 56.57, + "HellaSwag": 77.66, + "MMLU": 64.05, + "TruthfulQA": 50.75, + "Winogrande": 73.95, + "GSM8K": 36.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7a441a69e1ebd192fbf52b904589130c3875aacc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/samantha-1.2-mistral-7b", + "Average \u2b06\ufe0f": 59.83, + "ARC": 64.08, + "HellaSwag": 85.08, + "MMLU": 63.91, + "TruthfulQA": 50.4, + "Winogrande": 78.53, + "GSM8K": 16.98, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5574a021f55a446a756dcbc776f1765aefc280a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/llama-30b-instruct-2048-PL-lora", + "Average \u2b06\ufe0f": 59.82, + "ARC": 63.31, + "HellaSwag": 84.66, + "MMLU": 61.66, + "TruthfulQA": 53.35, + "Winogrande": 79.08, + "GSM8K": 16.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1a076bce564f03bd47951eecab628c541fb1a6ad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jilp00\/Hermes-2-SOLAR-10.7B-Symbolic", + "Average \u2b06\ufe0f": 59.81, + "ARC": 61.69, + "HellaSwag": 82.57, + "MMLU": 65.06, + "TruthfulQA": 54.85, + "Winogrande": 80.74, + "GSM8K": 13.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a5e2987baf03cab726e1135877ce3ae319ccd843", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "WizardLM\/WizardMath-70B-V1.0", + "Average \u2b06\ufe0f": 59.81, + "ARC": 67.49, + "HellaSwag": 86.03, + "MMLU": 68.44, + "TruthfulQA": 52.23, + "Winogrande": 81.77, + "GSM8K": 2.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 70.0, + "Hub \u2764\ufe0f": 111.0, + "Available on the hub": true, + "Model sha": "97e5913edd2c593c3eef12070024674e7ee4e16c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Xenon1\/Zenith-7B-dpo", + "Average \u2b06\ufe0f": 59.8, + "ARC": 60.92, + "HellaSwag": 82.94, + "MMLU": 60.54, + "TruthfulQA": 60.5, + "Winogrande": 77.27, + "GSM8K": 16.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a208869ce8f2643a1779cd89b1f8615b11206a8a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dball\/zephyr-7b-sft-qlora", + "Average \u2b06\ufe0f": 59.8, + "ARC": 59.73, + "HellaSwag": 82.49, + "MMLU": 61.9, + "TruthfulQA": 42.32, + "Winogrande": 78.22, + "GSM8K": 34.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ffcebbaaabb14ac25326c6385327f73785ec4a95", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kimwooglae\/AISquare-Instruct-SOLAR-10.7b-v0.5.32", + "Average \u2b06\ufe0f": 59.79, + "ARC": 61.86, + "HellaSwag": 84.66, + "MMLU": 63.13, + "TruthfulQA": 51.19, + "Winogrande": 82.79, + "GSM8K": 15.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2d978ca8513d3863d945e59a3569f59773618dc3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HuggingFaceH4\/mistral-7b-sft-beta", + "Average \u2b06\ufe0f": 59.78, + "ARC": 57.42, + "HellaSwag": 82.23, + "MMLU": 61.42, + "TruthfulQA": 43.58, + "Winogrande": 77.58, + "GSM8K": 36.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "c985a04e76fb00d3c3f65214d0b02c5a751d2274", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xenon1\/Zenith-7B-dpo-v1", + "Average \u2b06\ufe0f": 59.78, + "ARC": 60.49, + "HellaSwag": 82.95, + "MMLU": 60.39, + "TruthfulQA": 60.6, + "Winogrande": 77.27, + "GSM8K": 16.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "907891fc0660b02f0e37749291696d1a26a88b58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CorticalStack\/mistral-7b-openhermes-sft", + "Average \u2b06\ufe0f": 59.78, + "ARC": 60.58, + "HellaSwag": 82.01, + "MMLU": 60.95, + "TruthfulQA": 46.31, + "Winogrande": 77.58, + "GSM8K": 31.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "911e144035ebbffe7fe41335cb0aca44c188fb58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "neovalle\/H4rmoniousAnthea", + "Average \u2b06\ufe0f": 59.76, + "ARC": 65.87, + "HellaSwag": 84.09, + "MMLU": 63.67, + "TruthfulQA": 55.08, + "Winogrande": 76.87, + "GSM8K": 12.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "42979461b582e0e511f29ec4c72a69a13dc4a831", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aloobun\/bun_mistral_7b_v2", + "Average \u2b06\ufe0f": 59.76, + "ARC": 59.9, + "HellaSwag": 82.65, + "MMLU": 61.77, + "TruthfulQA": 40.67, + "Winogrande": 78.3, + "GSM8K": 35.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4b7c558e530a9e887ba38fc5f58caf7b41db608e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Llama-2-70B-chat-GPTQ", + "Average \u2b06\ufe0f": 59.75, + "ARC": 62.63, + "HellaSwag": 84.81, + "MMLU": 62.74, + "TruthfulQA": 50.98, + "Winogrande": 78.69, + "GSM8K": 18.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "?", + "#Params (B)": 72.82, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "054fbf6f65e7ab7691ec07ec9ad366acf2dd90bf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Locutusque\/Orca-2-13b-SFT-v4", + "Average \u2b06\ufe0f": 59.75, + "ARC": 59.22, + "HellaSwag": 79.58, + "MMLU": 60.23, + "TruthfulQA": 51.15, + "Winogrande": 80.03, + "GSM8K": 28.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "f3491a4c169a5b8307383499b72ab9e2174c37da", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "crumb\/apricot-wildflower-20", + "Average \u2b06\ufe0f": 59.74, + "ARC": 59.64, + "HellaSwag": 81.76, + "MMLU": 63.38, + "TruthfulQA": 41.76, + "Winogrande": 77.9, + "GSM8K": 33.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "27610b542c84b446c397dd92cc28d53c278b1ecb", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-thoughts-mistral-7b", + "Average \u2b06\ufe0f": 59.72, + "ARC": 58.96, + "HellaSwag": 80.71, + "MMLU": 60.11, + "TruthfulQA": 49.91, + "Winogrande": 77.82, + "GSM8K": 30.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e4428eeadd912f5ad207c4c6f53b10b6ec537af9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "adamo1139\/Mistral-7B-AEZAKMI-v2", + "Average \u2b06\ufe0f": 59.69, + "ARC": 58.11, + "HellaSwag": 82.53, + "MMLU": 59.89, + "TruthfulQA": 51.5, + "Winogrande": 73.64, + "GSM8K": 32.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5a1bbf8066d2ff0effdf6ba311f295a1a5b88c65", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "joey00072\/ToxicHermes-2.5-Mistral-7B", + "Average \u2b06\ufe0f": 59.69, + "ARC": 64.59, + "HellaSwag": 83.75, + "MMLU": 63.67, + "TruthfulQA": 50.84, + "Winogrande": 77.9, + "GSM8K": 17.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "b8355885ec4e429f8cf1c7f0c324a696ee7a2893", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sarahlintang\/mistral-indo-7b", + "Average \u2b06\ufe0f": 59.68, + "ARC": 61.09, + "HellaSwag": 81.19, + "MMLU": 62.99, + "TruthfulQA": 42.34, + "Winogrande": 78.37, + "GSM8K": 32.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eb5051623b2057c2af3d69247a649d4e8ec5b111", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Tiger-DPO", + "Average \u2b06\ufe0f": 59.66, + "ARC": 48.21, + "HellaSwag": 81.82, + "MMLU": 59.85, + "TruthfulQA": 50.76, + "Winogrande": 76.32, + "GSM8K": 41.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7fc4622f783428dcbfba81a7aa8344c84b74a7b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NECOUDBFM\/Jellyfish", + "Average \u2b06\ufe0f": 59.65, + "ARC": 63.31, + "HellaSwag": 83.19, + "MMLU": 58.6, + "TruthfulQA": 53.32, + "Winogrande": 75.85, + "GSM8K": 23.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "33e7aa13e855f0342d7e3173e78142bd5989c671", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/Synatra-RP-Orca-2-7b-v0.1", + "Average \u2b06\ufe0f": 59.65, + "ARC": 57.68, + "HellaSwag": 77.37, + "MMLU": 56.1, + "TruthfulQA": 52.52, + "Winogrande": 74.59, + "GSM8K": 39.65, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "da80bc823c407c28c464cc0547a8ed9e0ca82f79", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Orca-2-13B-no_robots", + "Average \u2b06\ufe0f": 59.63, + "ARC": 59.13, + "HellaSwag": 79.57, + "MMLU": 60.28, + "TruthfulQA": 51.17, + "Winogrande": 80.35, + "GSM8K": 27.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6f32722f7d24501036698cbca9c7a3e2336f071f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Yarn-Mistral-7b-64k", + "Average \u2b06\ufe0f": 59.63, + "ARC": 59.9, + "HellaSwag": 82.51, + "MMLU": 62.96, + "TruthfulQA": 41.86, + "Winogrande": 77.27, + "GSM8K": 33.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "0273c624561fcecc8e8f4030492a9307aa60f945", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/test-case-2", + "Average \u2b06\ufe0f": 59.63, + "ARC": 58.53, + "HellaSwag": 79.4, + "MMLU": 56.14, + "TruthfulQA": 49.59, + "Winogrande": 75.3, + "GSM8K": 38.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c172974de60343295ebb355ebc204d3804786e9f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sequelbox\/DiamondForce", + "Average \u2b06\ufe0f": 59.63, + "ARC": 62.12, + "HellaSwag": 83.43, + "MMLU": 58.1, + "TruthfulQA": 46.46, + "Winogrande": 79.01, + "GSM8K": 28.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e92bbb8e6373408235e30cebcf4a71cc319b0ae3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/SynthIA-7B-v1.5", + "Average \u2b06\ufe0f": 59.59, + "ARC": 62.71, + "HellaSwag": 83.37, + "MMLU": 63.48, + "TruthfulQA": 51.32, + "Winogrande": 79.24, + "GSM8K": 17.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "5a9912ef90a0efc1aaea327e5cf3e9554c8bd897", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "nisten\/BigCodeLlama-92b", + "Average \u2b06\ufe0f": 59.57, + "ARC": 54.78, + "HellaSwag": 77.84, + "MMLU": 55.4, + "TruthfulQA": 51.34, + "Winogrande": 73.09, + "GSM8K": 44.96, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 92.08, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "77640c1d7006d83f26c29a3c2454a4639277a106", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/Mistral-7B-Holodeck-1", + "Average \u2b06\ufe0f": 59.56, + "ARC": 60.24, + "HellaSwag": 82.53, + "MMLU": 62.67, + "TruthfulQA": 41.53, + "Winogrande": 76.72, + "GSM8K": 33.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "76057cc5c1923921162133c81ae7ca0e92755810", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ValiantLabs\/ShiningValiantXS", + "Average \u2b06\ufe0f": 59.56, + "ARC": 58.96, + "HellaSwag": 81.93, + "MMLU": 56.75, + "TruthfulQA": 48.7, + "Winogrande": 76.95, + "GSM8K": 34.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "8c1f86bd2e646408eed2ed3a2634b38ea4e5c599", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "maywell\/Synatra-RP-Orca-2-7b-v0.1", + "Average \u2b06\ufe0f": 59.55, + "ARC": 57.42, + "HellaSwag": 77.31, + "MMLU": 56.12, + "TruthfulQA": 52.55, + "Winogrande": 74.43, + "GSM8K": 39.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "da80bc823c407c28c464cc0547a8ed9e0ca82f79", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "internlm\/internlm-20b", + "Average \u2b06\ufe0f": 59.55, + "ARC": 60.49, + "HellaSwag": 82.13, + "MMLU": 61.85, + "TruthfulQA": 52.61, + "Winogrande": 76.72, + "GSM8K": 23.5, + "Type": "pretrained", + "Architecture": "InternLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 71.0, + "Available on the hub": true, + "Model sha": "b8825fe3394608fe84f0f5eb6471454384fb83aa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BlouseJury\/Mistral-7B-Discord-0.2", + "Average \u2b06\ufe0f": 59.55, + "ARC": 60.58, + "HellaSwag": 82.49, + "MMLU": 62.82, + "TruthfulQA": 42.73, + "Winogrande": 77.74, + "GSM8K": 30.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "721a1203baea1e9b234e90f98aebdca0e556153f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zangs3011\/mistral_7b_HalfEpoch_DolphinCoder", + "Average \u2b06\ufe0f": 59.55, + "ARC": 61.69, + "HellaSwag": 82.38, + "MMLU": 61.44, + "TruthfulQA": 45.51, + "Winogrande": 75.77, + "GSM8K": 30.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "94f00b028f630b625759e3a7798f4c57ce753506", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/cloudymixtral7Bx2-nectar-0.2", + "Average \u2b06\ufe0f": 59.54, + "ARC": 67.49, + "HellaSwag": 80.83, + "MMLU": 65.14, + "TruthfulQA": 68.7, + "Winogrande": 73.88, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "56b640240f1aca4a91ccf66de041c86102dfe2c9", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "xriminact\/TarsMeta", + "Average \u2b06\ufe0f": 59.54, + "ARC": 52.9, + "HellaSwag": 78.2, + "MMLU": 52.63, + "TruthfulQA": 47.88, + "Winogrande": 72.77, + "GSM8K": 52.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "458bf65b37f4f89ea92a72ee3df6e0048324252f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andysalerno\/cloudymixtral7Bx2-nectar-0.2", + "Average \u2b06\ufe0f": 59.53, + "ARC": 67.49, + "HellaSwag": 80.77, + "MMLU": 65.09, + "TruthfulQA": 68.73, + "Winogrande": 73.95, + "GSM8K": 1.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 12.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "56b640240f1aca4a91ccf66de041c86102dfe2c9", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "perlthoughts\/Chupacabra-v3", + "Average \u2b06\ufe0f": 59.52, + "ARC": 66.21, + "HellaSwag": 81.29, + "MMLU": 59.36, + "TruthfulQA": 57.85, + "Winogrande": 77.43, + "GSM8K": 15.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1dfa5e16d4be646b496d657d86554482ad48b3c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/WizardLM-30B-fp16", + "Average \u2b06\ufe0f": 59.51, + "ARC": 62.54, + "HellaSwag": 83.28, + "MMLU": 59.03, + "TruthfulQA": 52.49, + "Winogrande": 77.51, + "GSM8K": 22.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "465f87a243969963f25ae6cf8f8d2de6c0898bbe", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/gpt4-alpaca-lora-30b-HF", + "Average \u2b06\ufe0f": 59.51, + "ARC": 64.85, + "HellaSwag": 85.72, + "MMLU": 58.51, + "TruthfulQA": 52.24, + "Winogrande": 80.19, + "GSM8K": 15.54, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "3c8007467a081dc72ae09b9d358416b056b38920", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HuggingFaceH4\/zephyr-7b-alpha", + "Average \u2b06\ufe0f": 59.5, + "ARC": 61.01, + "HellaSwag": 84.04, + "MMLU": 61.39, + "TruthfulQA": 57.9, + "Winogrande": 78.61, + "GSM8K": 14.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1047.0, + "Available on the hub": true, + "Model sha": "2cd2cd16a6ab22585d643cf264fac73b18e7852a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/HelpSteer-filtered-7B", + "Average \u2b06\ufe0f": 59.49, + "ARC": 59.56, + "HellaSwag": 83.32, + "MMLU": 63.52, + "TruthfulQA": 41.11, + "Winogrande": 76.01, + "GSM8K": 33.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0f14404caa1b4609bb2f50714df973223f443e40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "diffnamehard\/Psyfighter2-Noromaid-ties-13B", + "Average \u2b06\ufe0f": 59.47, + "ARC": 61.86, + "HellaSwag": 84.58, + "MMLU": 57.04, + "TruthfulQA": 50.66, + "Winogrande": 75.37, + "GSM8K": 27.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "191d13355682a875a24d2ebdd3322df55d6f9954", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "LLMs\/WizardLM-30B-V1.0", + "Average \u2b06\ufe0f": 59.45, + "ARC": 62.54, + "HellaSwag": 83.27, + "MMLU": 59.05, + "TruthfulQA": 52.49, + "Winogrande": 77.51, + "GSM8K": 21.83, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "75318440dba949804d6263d368e1f29a94ea7c5f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Yarn-Mistral-7b-128k", + "Average \u2b06\ufe0f": 59.42, + "ARC": 59.64, + "HellaSwag": 82.5, + "MMLU": 63.02, + "TruthfulQA": 41.78, + "Winogrande": 76.95, + "GSM8K": 32.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 532.0, + "Available on the hub": true, + "Model sha": "d09f1f8ed437d61c1aff94c1beabee554843dcdd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "qblocks\/mistral_7b_HalfEpoch_DolphinCoder", + "Average \u2b06\ufe0f": 59.4, + "ARC": 61.77, + "HellaSwag": 82.26, + "MMLU": 61.75, + "TruthfulQA": 45.46, + "Winogrande": 75.53, + "GSM8K": 29.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a9256ea648ecd6450d5ea4ebc2d07a1222ba8e9a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "hywu\/Camelidae-8x13B", + "Average \u2b06\ufe0f": 59.4, + "ARC": 61.18, + "HellaSwag": 82.73, + "MMLU": 57.21, + "TruthfulQA": 43.37, + "Winogrande": 77.35, + "GSM8K": 34.57, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "857292e46549732062a27eb965f3c9869dc62794", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-XS-v1.1", + "Average \u2b06\ufe0f": 59.39, + "ARC": 63.91, + "HellaSwag": 84.06, + "MMLU": 63.07, + "TruthfulQA": 49.92, + "Winogrande": 79.16, + "GSM8K": 16.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "e8850e534a3a9f602f72201b09c7ef8f879c1c0b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "deepseek-ai\/deepseek-llm-7b-chat", + "Average \u2b06\ufe0f": 59.38, + "ARC": 55.8, + "HellaSwag": 79.38, + "MMLU": 51.75, + "TruthfulQA": 47.98, + "Winogrande": 74.82, + "GSM8K": 46.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 58.0, + "Available on the hub": true, + "Model sha": "afbda8b347ec881666061fa67447046fc5164ec8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CallComply\/openchat-3.5-0106-128k", + "Average \u2b06\ufe0f": 59.38, + "ARC": 64.25, + "HellaSwag": 77.31, + "MMLU": 57.58, + "TruthfulQA": 46.5, + "Winogrande": 77.66, + "GSM8K": 32.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "35cf427cc9af94533baeea8afa1428a0eff78f3f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-thoughts-mistral-7b-v1.0", + "Average \u2b06\ufe0f": 59.36, + "ARC": 58.53, + "HellaSwag": 81.25, + "MMLU": 54.95, + "TruthfulQA": 48.09, + "Winogrande": 78.14, + "GSM8K": 35.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e5aa2dc21065b86fced97bd09d8567bd384a273d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/test-case-0", + "Average \u2b06\ufe0f": 59.35, + "ARC": 57.51, + "HellaSwag": 79.64, + "MMLU": 58.02, + "TruthfulQA": 48.8, + "Winogrande": 77.82, + "GSM8K": 34.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "75bc9a822d2f1200cc41eb0fbe0f48326a0e8947", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/OpenAssistant-SFT-7-Llama-30B-HF", + "Average \u2b06\ufe0f": 59.34, + "ARC": 60.58, + "HellaSwag": 82.17, + "MMLU": 57.93, + "TruthfulQA": 46.94, + "Winogrande": 78.61, + "GSM8K": 29.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "a7a2306b9a63de2c545f35b24735f4540baf5903", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EleutherAI\/llemma_34b", + "Average \u2b06\ufe0f": 59.34, + "ARC": 55.29, + "HellaSwag": 75.08, + "MMLU": 58.93, + "TruthfulQA": 40.31, + "Winogrande": 75.53, + "GSM8K": 50.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 71.0, + "Available on the hub": true, + "Model sha": "08634a81f7bc7343f94d1c82fae461ad9b03e233", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/SynthIA-7B-v1.3", + "Average \u2b06\ufe0f": 59.34, + "ARC": 62.12, + "HellaSwag": 83.45, + "MMLU": 62.65, + "TruthfulQA": 51.37, + "Winogrande": 78.85, + "GSM8K": 17.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 137.0, + "Available on the hub": true, + "Model sha": "8e6d0b18be876e0ebfff47d6c4f33d776f189971", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "bavest\/fin-llama-33b-merged", + "Average \u2b06\ufe0f": 59.33, + "ARC": 65.02, + "HellaSwag": 86.2, + "MMLU": 58.73, + "TruthfulQA": 49.75, + "Winogrande": 80.03, + "GSM8K": 16.22, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "17114520801da7b9599fe7a9fdf238915713a59b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhanushreddy29\/BrokenKeyboardMerge", + "Average \u2b06\ufe0f": 59.33, + "ARC": 59.73, + "HellaSwag": 81.25, + "MMLU": 58.36, + "TruthfulQA": 52.0, + "Winogrande": 78.69, + "GSM8K": 25.93, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "79693860dd86978c3b3de3fefe3b0664c9183e07", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "manishiitg\/open-aditi-hi-v2", + "Average \u2b06\ufe0f": 59.31, + "ARC": 59.39, + "HellaSwag": 82.01, + "MMLU": 61.41, + "TruthfulQA": 45.84, + "Winogrande": 77.19, + "GSM8K": 30.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "a142544973d7baa480ca71145ae297343ed84d38", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Walmart-the-bag\/MysticFusion-13B", + "Average \u2b06\ufe0f": 59.31, + "ARC": 61.35, + "HellaSwag": 84.43, + "MMLU": 57.29, + "TruthfulQA": 51.98, + "Winogrande": 76.01, + "GSM8K": 24.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "02255943c6eff59ef6bd17e1a43a37ce3751ff5e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ariellee\/SuperPlatty-30B", + "Average \u2b06\ufe0f": 59.3, + "ARC": 65.78, + "HellaSwag": 83.95, + "MMLU": 62.57, + "TruthfulQA": 53.52, + "Winogrande": 80.35, + "GSM8K": 9.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "017e1c32bca060107337dbf26db2044a7caa56f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SuperAGI\/SAM", + "Average \u2b06\ufe0f": 59.3, + "ARC": 59.39, + "HellaSwag": 82.31, + "MMLU": 62.15, + "TruthfulQA": 52.64, + "Winogrande": 76.4, + "GSM8K": 22.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "ce1fb6a278121df73eee5d7d39dc0d30b214a1b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "deepseek-ai\/deepseek-llm-7b-chat", + "Average \u2b06\ufe0f": 59.27, + "ARC": 55.72, + "HellaSwag": 79.38, + "MMLU": 51.77, + "TruthfulQA": 47.92, + "Winogrande": 74.9, + "GSM8K": 45.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 58.0, + "Available on the hub": true, + "Model sha": "afbda8b347ec881666061fa67447046fc5164ec8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Norquinal\/Mistral-7B-claude-instruct", + "Average \u2b06\ufe0f": 59.27, + "ARC": 63.23, + "HellaSwag": 84.99, + "MMLU": 63.84, + "TruthfulQA": 47.47, + "Winogrande": 78.14, + "GSM8K": 17.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "faff0de73681ad1f0500169ae18d7a5ff424eb7f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Venomia-1.1-m7", + "Average \u2b06\ufe0f": 59.27, + "ARC": 58.45, + "HellaSwag": 83.04, + "MMLU": 56.39, + "TruthfulQA": 47.21, + "Winogrande": 74.43, + "GSM8K": 36.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "00dd78ef6ee386c860f9136b9ef703a4c141e7f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mergedlm\/zephyrnotus-11b-alpha", + "Average \u2b06\ufe0f": 59.26, + "ARC": 61.35, + "HellaSwag": 82.8, + "MMLU": 60.67, + "TruthfulQA": 57.22, + "Winogrande": 76.4, + "GSM8K": 17.13, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a6f74e800b6c77261a1d212bb3e6b2752cbedef9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/Synatra-7B-v0.3-RP", + "Average \u2b06\ufe0f": 59.26, + "ARC": 62.2, + "HellaSwag": 82.29, + "MMLU": 60.8, + "TruthfulQA": 52.64, + "Winogrande": 76.48, + "GSM8K": 21.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "372f6e0ab2c20b93e0c42218f76a71a4f9bb282e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BlueNipples\/TimeCrystal-l2-13B", + "Average \u2b06\ufe0f": 59.26, + "ARC": 61.18, + "HellaSwag": 83.71, + "MMLU": 56.46, + "TruthfulQA": 51.3, + "Winogrande": 75.37, + "GSM8K": 27.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "f0076c437e766880841dc1768693dc745d093b8b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "sethuiyer\/Aika-7B", + "Average \u2b06\ufe0f": 59.25, + "ARC": 65.36, + "HellaSwag": 81.49, + "MMLU": 53.91, + "TruthfulQA": 51.22, + "Winogrande": 77.74, + "GSM8K": 25.78, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "00589aa6b5081b35c38103071c3901d191d5ecf2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sethuiyer\/Dr_Samantha_7b_mistral", + "Average \u2b06\ufe0f": 59.25, + "ARC": 60.41, + "HellaSwag": 83.65, + "MMLU": 63.14, + "TruthfulQA": 41.37, + "Winogrande": 75.45, + "GSM8K": 31.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e0201aa9423f082a4182cbf910d75ba438528ddb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gaodrew\/gaodrew-llama-30b-instruct-2048-Open-Platypus-100steps", + "Average \u2b06\ufe0f": 59.22, + "ARC": 61.52, + "HellaSwag": 84.06, + "MMLU": 60.23, + "TruthfulQA": 51.05, + "Winogrande": 80.82, + "GSM8K": 17.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1114ff08ed15ef417502da58f0237d2f6650c9ce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Xenon1\/Xenon-1", + "Average \u2b06\ufe0f": 59.21, + "ARC": 55.29, + "HellaSwag": 81.56, + "MMLU": 61.22, + "TruthfulQA": 56.68, + "Winogrande": 78.69, + "GSM8K": 21.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "70bd2d2359875ec03a3b1e82cc653334dfe2e721", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen-7B", + "Average \u2b06\ufe0f": 59.19, + "ARC": 51.37, + "HellaSwag": 78.47, + "MMLU": 59.84, + "TruthfulQA": 47.79, + "Winogrande": 72.69, + "GSM8K": 44.96, + "Type": "pretrained", + "Architecture": "QWenLMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 330.0, + "Available on the hub": true, + "Model sha": "c9bdb955021a80ae26fa6978891996dbe4951d8d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bofenghuang\/vigostral-7b-chat", + "Average \u2b06\ufe0f": 59.18, + "ARC": 62.63, + "HellaSwag": 84.34, + "MMLU": 63.53, + "TruthfulQA": 49.24, + "Winogrande": 78.61, + "GSM8K": 16.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "969fbfc7a91f53c8562a2c48a3c24dd3745d5a97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Borealis-10.7B-DPO", + "Average \u2b06\ufe0f": 59.18, + "ARC": 57.94, + "HellaSwag": 81.21, + "MMLU": 60.74, + "TruthfulQA": 46.37, + "Winogrande": 75.45, + "GSM8K": 33.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.7, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "9d6e34fa51cd3c4745a044fbb2bca91b1c9a9f5a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Locutusque\/UltraQwen-7B", + "Average \u2b06\ufe0f": 59.17, + "ARC": 51.71, + "HellaSwag": 77.93, + "MMLU": 59.16, + "TruthfulQA": 48.2, + "Winogrande": 73.95, + "GSM8K": 44.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "dc90ee7e2014b4fc862fa84868373982bb106fbd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/PiVoT-0.1-Evil-a", + "Average \u2b06\ufe0f": 59.16, + "ARC": 59.64, + "HellaSwag": 81.48, + "MMLU": 58.94, + "TruthfulQA": 39.23, + "Winogrande": 75.3, + "GSM8K": 40.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 36.0, + "Available on the hub": true, + "Model sha": "b6e20287ba4156f06b4288d4003acc677040527f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "FPHam\/Karen_TheEditor_V2_STRICT_Mistral_7B", + "Average \u2b06\ufe0f": 59.13, + "ARC": 59.56, + "HellaSwag": 81.79, + "MMLU": 59.56, + "TruthfulQA": 49.36, + "Winogrande": 74.35, + "GSM8K": 30.17, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "0935960b2765aa23d7a63c49873361b09dd12f60", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PeanutJar\/Mistral-v0.1-PeanutButter-v0.0.0-7B", + "Average \u2b06\ufe0f": 59.09, + "ARC": 62.2, + "HellaSwag": 84.1, + "MMLU": 64.14, + "TruthfulQA": 46.94, + "Winogrande": 78.69, + "GSM8K": 18.5, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9609a969ba6429b84e538d96afac55eb133a9983", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/test-case-1", + "Average \u2b06\ufe0f": 59.09, + "ARC": 57.17, + "HellaSwag": 79.47, + "MMLU": 56.41, + "TruthfulQA": 53.11, + "Winogrande": 76.32, + "GSM8K": 32.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "35203580388abb5beb595b57630258f415c4dd03", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/Noromaid-7B-0.4-DPO", + "Average \u2b06\ufe0f": 59.08, + "ARC": 62.29, + "HellaSwag": 84.32, + "MMLU": 63.2, + "TruthfulQA": 42.28, + "Winogrande": 76.95, + "GSM8K": 25.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "47a417a2167064112038e71f2be30d7293eb485d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "abdulrahman-nuzha\/finetuned-Mistral-5000-v1.0", + "Average \u2b06\ufe0f": 59.08, + "ARC": 59.9, + "HellaSwag": 82.37, + "MMLU": 61.68, + "TruthfulQA": 41.17, + "Winogrande": 78.3, + "GSM8K": 31.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e8050c54d484d7e0a885b9d97a0781f0dd2e745e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HuggingFaceH4\/zephyr-7b-beta", + "Average \u2b06\ufe0f": 59.08, + "ARC": 62.03, + "HellaSwag": 84.53, + "MMLU": 61.06, + "TruthfulQA": 57.44, + "Winogrande": 78.06, + "GSM8K": 11.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1312.0, + "Available on the hub": true, + "Model sha": "8af01af3d4f9dc9b962447180d6d0f8c5315da86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "osanseviero\/mistral-instruct-slerp", + "Average \u2b06\ufe0f": 59.08, + "ARC": 57.42, + "HellaSwag": 78.34, + "MMLU": 55.19, + "TruthfulQA": 57.61, + "Winogrande": 75.14, + "GSM8K": 30.78, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1994dd1daadcfd88c471531e6a264271d6e07b4d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NurtureAI\/openchat_3.5-16k", + "Average \u2b06\ufe0f": 59.03, + "ARC": 63.31, + "HellaSwag": 83.58, + "MMLU": 61.9, + "TruthfulQA": 43.47, + "Winogrande": 80.11, + "GSM8K": 21.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 30.0, + "Available on the hub": true, + "Model sha": "e8d66e7fb2ebb918f468137ea5fa3dc13ddc69da", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "garage-bAInd\/Platypus-30B", + "Average \u2b06\ufe0f": 59.03, + "ARC": 64.59, + "HellaSwag": 84.26, + "MMLU": 64.23, + "TruthfulQA": 45.35, + "Winogrande": 81.37, + "GSM8K": 14.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "c5d21054f8dd71099696bd7790df07ac54990f29", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lilloukas\/Platypus-30B", + "Average \u2b06\ufe0f": 59.03, + "ARC": 64.59, + "HellaSwag": 84.24, + "MMLU": 64.19, + "TruthfulQA": 45.35, + "Winogrande": 81.37, + "GSM8K": 14.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "979ad39b58a8e4a9419b7bc7a0dc8419f3912e71", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/orca_mini_v3_13B-GPTQ", + "Average \u2b06\ufe0f": 59.01, + "ARC": 61.95, + "HellaSwag": 81.56, + "MMLU": 56.1, + "TruthfulQA": 49.22, + "Winogrande": 75.77, + "GSM8K": 29.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.23, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "7b7a2dcd946f393e26215268c4c7e0699be2bbd8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/zephyr-alpha-Nebula-v2-7B", + "Average \u2b06\ufe0f": 59.01, + "ARC": 58.62, + "HellaSwag": 83.05, + "MMLU": 56.68, + "TruthfulQA": 58.28, + "Winogrande": 73.56, + "GSM8K": 23.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e8f1fd1acceda7fb662340f5afe312a7ef030374", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "unaidedelf87777\/wizard-mistral-v0.1", + "Average \u2b06\ufe0f": 59.01, + "ARC": 61.77, + "HellaSwag": 83.51, + "MMLU": 63.99, + "TruthfulQA": 47.46, + "Winogrande": 78.3, + "GSM8K": 19.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b66724f8195e7b76289f8f3f72a98392557c46ad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alignment-handbook\/zephyr-7b-sft-qlora", + "Average \u2b06\ufe0f": 59.0, + "ARC": 60.07, + "HellaSwag": 82.36, + "MMLU": 61.65, + "TruthfulQA": 38.88, + "Winogrande": 76.8, + "GSM8K": 34.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "156bec577ff12a65236cfc90860dcc61e96c6fd6", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "ehartford\/samantha-1.1-llama-33b", + "Average \u2b06\ufe0f": 58.98, + "ARC": 67.83, + "HellaSwag": 85.55, + "MMLU": 58.79, + "TruthfulQA": 61.19, + "Winogrande": 76.48, + "GSM8K": 4.02, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ad8892a17be1372f611203a4cf71560cc337e458", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "osanseviero\/mistral-instruct-frankenmerge", + "Average \u2b06\ufe0f": 58.96, + "ARC": 58.19, + "HellaSwag": 83.26, + "MMLU": 59.53, + "TruthfulQA": 66.48, + "Winogrande": 75.06, + "GSM8K": 11.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "af5cbc3a435aab75424e4ecc75f041f2eda133ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Dans-DiscountModels\/Mistral-7b-FFT-Test3", + "Average \u2b06\ufe0f": 58.96, + "ARC": 60.24, + "HellaSwag": 82.36, + "MMLU": 62.2, + "TruthfulQA": 44.36, + "Winogrande": 77.82, + "GSM8K": 26.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ff6ab8204162794d7d74297d60acb741c2ef8e3a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Hercules-1.0-Mistral-7B", + "Average \u2b06\ufe0f": 58.95, + "ARC": 57.08, + "HellaSwag": 81.13, + "MMLU": 58.98, + "TruthfulQA": 49.47, + "Winogrande": 77.19, + "GSM8K": 29.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "28c4847fbd13acc613078092ddfa2995ba6cf470", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/rezephyr-dpo", + "Average \u2b06\ufe0f": 58.95, + "ARC": 57.59, + "HellaSwag": 81.75, + "MMLU": 60.55, + "TruthfulQA": 44.32, + "Winogrande": 77.03, + "GSM8K": 32.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2be4ee1d2a8e693bb68031f719d12642d9e47b13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Tess-XS-v1.0", + "Average \u2b06\ufe0f": 58.95, + "ARC": 61.43, + "HellaSwag": 83.82, + "MMLU": 64.1, + "TruthfulQA": 47.12, + "Winogrande": 78.93, + "GSM8K": 18.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a581ab1793366ff2d5f3c966ff0e7b8b1149d775", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/Noromaid-7B-0.4-DPO", + "Average \u2b06\ufe0f": 58.93, + "ARC": 62.2, + "HellaSwag": 84.41, + "MMLU": 63.14, + "TruthfulQA": 42.34, + "Winogrande": 76.95, + "GSM8K": 24.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "47a417a2167064112038e71f2be30d7293eb485d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "codellama\/CodeLlama-70b-hf", + "Average \u2b06\ufe0f": 58.93, + "ARC": 56.74, + "HellaSwag": 78.21, + "MMLU": 59.67, + "TruthfulQA": 39.79, + "Winogrande": 75.22, + "GSM8K": 43.97, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 273.0, + "Available on the hub": true, + "Model sha": "4570a4edc524fb9f20f605b417bb43828fa5997a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Henk717\/chronoboros-33B", + "Average \u2b06\ufe0f": 58.92, + "ARC": 63.91, + "HellaSwag": 85.0, + "MMLU": 59.44, + "TruthfulQA": 49.83, + "Winogrande": 80.35, + "GSM8K": 15.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "a4deca117c5fa48f2cdc49ed2e2596046201d688", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "akjindal53244\/Mistral-7B-v0.1-Open-Platypus", + "Average \u2b06\ufe0f": 58.92, + "ARC": 62.37, + "HellaSwag": 85.08, + "MMLU": 63.79, + "TruthfulQA": 47.33, + "Winogrande": 77.66, + "GSM8K": 17.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "aa2c84e89c4c8a10e0569e45021b59e6d1c08bda", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mwitiderrick\/SwahiliInstruct-v0.1", + "Average \u2b06\ufe0f": 58.92, + "ARC": 57.59, + "HellaSwag": 80.92, + "MMLU": 57.0, + "TruthfulQA": 58.08, + "Winogrande": 74.66, + "GSM8K": 25.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06ae9044dac3c8f7cf67f4fd33986c5b79dbe69e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "upstage\/llama-30b-instruct", + "Average \u2b06\ufe0f": 58.91, + "ARC": 62.46, + "HellaSwag": 86.23, + "MMLU": 59.37, + "TruthfulQA": 52.78, + "Winogrande": 80.51, + "GSM8K": 12.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": false, + "Model sha": "fea4312379557e8a1e8073965f560798de369edd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mncai\/Mistral-7B-OpenOrca-1k", + "Average \u2b06\ufe0f": 58.9, + "ARC": 62.97, + "HellaSwag": 84.66, + "MMLU": 62.2, + "TruthfulQA": 52.96, + "Winogrande": 78.61, + "GSM8K": 11.98, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "ae9e37811a54ffe45f41a572c7e68363aa11b062", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/test-case-5", + "Average \u2b06\ufe0f": 58.89, + "ARC": 56.57, + "HellaSwag": 79.04, + "MMLU": 55.73, + "TruthfulQA": 50.0, + "Winogrande": 76.4, + "GSM8K": 35.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3ce1dc83a11f5875e876ca7efb43643901e0ae1f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/zephyr-7b-beta-MultiLoRA-mmlu-merged", + "Average \u2b06\ufe0f": 58.89, + "ARC": 57.94, + "HellaSwag": 81.43, + "MMLU": 58.57, + "TruthfulQA": 51.98, + "Winogrande": 76.64, + "GSM8K": 26.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a01728a56fbe14f6f348052a748c8c4c89bbc5f1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/manticore-30b-chat-pyg-alpha", + "Average \u2b06\ufe0f": 58.86, + "ARC": 64.16, + "HellaSwag": 84.38, + "MMLU": 57.49, + "TruthfulQA": 51.57, + "Winogrande": 79.48, + "GSM8K": 16.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": false, + "Model sha": "0cff8e9718e57202171003d556d2e6630061879d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-code-mistral-7b-v1.0", + "Average \u2b06\ufe0f": 58.85, + "ARC": 60.58, + "HellaSwag": 83.75, + "MMLU": 62.98, + "TruthfulQA": 47.9, + "Winogrande": 78.69, + "GSM8K": 19.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "753852b8cb52dc5f0411568e98c0cb445a7835dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "qblocks\/mistral_7b_norobots", + "Average \u2b06\ufe0f": 58.85, + "ARC": 58.96, + "HellaSwag": 80.57, + "MMLU": 57.66, + "TruthfulQA": 41.91, + "Winogrande": 75.61, + "GSM8K": 38.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "36dde2c5b08140d612042d1ae047dd7551b7e15b", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Henk717\/airochronos-33B", + "Average \u2b06\ufe0f": 58.84, + "ARC": 64.42, + "HellaSwag": 85.21, + "MMLU": 59.79, + "TruthfulQA": 50.59, + "Winogrande": 79.32, + "GSM8K": 13.72, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "06843c6693cc265dabb464c818a3d3713239721a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/Mistral-11B-SynthIAirOmniMix", + "Average \u2b06\ufe0f": 58.84, + "ARC": 62.46, + "HellaSwag": 83.13, + "MMLU": 63.47, + "TruthfulQA": 55.69, + "Winogrande": 76.4, + "GSM8K": 11.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "19694dc88e74a018d54bac6070cf521dff6d4397", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PulsarAI\/Nebula-v2-7B", + "Average \u2b06\ufe0f": 58.82, + "ARC": 58.7, + "HellaSwag": 83.06, + "MMLU": 57.61, + "TruthfulQA": 46.72, + "Winogrande": 75.14, + "GSM8K": 31.69, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d2a5611f7d7c37bfa2270d1823bceef01c0be383", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/scarlett-33b", + "Average \u2b06\ufe0f": 58.81, + "ARC": 67.75, + "HellaSwag": 85.48, + "MMLU": 58.98, + "TruthfulQA": 61.05, + "Winogrande": 76.8, + "GSM8K": 2.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "305eea72fb9fe2ac5929a62483ea51f152bcc060", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Dans-DiscountModels\/Mistral-7b-FFT-Test3", + "Average \u2b06\ufe0f": 58.79, + "ARC": 60.41, + "HellaSwag": 82.31, + "MMLU": 62.45, + "TruthfulQA": 44.33, + "Winogrande": 77.58, + "GSM8K": 25.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ff6ab8204162794d7d74297d60acb741c2ef8e3a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "freeCS-dot-org\/Zero-7B-test-3", + "Average \u2b06\ufe0f": 58.77, + "ARC": 64.25, + "HellaSwag": 79.85, + "MMLU": 53.49, + "TruthfulQA": 58.3, + "Winogrande": 76.32, + "GSM8K": 20.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ddcd86b0ef66dd8b7d7b9418b88f3fbc1cfdc828", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/Noromaid-13b-v0.3", + "Average \u2b06\ufe0f": 58.77, + "ARC": 62.8, + "HellaSwag": 84.42, + "MMLU": 56.86, + "TruthfulQA": 50.73, + "Winogrande": 74.74, + "GSM8K": 23.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "1013d7e539e53c15e5285ed27902a713c8caad09", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-llama-30b", + "Average \u2b06\ufe0f": 58.77, + "ARC": 64.25, + "HellaSwag": 83.64, + "MMLU": 58.23, + "TruthfulQA": 53.2, + "Winogrande": 77.43, + "GSM8K": 15.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7f035eabd1d0e7b38ace395847a623f475d90da8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Henk717\/airochronos-33B", + "Average \u2b06\ufe0f": 58.75, + "ARC": 64.25, + "HellaSwag": 85.2, + "MMLU": 59.83, + "TruthfulQA": 50.56, + "Winogrande": 79.08, + "GSM8K": 13.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "06843c6693cc265dabb464c818a3d3713239721a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-m-7b-3.1.2", + "Average \u2b06\ufe0f": 58.75, + "ARC": 61.86, + "HellaSwag": 83.51, + "MMLU": 61.91, + "TruthfulQA": 53.75, + "Winogrande": 77.58, + "GSM8K": 13.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 41.0, + "Available on the hub": true, + "Model sha": "e9a7f0271fa442d65bf6be87feeb3f4de2f5760e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Novocoders\/Mistral-NeuralDPO-v0.7", + "Average \u2b06\ufe0f": 58.74, + "ARC": 65.87, + "HellaSwag": 84.4, + "MMLU": 57.6, + "TruthfulQA": 39.91, + "Winogrande": 79.56, + "GSM8K": 25.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3e86d80ad5268021c77f0b86b047df5467b174f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/dromedary-65b-lora-HF", + "Average \u2b06\ufe0f": 58.73, + "ARC": 61.6, + "HellaSwag": 82.53, + "MMLU": 63.08, + "TruthfulQA": 38.82, + "Winogrande": 78.93, + "GSM8K": 27.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 65.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "3fa4546259d6bbd6b5d637484c325ab19181a73c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ausboss\/llama-30b-supercot", + "Average \u2b06\ufe0f": 58.73, + "ARC": 64.85, + "HellaSwag": 85.08, + "MMLU": 56.56, + "TruthfulQA": 53.96, + "Winogrande": 80.03, + "GSM8K": 11.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 126.0, + "Available on the hub": false, + "Model sha": "dc9d81f454d286ea040c5cd45b058aecaa51c13e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openbmb\/UltraLM-13b-v2.0", + "Average \u2b06\ufe0f": 58.72, + "ARC": 62.63, + "HellaSwag": 81.49, + "MMLU": 56.17, + "TruthfulQA": 49.48, + "Winogrande": 76.48, + "GSM8K": 26.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "a452045c96ae62379a98ef0d85666616a66e78a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/CollectiveCognition-v1.1-Mistral-7B-dare-0.85", + "Average \u2b06\ufe0f": 58.72, + "ARC": 61.01, + "HellaSwag": 84.31, + "MMLU": 64.34, + "TruthfulQA": 44.87, + "Winogrande": 78.85, + "GSM8K": 18.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7ecfa4c5b100565bf8cfdfa7442e9772d28a9a23", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aeala\/GPT4-x-AlpacaDente2-30b", + "Average \u2b06\ufe0f": 58.71, + "ARC": 60.58, + "HellaSwag": 81.81, + "MMLU": 56.63, + "TruthfulQA": 48.38, + "Winogrande": 78.14, + "GSM8K": 26.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 32.0, + "Available on the hub": false, + "Model sha": "9fe5a8dada738f44e7ee9293b2140ae0be021787", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bhenrym14\/mistral-7b-platypus-fp16", + "Average \u2b06\ufe0f": 58.71, + "ARC": 63.05, + "HellaSwag": 84.15, + "MMLU": 64.11, + "TruthfulQA": 45.07, + "Winogrande": 78.53, + "GSM8K": 17.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": false, + "Model sha": "d836a261afa0871d3734a7dfd1a28dc23c173ea7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hfl\/chinese-mixtral", + "Average \u2b06\ufe0f": 58.69, + "ARC": 67.58, + "HellaSwag": 85.34, + "MMLU": 70.38, + "TruthfulQA": 46.86, + "Winogrande": 82.0, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7b37775efb34a0734efd60a32781bd706c60e85b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "jilp00\/Nous-Hermes-2-SOLAR-10.7B-v1.1", + "Average \u2b06\ufe0f": 58.69, + "ARC": 63.99, + "HellaSwag": 82.72, + "MMLU": 65.85, + "TruthfulQA": 56.97, + "Winogrande": 81.22, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8e1cbfa67643f49be67a6021db933cdd941a6d2f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/Dolphin-Nebula-7B", + "Average \u2b06\ufe0f": 58.69, + "ARC": 55.2, + "HellaSwag": 78.57, + "MMLU": 53.44, + "TruthfulQA": 57.97, + "Winogrande": 73.88, + "GSM8K": 33.06, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c14b3545066e5ee5562c1724a037b41db95f1f0d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2", + "Average \u2b06\ufe0f": 58.67, + "ARC": 60.32, + "HellaSwag": 82.88, + "MMLU": 59.79, + "TruthfulQA": 42.36, + "Winogrande": 76.56, + "GSM8K": 30.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a6b293b6a0fc4c3d0eed5dcf41055ef851e2b29c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/72B-preview-canary-llamafied-qwen-llamafy-unbias-qkv", + "Average \u2b06\ufe0f": 58.67, + "ARC": 53.07, + "HellaSwag": 63.13, + "MMLU": 67.39, + "TruthfulQA": 57.62, + "Winogrande": 75.14, + "GSM8K": 35.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "dc66cf314292f3bfd5a2eed74018671effac6405", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PeanutJar\/Mistral-v0.1-PeanutButter-v0.0.2-7B", + "Average \u2b06\ufe0f": 58.66, + "ARC": 61.77, + "HellaSwag": 84.11, + "MMLU": 64.38, + "TruthfulQA": 45.92, + "Winogrande": 78.37, + "GSM8K": 17.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f4d471d7a9447d0969a58d5b3146d50cfa3005b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "microsoft\/Orca-2-13b", + "Average \u2b06\ufe0f": 58.64, + "ARC": 60.67, + "HellaSwag": 79.81, + "MMLU": 60.37, + "TruthfulQA": 56.41, + "Winogrande": 76.64, + "GSM8K": 17.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 624.0, + "Available on the hub": true, + "Model sha": "2539ff53e6baa4cc603774ad5a2d646f4041ea4e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "dfurman\/falcon-40b-openassistant-peft", + "Average \u2b06\ufe0f": 58.63, + "ARC": 62.63, + "HellaSwag": 85.59, + "MMLU": 57.77, + "TruthfulQA": 51.02, + "Winogrande": 81.45, + "GSM8K": 13.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 40.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3d5084b6fbcb9f9f36493d9fd1e3795b0b9860f0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/SOLAR-Platypus-10.7B-v1", + "Average \u2b06\ufe0f": 58.62, + "ARC": 61.69, + "HellaSwag": 84.23, + "MMLU": 60.37, + "TruthfulQA": 51.58, + "Winogrande": 82.79, + "GSM8K": 11.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e9314a1f1ca7f790491c177e7720fb14851ef603", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EllieS\/zephyr-7b-dpo-lora-pubmedqa-ultrafeedback", + "Average \u2b06\ufe0f": 58.62, + "ARC": 60.49, + "HellaSwag": 83.13, + "MMLU": 60.58, + "TruthfulQA": 44.79, + "Winogrande": 76.24, + "GSM8K": 26.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b688325e94904c69ab3815543d5ec51e1e869e8b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "quantumaikr\/QuantumLM-70B-hf", + "Average \u2b06\ufe0f": 58.61, + "ARC": 59.47, + "HellaSwag": 83.02, + "MMLU": 62.25, + "TruthfulQA": 53.39, + "Winogrande": 78.77, + "GSM8K": 14.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e13dd23ae5e611e959b6c8d5bc47bf4fd37cd9d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CobraMamba\/mamba-gpt-7b-v1", + "Average \u2b06\ufe0f": 58.61, + "ARC": 61.26, + "HellaSwag": 84.1, + "MMLU": 63.46, + "TruthfulQA": 46.34, + "Winogrande": 79.16, + "GSM8K": 17.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e64d658b397748e409d9633fd24fc5a6df429600", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/koOpenChat-sft", + "Average \u2b06\ufe0f": 58.61, + "ARC": 59.81, + "HellaSwag": 78.73, + "MMLU": 61.32, + "TruthfulQA": 51.24, + "Winogrande": 76.4, + "GSM8K": 24.18, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "47472b36e181694422564b130ee075ffa596537d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gradientputri\/MegaMix-T1-13B", + "Average \u2b06\ufe0f": 58.61, + "ARC": 61.35, + "HellaSwag": 83.44, + "MMLU": 58.49, + "TruthfulQA": 48.19, + "Winogrande": 76.09, + "GSM8K": 24.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "55d31300f8972b56320855bb40efb5e3d1e1a6fc", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/alignment-handbook-zephyr-7b_ppo_5e7step_51", + "Average \u2b06\ufe0f": 58.59, + "ARC": 59.73, + "HellaSwag": 82.52, + "MMLU": 59.76, + "TruthfulQA": 41.46, + "Winogrande": 77.19, + "GSM8K": 30.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "58adefcddc81bda70caea1bf7b3d377b5e585942", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/dolphin-2.0-mistral-7b", + "Average \u2b06\ufe0f": 58.58, + "ARC": 59.22, + "HellaSwag": 80.26, + "MMLU": 56.9, + "TruthfulQA": 61.09, + "Winogrande": 75.37, + "GSM8K": 18.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c673387016c622fd0a707426953c03957398bc37", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "S4sch\/zephyr-neural-chat-frankenmerge11b", + "Average \u2b06\ufe0f": 58.57, + "ARC": 61.52, + "HellaSwag": 84.09, + "MMLU": 61.51, + "TruthfulQA": 60.63, + "Winogrande": 76.24, + "GSM8K": 7.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 11.39, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "f915831e904e0dcda760873aa16a35daf5ac9e6d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "hfl\/chinese-mixtral", + "Average \u2b06\ufe0f": 58.57, + "ARC": 67.49, + "HellaSwag": 85.25, + "MMLU": 70.31, + "TruthfulQA": 46.75, + "Winogrande": 81.61, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7b37775efb34a0734efd60a32781bd706c60e85b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "umd-zhou-lab\/claude2-alpaca-13B", + "Average \u2b06\ufe0f": 58.57, + "ARC": 61.18, + "HellaSwag": 84.21, + "MMLU": 55.93, + "TruthfulQA": 45.02, + "Winogrande": 76.8, + "GSM8K": 28.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1d670244f2f70ab35219c9bbf83eef4f5dc28730", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "lmsys\/vicuna-33b-v1.3", + "Average \u2b06\ufe0f": 58.54, + "ARC": 62.12, + "HellaSwag": 83.0, + "MMLU": 59.22, + "TruthfulQA": 56.16, + "Winogrande": 77.03, + "GSM8K": 13.72, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 273.0, + "Available on the hub": false, + "Model sha": "ef8d6becf883fb3ce52e3706885f761819477ab4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/72B-preview-canary-llamafied-qwen-llamafy-unbias-qkv", + "Average \u2b06\ufe0f": 58.54, + "ARC": 52.56, + "HellaSwag": 62.99, + "MMLU": 67.45, + "TruthfulQA": 57.61, + "Winogrande": 75.14, + "GSM8K": 35.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 72.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "dc66cf314292f3bfd5a2eed74018671effac6405", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gradientputri\/MegaMix-A1-13B", + "Average \u2b06\ufe0f": 58.52, + "ARC": 61.6, + "HellaSwag": 83.49, + "MMLU": 58.26, + "TruthfulQA": 47.48, + "Winogrande": 76.16, + "GSM8K": 24.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "14e0756c210bcf420fbf825e6b8087ee5c716e7f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NeverSleep\/Noromaid-13b-v0.2", + "Average \u2b06\ufe0f": 58.51, + "ARC": 60.92, + "HellaSwag": 84.04, + "MMLU": 57.67, + "TruthfulQA": 52.58, + "Winogrande": 74.11, + "GSM8K": 21.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "dad2d749b01cf10b65951dea6e130da8cc53e2c0", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/MLewd-ReMM-L2-Chat-20B", + "Average \u2b06\ufe0f": 58.49, + "ARC": 62.46, + "HellaSwag": 85.62, + "MMLU": 59.13, + "TruthfulQA": 55.63, + "Winogrande": 77.19, + "GSM8K": 10.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "cda06630a1d8173541431e5ce8bc17dcfaa37e5e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "manishiitg\/open-aditi-hi-v1", + "Average \u2b06\ufe0f": 58.49, + "ARC": 58.79, + "HellaSwag": 81.38, + "MMLU": 58.51, + "TruthfulQA": 42.34, + "Winogrande": 76.48, + "GSM8K": 33.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1f6cbcdf01831830ff0f25f6f0e84ec4e9337e72", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/Wizard-Vicuna-30B-Uncensored-GPTQ", + "Average \u2b06\ufe0f": 58.47, + "ARC": 61.09, + "HellaSwag": 82.4, + "MMLU": 56.46, + "TruthfulQA": 49.9, + "Winogrande": 77.66, + "GSM8K": 23.28, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 35.58, + "Hub \u2764\ufe0f": 520.0, + "Available on the hub": true, + "Model sha": "56a82ece7a9309189561a590e8f4d2fe0d4be92b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Intel\/neural-chat-7b-v3", + "Average \u2b06\ufe0f": 58.46, + "ARC": 67.15, + "HellaSwag": 83.29, + "MMLU": 62.26, + "TruthfulQA": 58.77, + "Winogrande": 78.06, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 62.0, + "Available on the hub": true, + "Model sha": "7a05c8a2151f7d32252d9ef5db10445c13ae1f20", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "posicube\/Llama2-chat-AYB-13B", + "Average \u2b06\ufe0f": 58.45, + "ARC": 63.4, + "HellaSwag": 84.79, + "MMLU": 59.34, + "TruthfulQA": 55.62, + "Winogrande": 76.24, + "GSM8K": 11.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "cc7ca1b8f906b9f62ace094540f4ff4124dd581a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/trurl-2-13b-pl-instruct_unload", + "Average \u2b06\ufe0f": 58.44, + "ARC": 59.9, + "HellaSwag": 79.99, + "MMLU": 78.66, + "TruthfulQA": 45.56, + "Winogrande": 74.35, + "GSM8K": 12.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "17f57642165e30a4025d6817bd47dcd80d0c5c4d", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/X-MythoChronos-13B", + "Average \u2b06\ufe0f": 58.43, + "ARC": 59.73, + "HellaSwag": 83.39, + "MMLU": 56.5, + "TruthfulQA": 53.55, + "Winogrande": 74.43, + "GSM8K": 22.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "8d302741466512f0621a594fce6bf5b8125c8d4c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CalderaAI\/30B-Lazarus", + "Average \u2b06\ufe0f": 58.4, + "ARC": 64.93, + "HellaSwag": 84.27, + "MMLU": 56.47, + "TruthfulQA": 58.65, + "Winogrande": 78.37, + "GSM8K": 7.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 119.0, + "Available on the hub": false, + "Model sha": "24da9e88f2b2b7946bc6fe9412d6728b9adc2c3d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PocketDoc\/Dans-PersonalityEngine-30b", + "Average \u2b06\ufe0f": 58.39, + "ARC": 63.48, + "HellaSwag": 84.37, + "MMLU": 58.99, + "TruthfulQA": 46.98, + "Winogrande": 80.98, + "GSM8K": 15.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "1990b46a2e2ac1f6282d961bce691ceceafed514", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "codemateai\/CodeMate-v0.1", + "Average \u2b06\ufe0f": 58.39, + "ARC": 55.55, + "HellaSwag": 78.03, + "MMLU": 55.31, + "TruthfulQA": 48.64, + "Winogrande": 72.61, + "GSM8K": 40.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "01015a269bdf5283e6749e9a4f5ff7ccfb216e57", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Cartinoe5930\/iDUS-8layers", + "Average \u2b06\ufe0f": 58.38, + "ARC": 59.3, + "HellaSwag": 81.34, + "MMLU": 63.22, + "TruthfulQA": 40.62, + "Winogrande": 76.24, + "GSM8K": 29.57, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5291ad4b5e6388ff2a346cfd783d119b0e17e0df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/SynthIA-7B-v1.3-dare-0.85", + "Average \u2b06\ufe0f": 58.38, + "ARC": 61.01, + "HellaSwag": 83.5, + "MMLU": 64.49, + "TruthfulQA": 43.77, + "Winogrande": 78.93, + "GSM8K": 18.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "91381d0ac625dcde542428ed6cb35177b4260923", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Uncensored-Frank-33B", + "Average \u2b06\ufe0f": 58.38, + "ARC": 62.12, + "HellaSwag": 83.3, + "MMLU": 57.57, + "TruthfulQA": 54.03, + "Winogrande": 76.56, + "GSM8K": 16.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "1c1f4e9256ac2be145a9106863ee9f2e9d701e74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "g-ronimo\/phi-2-OpenHermes-2.5", + "Average \u2b06\ufe0f": 58.38, + "ARC": 59.81, + "HellaSwag": 74.85, + "MMLU": 55.51, + "TruthfulQA": 43.86, + "Winogrande": 75.06, + "GSM8K": 41.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ee382f2c6f1006d6854a1b3cc26cbaa28eeab2cb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/alignment-handbook-zephyr-7b_ppo_5e7step_102", + "Average \u2b06\ufe0f": 58.37, + "ARC": 59.22, + "HellaSwag": 82.45, + "MMLU": 59.62, + "TruthfulQA": 41.56, + "Winogrande": 77.03, + "GSM8K": 30.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2624e0c1fb055d98bd6ee41670d46d534e01facc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "posicube\/Llama-chat-AY-13B", + "Average \u2b06\ufe0f": 58.34, + "ARC": 62.8, + "HellaSwag": 83.23, + "MMLU": 60.01, + "TruthfulQA": 55.95, + "Winogrande": 75.93, + "GSM8K": 12.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "66037b5ee553f7b878d796d2b2d5ada5734cc164", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/SynthIA-v1.3-Nebula-v2-7B", + "Average \u2b06\ufe0f": 58.33, + "ARC": 59.39, + "HellaSwag": 82.77, + "MMLU": 57.57, + "TruthfulQA": 50.62, + "Winogrande": 74.74, + "GSM8K": 24.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c6030620e9d4390d54ec221a18ff3e530f4dcd84", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kwchoi\/DPO_mistral_v01_7b_ultra_0131_1k_1epoch", + "Average \u2b06\ufe0f": 58.32, + "ARC": 55.97, + "HellaSwag": 76.78, + "MMLU": 55.97, + "TruthfulQA": 57.94, + "Winogrande": 73.4, + "GSM8K": 29.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d9049778b541c69946ec235b81985020e065fbff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CobraMamba\/mamba-gpt-7b-v2", + "Average \u2b06\ufe0f": 58.31, + "ARC": 61.95, + "HellaSwag": 83.83, + "MMLU": 61.74, + "TruthfulQA": 46.63, + "Winogrande": 78.45, + "GSM8K": 17.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "6439444e2c0b61253d3e61ae04fe0436717acc2f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont1", + "Average \u2b06\ufe0f": 58.29, + "ARC": 60.24, + "HellaSwag": 82.28, + "MMLU": 60.61, + "TruthfulQA": 40.55, + "Winogrande": 77.11, + "GSM8K": 28.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1ad23ee605793a7d2dd6a5030b293c68cc8f6f1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/30B-Lazarus-instruct-PL-lora_unload", + "Average \u2b06\ufe0f": 58.29, + "ARC": 62.8, + "HellaSwag": 84.13, + "MMLU": 56.87, + "TruthfulQA": 55.49, + "Winogrande": 79.08, + "GSM8K": 11.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "eeb29b35ceb6dd5c532f1e4e1235f1cdd3f51f23", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "concedo\/Vicuzard-30B-Uncensored", + "Average \u2b06\ufe0f": 58.26, + "ARC": 62.97, + "HellaSwag": 83.68, + "MMLU": 58.16, + "TruthfulQA": 52.27, + "Winogrande": 77.11, + "GSM8K": 15.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "e2329c05a6e59660ba3cbcc01adf30a78f852594", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PeanutJar\/Mistral-v0.1-PeanutButter-v0.0.5-SFT-7B-QLoRA", + "Average \u2b06\ufe0f": 58.24, + "ARC": 60.75, + "HellaSwag": 84.24, + "MMLU": 63.66, + "TruthfulQA": 44.94, + "Winogrande": 78.69, + "GSM8K": 17.13, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2609363766acf308877a71aba352e60d7c044b49", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TriadParty\/deepmoney-34b-200k-base", + "Average \u2b06\ufe0f": 58.21, + "ARC": 63.99, + "HellaSwag": 83.87, + "MMLU": 74.04, + "TruthfulQA": 45.93, + "Winogrande": 81.45, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "8ae3d155e57352d4b7fef1d60f74e8c8650a8ab7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-33b-gpt4-1.4", + "Average \u2b06\ufe0f": 58.2, + "ARC": 64.42, + "HellaSwag": 85.13, + "MMLU": 59.53, + "TruthfulQA": 50.47, + "Winogrande": 77.9, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "04e1e194247a95cc60ba3cd70d026bc94c1f1764", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/mistral-7b-platypus1k", + "Average \u2b06\ufe0f": 58.19, + "ARC": 61.6, + "HellaSwag": 82.93, + "MMLU": 63.16, + "TruthfulQA": 46.96, + "Winogrande": 78.14, + "GSM8K": 16.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c34c4a249ecf0cc391beba142a1f9cb23154fcd1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Riiid\/sheep-duck-llama-2-13b", + "Average \u2b06\ufe0f": 58.19, + "ARC": 63.14, + "HellaSwag": 84.52, + "MMLU": 59.89, + "TruthfulQA": 55.48, + "Winogrande": 76.95, + "GSM8K": 9.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "71edf22c49677d0239caf5f87d8139dd9cc79078", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Secbone\/llama-33B-instructed", + "Average \u2b06\ufe0f": 58.18, + "ARC": 64.59, + "HellaSwag": 86.17, + "MMLU": 60.5, + "TruthfulQA": 44.12, + "Winogrande": 79.32, + "GSM8K": 14.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7c40caaea4fe3264fd469dac428b0f9450e574a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "42MARU\/sitebunny-13b", + "Average \u2b06\ufe0f": 58.17, + "ARC": 63.14, + "HellaSwag": 83.64, + "MMLU": 59.91, + "TruthfulQA": 56.21, + "Winogrande": 76.72, + "GSM8K": 9.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "67107327d09c2f9bf3e4b316d97767c97f5a0804", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PocketDoc\/Dans-TotSirocco-7b", + "Average \u2b06\ufe0f": 58.16, + "ARC": 62.2, + "HellaSwag": 84.28, + "MMLU": 63.8, + "TruthfulQA": 46.04, + "Winogrande": 79.48, + "GSM8K": 13.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "824e3a4738818142374721306ce85b83770de24b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "martyn\/llama-megamerge-dare-13b", + "Average \u2b06\ufe0f": 58.15, + "ARC": 60.58, + "HellaSwag": 83.0, + "MMLU": 54.91, + "TruthfulQA": 45.76, + "Winogrande": 76.16, + "GSM8K": 28.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5529ddb255dbdabdd179bdc911f141c3f0d2fb3f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PocketDoc\/Dans-TotSirocco-7b", + "Average \u2b06\ufe0f": 58.15, + "ARC": 62.03, + "HellaSwag": 84.23, + "MMLU": 64.19, + "TruthfulQA": 46.49, + "Winogrande": 78.69, + "GSM8K": 13.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "824e3a4738818142374721306ce85b83770de24b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "rizla\/rizla54", + "Average \u2b06\ufe0f": 58.15, + "ARC": 58.19, + "HellaSwag": 78.74, + "MMLU": 61.29, + "TruthfulQA": 53.26, + "Winogrande": 76.8, + "GSM8K": 20.62, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 53.58, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ba0f54d38f2dc2be8d6a1035d55f848c6b1b6ab9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/Mistral-7B-OpenOrca-lora", + "Average \u2b06\ufe0f": 58.14, + "ARC": 61.95, + "HellaSwag": 83.62, + "MMLU": 64.16, + "TruthfulQA": 42.74, + "Winogrande": 79.08, + "GSM8K": 17.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "605dc043063cb9589c06883d839122920ed1eca5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Technoculture\/Medchator-2x7b", + "Average \u2b06\ufe0f": 58.13, + "ARC": 57.59, + "HellaSwag": 78.14, + "MMLU": 56.13, + "TruthfulQA": 48.77, + "Winogrande": 75.3, + "GSM8K": 32.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 11.07, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b25e7e678c6881b3599cd00387f0f622be6ae7e9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "caisarl76\/mistral-guanaco1k-ep2", + "Average \u2b06\ufe0f": 58.13, + "ARC": 60.07, + "HellaSwag": 82.76, + "MMLU": 61.5, + "TruthfulQA": 54.4, + "Winogrande": 78.06, + "GSM8K": 11.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9c9f31f213b69da7797c2c0630c17cf8f785fc13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "caisarl76\/Mistral-7B-guanaco1k-ep2", + "Average \u2b06\ufe0f": 58.13, + "ARC": 60.07, + "HellaSwag": 82.76, + "MMLU": 61.5, + "TruthfulQA": 54.4, + "Winogrande": 78.06, + "GSM8K": 11.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9c9f31f213b69da7797c2c0630c17cf8f785fc13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Stheno-1.8-L2-13B", + "Average \u2b06\ufe0f": 58.12, + "ARC": 63.48, + "HellaSwag": 84.12, + "MMLU": 58.57, + "TruthfulQA": 52.86, + "Winogrande": 76.4, + "GSM8K": 13.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "fe054ab749a69375285df40913a88bd40f1e2bf6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/2x-LoRA-Assemble-13B", + "Average \u2b06\ufe0f": 58.1, + "ARC": 63.65, + "HellaSwag": 83.47, + "MMLU": 59.82, + "TruthfulQA": 55.94, + "Winogrande": 76.48, + "GSM8K": 9.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1aca45d37eade21eb381aaefc9245b58ec3b7b26", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Cartinoe5930\/SOLAR-DUS-implement", + "Average \u2b06\ufe0f": 58.1, + "ARC": 59.56, + "HellaSwag": 81.18, + "MMLU": 63.68, + "TruthfulQA": 40.72, + "Winogrande": 76.48, + "GSM8K": 26.99, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bfce9b8f3e599767b3c3974b0a3cbbd1b7f2da6c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/Vicuzard-30B-Uncensored-instruct-PL-lora_unload", + "Average \u2b06\ufe0f": 58.09, + "ARC": 62.46, + "HellaSwag": 83.66, + "MMLU": 57.82, + "TruthfulQA": 50.94, + "Winogrande": 78.37, + "GSM8K": 15.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "652f03ac67b4293198d98b618e64285fb32a28e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bofenghuang\/vigogne-33b-instruct", + "Average \u2b06\ufe0f": 58.08, + "ARC": 63.05, + "HellaSwag": 85.0, + "MMLU": 58.32, + "TruthfulQA": 52.1, + "Winogrande": 78.85, + "GSM8K": 11.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "9c2b558b888e0ef8b4a72e0771db72a06a5c8474", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "tiiuae\/falcon-40b", + "Average \u2b06\ufe0f": 58.07, + "ARC": 61.86, + "HellaSwag": 85.28, + "MMLU": 56.89, + "TruthfulQA": 41.65, + "Winogrande": 81.29, + "GSM8K": 21.46, + "Type": "pretrained", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 40.0, + "Hub \u2764\ufe0f": 2381.0, + "Available on the hub": true, + "Model sha": "3d7c5902f1dc9da830979a826cd96114b3ba4ec1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mncai\/Mistral-7B-openplatypus-1k", + "Average \u2b06\ufe0f": 58.07, + "ARC": 60.15, + "HellaSwag": 84.25, + "MMLU": 59.84, + "TruthfulQA": 49.86, + "Winogrande": 76.87, + "GSM8K": 17.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dad401175da3782475a122008720ddc3338e2632", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TencentARC\/LLaMA-Pro-8B-Instruct", + "Average \u2b06\ufe0f": 58.06, + "ARC": 52.99, + "HellaSwag": 76.98, + "MMLU": 52.58, + "TruthfulQA": 49.43, + "Winogrande": 72.22, + "GSM8K": 44.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 8.36, + "Hub \u2764\ufe0f": 57.0, + "Available on the hub": true, + "Model sha": "209760d8bffdc49afa18afdb038b0cf921b19fe4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "camel-ai\/CAMEL-33B-Combined-Data", + "Average \u2b06\ufe0f": 58.06, + "ARC": 62.97, + "HellaSwag": 83.83, + "MMLU": 58.98, + "TruthfulQA": 50.21, + "Winogrande": 78.3, + "GSM8K": 14.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "62c74e7531625c1383bbbdc7c8346a996e9d1e21", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "scb10x\/typhoon-7b", + "Average \u2b06\ufe0f": 58.05, + "ARC": 58.53, + "HellaSwag": 81.55, + "MMLU": 59.54, + "TruthfulQA": 40.52, + "Winogrande": 76.56, + "GSM8K": 31.61, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 62.0, + "Available on the hub": true, + "Model sha": "35fb2f9cee5dbac35109effc816ca206962dad43", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Mistral-11B-v0.1", + "Average \u2b06\ufe0f": 58.05, + "ARC": 59.56, + "HellaSwag": 81.17, + "MMLU": 63.56, + "TruthfulQA": 40.67, + "Winogrande": 76.64, + "GSM8K": 26.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "e9698271ea1ab340bacfd5ebf0d77108a6f18a90", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/hippogriff-30b-chat", + "Average \u2b06\ufe0f": 58.05, + "ARC": 64.51, + "HellaSwag": 85.2, + "MMLU": 59.09, + "TruthfulQA": 48.42, + "Winogrande": 80.82, + "GSM8K": 10.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": false, + "Model sha": "64c10edf5312cd13704925b07413882d9e94c7a0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/airoboros-m-7b-3.1.2-dare-0.85", + "Average \u2b06\ufe0f": 58.03, + "ARC": 61.09, + "HellaSwag": 83.57, + "MMLU": 64.05, + "TruthfulQA": 43.64, + "Winogrande": 78.37, + "GSM8K": 17.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "b5bc02f4e1008bd3a72046a93ac2f4dd4bef02da", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "codellama\/CodeLlama-70b-Python-hf", + "Average \u2b06\ufe0f": 58.0, + "ARC": 55.12, + "HellaSwag": 78.48, + "MMLU": 56.17, + "TruthfulQA": 41.78, + "Winogrande": 73.01, + "GSM8K": 43.44, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 90.0, + "Available on the hub": true, + "Model sha": "79467981bab591dd6860707ed517d1186fbcfc1e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/Luban-Marcoroni-13B", + "Average \u2b06\ufe0f": 57.98, + "ARC": 63.65, + "HellaSwag": 82.92, + "MMLU": 58.7, + "TruthfulQA": 55.55, + "Winogrande": 77.03, + "GSM8K": 10.01, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bf152c36935acd67a9029c017f0c1ff2d7a92314", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/samantha-mistral-7b", + "Average \u2b06\ufe0f": 57.96, + "ARC": 63.4, + "HellaSwag": 84.1, + "MMLU": 61.36, + "TruthfulQA": 46.08, + "Winogrande": 76.8, + "GSM8K": 16.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7f9e40543fdff8c3e58eca0390c8a631829c1206", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "martyn\/llama2-megamerge-dare-13b-v2", + "Average \u2b06\ufe0f": 57.94, + "ARC": 59.39, + "HellaSwag": 80.93, + "MMLU": 55.26, + "TruthfulQA": 47.27, + "Winogrande": 75.53, + "GSM8K": 29.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d0ff28a0cb4a70b15f55a416fbae6979f4ae5775", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/Luban-Marcoroni-13B-v3", + "Average \u2b06\ufe0f": 57.94, + "ARC": 63.74, + "HellaSwag": 82.88, + "MMLU": 58.64, + "TruthfulQA": 55.56, + "Winogrande": 76.87, + "GSM8K": 9.93, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "9b68680ed8351ef8ef6948169e69a888af40002e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Stellaris-internlm2-20b-r256", + "Average \u2b06\ufe0f": 57.93, + "ARC": 61.09, + "HellaSwag": 82.22, + "MMLU": 66.01, + "TruthfulQA": 51.81, + "Winogrande": 85.24, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d137609421ccbe34f0275a469e33dae3e931adf7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Llamix2-Xwin-MoE-4x13B", + "Average \u2b06\ufe0f": 57.93, + "ARC": 60.41, + "HellaSwag": 82.96, + "MMLU": 56.24, + "TruthfulQA": 39.63, + "Winogrande": 75.14, + "GSM8K": 33.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 38.5, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "220833f87c233684e8a4b0e03126ffcdffce5229", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ericpolewski\/ASTS-PFAF", + "Average \u2b06\ufe0f": 57.93, + "ARC": 61.26, + "HellaSwag": 82.94, + "MMLU": 58.96, + "TruthfulQA": 43.74, + "Winogrande": 76.87, + "GSM8K": 23.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9c8f78a3ced78392dfcdf350628f5044e6b77122", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/Luban-Marcoroni-13B-v2", + "Average \u2b06\ufe0f": 57.92, + "ARC": 63.48, + "HellaSwag": 82.89, + "MMLU": 58.72, + "TruthfulQA": 55.56, + "Winogrande": 76.95, + "GSM8K": 9.93, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d7c704a08218dcc03963bc08e9113e281c056f53", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alnrg2arg\/blockchainlabs_7B_merged_test2_4_prune", + "Average \u2b06\ufe0f": 57.91, + "ARC": 60.58, + "HellaSwag": 77.74, + "MMLU": 52.27, + "TruthfulQA": 59.03, + "Winogrande": 76.4, + "GSM8K": 21.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "15b6cd5986ef27910202295530522cd433538a72", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "caisarl76\/Mistral-7B-OpenOrca-Guanaco-accu16", + "Average \u2b06\ufe0f": 57.91, + "ARC": 59.73, + "HellaSwag": 83.08, + "MMLU": 61.29, + "TruthfulQA": 50.81, + "Winogrande": 76.56, + "GSM8K": 16.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e83b8c1887c45473961a4ff36ae202ada1ca3d42", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "oh-yeontaek\/llama-2-13B-LoRA-assemble", + "Average \u2b06\ufe0f": 57.91, + "ARC": 63.57, + "HellaSwag": 83.51, + "MMLU": 59.82, + "TruthfulQA": 55.96, + "Winogrande": 76.16, + "GSM8K": 8.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": false, + "Model sha": "85bb49d333dba4a08b051418663d16853ce30cee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aeala\/Enterredaas-33b", + "Average \u2b06\ufe0f": 57.9, + "ARC": 60.92, + "HellaSwag": 84.18, + "MMLU": 58.3, + "TruthfulQA": 49.02, + "Winogrande": 78.77, + "GSM8K": 16.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d72dc1f05eaf1beb6373fd53fd22eb90f293a5c4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Cinder-Phi-2-STEM-2.94B-Test", + "Average \u2b06\ufe0f": 57.9, + "ARC": 57.08, + "HellaSwag": 72.21, + "MMLU": 53.87, + "TruthfulQA": 46.46, + "Winogrande": 75.61, + "GSM8K": 42.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.94, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ba849c8beeea4d6bffa6db6a590451d911df89ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/Wizard-Vicuna-30B-Uncensored", + "Average \u2b06\ufe0f": 57.89, + "ARC": 62.12, + "HellaSwag": 83.45, + "MMLU": 58.24, + "TruthfulQA": 50.81, + "Winogrande": 78.45, + "GSM8K": 14.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6374baef4cedd41f85c111b8eec3eb38ee24c4b9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Wizard-Vicuna-30B-Uncensored-fp16", + "Average \u2b06\ufe0f": 57.89, + "ARC": 62.12, + "HellaSwag": 83.45, + "MMLU": 58.24, + "TruthfulQA": 50.81, + "Winogrande": 78.45, + "GSM8K": 14.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "c7b7cecb5a314fc66deebabcb67c230a3fbe84f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "arlineka\/Brunhilde-13b-v1", + "Average \u2b06\ufe0f": 57.88, + "ARC": 61.09, + "HellaSwag": 83.58, + "MMLU": 55.32, + "TruthfulQA": 51.98, + "Winogrande": 75.22, + "GSM8K": 20.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e13977c7951d5d8cd77d301f75a7a3822c4800ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "posicube\/Llama2-chat-AYT-13B", + "Average \u2b06\ufe0f": 57.88, + "ARC": 63.31, + "HellaSwag": 83.53, + "MMLU": 59.67, + "TruthfulQA": 55.8, + "Winogrande": 76.09, + "GSM8K": 8.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "dd12dced8076a959c03b8b5c4a4266f234d6639a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/bubo-bubo-13b", + "Average \u2b06\ufe0f": 57.86, + "ARC": 61.43, + "HellaSwag": 83.14, + "MMLU": 58.18, + "TruthfulQA": 47.62, + "Winogrande": 76.16, + "GSM8K": 20.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1fe715732317ccd1c1cf295b97acd5765e209e01", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aeala\/VicUnlocked-alpaca-30b", + "Average \u2b06\ufe0f": 57.86, + "ARC": 61.86, + "HellaSwag": 83.79, + "MMLU": 57.64, + "TruthfulQA": 51.03, + "Winogrande": 78.22, + "GSM8K": 14.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "c63d117d1ec5794766dd6dc5e1469769df8aba1d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PulsarAI\/Chat-AYB-Nova-13B", + "Average \u2b06\ufe0f": 57.84, + "ARC": 62.97, + "HellaSwag": 84.28, + "MMLU": 58.58, + "TruthfulQA": 51.28, + "Winogrande": 77.58, + "GSM8K": 12.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "942af4d59533af09cf9ba13d1e369b8e871a0a4b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "souvik0306\/mistral_7b_2epoch_norobots", + "Average \u2b06\ufe0f": 57.84, + "ARC": 61.01, + "HellaSwag": 83.37, + "MMLU": 63.96, + "TruthfulQA": 42.62, + "Winogrande": 79.08, + "GSM8K": 16.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "624be22cfde6797a100230ec9dc1421f52eb0aa2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kwchoi\/DPO_mistral_v01_7b_ultra_0130_1k", + "Average \u2b06\ufe0f": 57.83, + "ARC": 57.17, + "HellaSwag": 79.16, + "MMLU": 55.85, + "TruthfulQA": 55.62, + "Winogrande": 72.85, + "GSM8K": 26.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "21b07f830456a4793db84060af6026597668bfd4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "s3nh\/Noromaid-Aeryth-7B", + "Average \u2b06\ufe0f": 57.82, + "ARC": 56.74, + "HellaSwag": 78.62, + "MMLU": 57.29, + "TruthfulQA": 65.66, + "Winogrande": 71.82, + "GSM8K": 16.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "e87dbfaf98d6d9422f3a16b10c8005801b28b139", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Stheno-V2-Delta-fp16", + "Average \u2b06\ufe0f": 57.81, + "ARC": 62.46, + "HellaSwag": 83.45, + "MMLU": 59.04, + "TruthfulQA": 55.25, + "Winogrande": 73.88, + "GSM8K": 12.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3979769be8d92aa2dd0c7aebf385635863f16dd9", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Sao10K\/Stheno-v2-Delta-fp16", + "Average \u2b06\ufe0f": 57.81, + "ARC": 62.46, + "HellaSwag": 83.45, + "MMLU": 59.04, + "TruthfulQA": 55.25, + "Winogrande": 73.88, + "GSM8K": 12.81, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3979769be8d92aa2dd0c7aebf385635863f16dd9", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Stellaris-internlm2-20b-r128", + "Average \u2b06\ufe0f": 57.76, + "ARC": 61.26, + "HellaSwag": 81.75, + "MMLU": 65.67, + "TruthfulQA": 52.5, + "Winogrande": 85.24, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b63187a2a0489f0b6768efe4b8e28381c3bcf025", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/ChatAYT-Lora-Assamble-Marcoroni", + "Average \u2b06\ufe0f": 57.76, + "ARC": 62.46, + "HellaSwag": 83.05, + "MMLU": 58.72, + "TruthfulQA": 56.12, + "Winogrande": 77.35, + "GSM8K": 8.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "51c9b600023cd26c4eb3754b9a89c60dde959ccc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-llama2-13b-v8.1-fp16", + "Average \u2b06\ufe0f": 57.76, + "ARC": 55.97, + "HellaSwag": 79.79, + "MMLU": 54.95, + "TruthfulQA": 51.16, + "Winogrande": 74.35, + "GSM8K": 30.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 63.0, + "Available on the hub": false, + "Model sha": "b51c6b29abdf7c420cb5e5f4f309ff83179c7bb8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Open-Orca\/OpenOrcaxOpenChat-Preview2-13B", + "Average \u2b06\ufe0f": 57.76, + "ARC": 62.37, + "HellaSwag": 82.96, + "MMLU": 58.68, + "TruthfulQA": 51.23, + "Winogrande": 77.19, + "GSM8K": 14.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 102.0, + "Available on the hub": true, + "Model sha": "26d1bc5c54c1f60a5de0b1ed4d0b16f285aee230", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/MLewd-L2-Chat-13B", + "Average \u2b06\ufe0f": 57.75, + "ARC": 62.03, + "HellaSwag": 84.19, + "MMLU": 58.75, + "TruthfulQA": 52.84, + "Winogrande": 77.43, + "GSM8K": 11.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 29.0, + "Available on the hub": true, + "Model sha": "6c66622a99c1bc73498aa6a15a59da825d875310", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JosephusCheung\/Pwen-14B-Chat-20_30", + "Average \u2b06\ufe0f": 57.74, + "ARC": 56.14, + "HellaSwag": 79.78, + "MMLU": 60.01, + "TruthfulQA": 47.02, + "Winogrande": 76.48, + "GSM8K": 26.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 14.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e878e1f1f7b533c32beb8e06ebcf0cfa23f3fe9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ai-business\/Luban-13B", + "Average \u2b06\ufe0f": 57.73, + "ARC": 63.05, + "HellaSwag": 82.8, + "MMLU": 58.73, + "TruthfulQA": 55.53, + "Winogrande": 76.56, + "GSM8K": 9.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "01b0f2046083dd8d9d8f9e626d78d83eaa1d57dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-33b-gpt4-1.2", + "Average \u2b06\ufe0f": 57.69, + "ARC": 64.42, + "HellaSwag": 84.93, + "MMLU": 60.35, + "TruthfulQA": 49.18, + "Winogrande": 77.51, + "GSM8K": 9.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "b3254a827fb1dfe0d4e428bf5ab1c3a2bac82d68", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Alpacino30b", + "Average \u2b06\ufe0f": 57.67, + "ARC": 62.71, + "HellaSwag": 85.04, + "MMLU": 58.48, + "TruthfulQA": 44.23, + "Winogrande": 79.79, + "GSM8K": 15.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 68.0, + "Available on the hub": true, + "Model sha": "300bc5f3dc129a3d17adf059394e381eff7fbd55", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "qblocks\/mistral_7b_DolphinCoder", + "Average \u2b06\ufe0f": 57.67, + "ARC": 59.73, + "HellaSwag": 81.64, + "MMLU": 59.87, + "TruthfulQA": 43.95, + "Winogrande": 74.59, + "GSM8K": 26.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7c05d338e0210072e13eb82b023e7747d5354c6e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zangs3011\/mistral_7b_DolphinCoder", + "Average \u2b06\ufe0f": 57.67, + "ARC": 59.73, + "HellaSwag": 81.64, + "MMLU": 59.87, + "TruthfulQA": 43.95, + "Winogrande": 74.59, + "GSM8K": 26.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "faac4b13e74395ea4b366156fd8bed15498c667c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "boomerchan\/magpie-13b", + "Average \u2b06\ufe0f": 57.64, + "ARC": 63.31, + "HellaSwag": 84.25, + "MMLU": 58.15, + "TruthfulQA": 49.15, + "Winogrande": 76.48, + "GSM8K": 14.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a58124cdc9f39ccd59d4290a8bdfda93ff3690dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "splm\/zephyr-7b-sft-full-spin-peft-iter1", + "Average \u2b06\ufe0f": 57.63, + "ARC": 57.94, + "HellaSwag": 80.78, + "MMLU": 60.23, + "TruthfulQA": 41.8, + "Winogrande": 76.24, + "GSM8K": 28.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bdc360638c254864af30b5c0e6ff9a7b19e51b46", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "splm\/zephyr-7b-sft-full-spin-peft-iter2", + "Average \u2b06\ufe0f": 57.63, + "ARC": 58.02, + "HellaSwag": 80.77, + "MMLU": 60.22, + "TruthfulQA": 41.79, + "Winogrande": 76.48, + "GSM8K": 28.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a07fc6ae0f9729767e2cedb229a515e7d84bd87f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "l3utterfly\/mistral-7b-v0.1-layla-v2", + "Average \u2b06\ufe0f": 57.6, + "ARC": 56.31, + "HellaSwag": 79.76, + "MMLU": 50.81, + "TruthfulQA": 51.57, + "Winogrande": 75.77, + "GSM8K": 31.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1e0dc1ba4a198773c2d47d0c8142aef1649f8c33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Orca-2-13B-GPTQ", + "Average \u2b06\ufe0f": 57.6, + "ARC": 59.81, + "HellaSwag": 79.12, + "MMLU": 59.35, + "TruthfulQA": 55.14, + "Winogrande": 76.64, + "GSM8K": 15.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.24, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": true, + "Model sha": "2fc627e11b197c7d563eeea9c4338c2adc8e2c93", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "steve-cse\/MelloGPT", + "Average \u2b06\ufe0f": 57.59, + "ARC": 53.84, + "HellaSwag": 76.12, + "MMLU": 55.99, + "TruthfulQA": 55.61, + "Winogrande": 73.88, + "GSM8K": 30.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "aedecb296e2cdcb3da95a345a794ea26f071c419", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "l3utterfly\/mistral-7b-v0.1-layla-v1", + "Average \u2b06\ufe0f": 57.56, + "ARC": 60.15, + "HellaSwag": 83.25, + "MMLU": 60.31, + "TruthfulQA": 48.9, + "Winogrande": 75.93, + "GSM8K": 16.83, + "Type": "", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5f06add6aa1d51d78288dbdcbd1abfd5f0ed0c84", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PotatoOff\/Michel-13B", + "Average \u2b06\ufe0f": 57.56, + "ARC": 61.26, + "HellaSwag": 83.21, + "MMLU": 55.05, + "TruthfulQA": 50.43, + "Winogrande": 75.22, + "GSM8K": 20.17, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "agpl-3.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "2d7bb01004f3bec6c4f4cfd27b9b896f5fa464a7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alignment-handbook\/zephyr-7b-sft-full", + "Average \u2b06\ufe0f": 57.56, + "ARC": 57.68, + "HellaSwag": 80.82, + "MMLU": 60.31, + "TruthfulQA": 41.71, + "Winogrande": 76.09, + "GSM8K": 28.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "92f9fac4529acacb2c33a35c46917393690c6311", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "splm\/zephyr-7b-sft-full-spin-peft-iter0", + "Average \u2b06\ufe0f": 57.55, + "ARC": 57.94, + "HellaSwag": 80.77, + "MMLU": 60.26, + "TruthfulQA": 41.79, + "Winogrande": 76.24, + "GSM8K": 28.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2995cd6e9b2780b8a14043fbc4241a81ba6d1feb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/PsyMedRP-v1-20B", + "Average \u2b06\ufe0f": 57.54, + "ARC": 60.49, + "HellaSwag": 83.94, + "MMLU": 56.68, + "TruthfulQA": 54.45, + "Winogrande": 74.82, + "GSM8K": 14.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": true, + "Model sha": "78188101b6331d9e61ef80f0971d715de100b44a", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/tulu-30B-fp16", + "Average \u2b06\ufe0f": 57.53, + "ARC": 59.98, + "HellaSwag": 83.4, + "MMLU": 56.1, + "TruthfulQA": 45.14, + "Winogrande": 80.82, + "GSM8K": 19.71, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "37c3655676c37662f60c68dacfce3f0e861be846", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "timpal0l\/Mistral-7B-v0.1-flashback-v2", + "Average \u2b06\ufe0f": 57.53, + "ARC": 57.17, + "HellaSwag": 80.74, + "MMLU": 59.98, + "TruthfulQA": 40.66, + "Winogrande": 77.19, + "GSM8K": 29.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "2711647da9d8da18d746406d60ad8d806b7f1fd7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-llama2-hermes-orca-platypus-wizardlm-13b", + "Average \u2b06\ufe0f": 57.52, + "ARC": 59.64, + "HellaSwag": 82.7, + "MMLU": 58.3, + "TruthfulQA": 56.0, + "Winogrande": 75.37, + "GSM8K": 13.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": false, + "Model sha": "4410d8a20871927e9fe981c01bc8314b451b2fcd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alignment-handbook\/zephyr-7b-sft-full", + "Average \u2b06\ufe0f": 57.52, + "ARC": 58.11, + "HellaSwag": 80.83, + "MMLU": 60.2, + "TruthfulQA": 41.74, + "Winogrande": 76.24, + "GSM8K": 27.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "92f9fac4529acacb2c33a35c46917393690c6311", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zangs3011\/mistral_7b_3Epoch_DolphinCoder", + "Average \u2b06\ufe0f": 57.51, + "ARC": 59.22, + "HellaSwag": 82.32, + "MMLU": 57.91, + "TruthfulQA": 43.7, + "Winogrande": 75.69, + "GSM8K": 26.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9335fee0bbe38195226c63e3f4aa606bbc387e8d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jilp00\/SOLAR-10.7B-tutored", + "Average \u2b06\ufe0f": 57.49, + "ARC": 62.29, + "HellaSwag": 82.24, + "MMLU": 65.09, + "TruthfulQA": 55.13, + "Winogrande": 80.19, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "40e46542b4ec136c76f61008a942000ff030cddc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-33b-gpt4-1.3", + "Average \u2b06\ufe0f": 57.49, + "ARC": 63.82, + "HellaSwag": 85.09, + "MMLU": 58.94, + "TruthfulQA": 45.33, + "Winogrande": 79.01, + "GSM8K": 12.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f94e5249d2b998933466d42e08fa9551e3238205", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xriminact\/TarsChattyBasev0.2", + "Average \u2b06\ufe0f": 57.47, + "ARC": 52.22, + "HellaSwag": 77.78, + "MMLU": 47.99, + "TruthfulQA": 43.79, + "Winogrande": 69.46, + "GSM8K": 53.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "91d90f5feb9c01d8279ed891c72e225356a4ca97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Unholy-v1-12L-13B", + "Average \u2b06\ufe0f": 57.47, + "ARC": 63.57, + "HellaSwag": 83.75, + "MMLU": 58.08, + "TruthfulQA": 51.09, + "Winogrande": 77.27, + "GSM8K": 11.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": true, + "Model sha": "ee25c078f08b0812d82597afa3f5e877c19a5c83", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/7B_ppo_phiRM_2GPU_3e-7step_4000", + "Average \u2b06\ufe0f": 57.46, + "ARC": 57.25, + "HellaSwag": 80.24, + "MMLU": 60.06, + "TruthfulQA": 41.48, + "Winogrande": 76.32, + "GSM8K": 29.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cebca6863a25b48f3a03f5ea65fdbcefcb934314", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PocketDoc\/Dans-AdventurousWinds-7b", + "Average \u2b06\ufe0f": 57.46, + "ARC": 61.01, + "HellaSwag": 83.47, + "MMLU": 63.69, + "TruthfulQA": 42.65, + "Winogrande": 78.22, + "GSM8K": 15.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "ddc7e4fcbbb5c666a3fe1bbe4a47b4477151b699", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/airoboros-33b-gpt4-1.3", + "Average \u2b06\ufe0f": 57.43, + "ARC": 63.91, + "HellaSwag": 85.04, + "MMLU": 58.53, + "TruthfulQA": 45.36, + "Winogrande": 78.69, + "GSM8K": 13.04, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f94e5249d2b998933466d42e08fa9551e3238205", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/MXLewd-L2-20B", + "Average \u2b06\ufe0f": 57.43, + "ARC": 63.23, + "HellaSwag": 85.33, + "MMLU": 57.36, + "TruthfulQA": 51.65, + "Winogrande": 76.09, + "GSM8K": 10.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "ac279478abd9ddb8d1f5adcc548be0287b963adf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-llama2-luban-orca-platypus-13b", + "Average \u2b06\ufe0f": 57.42, + "ARC": 62.54, + "HellaSwag": 82.76, + "MMLU": 59.23, + "TruthfulQA": 54.66, + "Winogrande": 77.11, + "GSM8K": 8.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "908cfb670611875b52045c4bab81cff53f0279a7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "hfl\/chinese-alpaca-2-13b", + "Average \u2b06\ufe0f": 57.41, + "ARC": 58.7, + "HellaSwag": 79.76, + "MMLU": 55.12, + "TruthfulQA": 50.22, + "Winogrande": 75.61, + "GSM8K": 25.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 80.0, + "Available on the hub": true, + "Model sha": "3b2e3895ff83c8892ab20fb8f98754d947879186", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SkunkworksAI\/Mistralic-7B-1", + "Average \u2b06\ufe0f": 57.4, + "ARC": 60.84, + "HellaSwag": 82.29, + "MMLU": 60.8, + "TruthfulQA": 52.38, + "Winogrande": 77.03, + "GSM8K": 11.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ebf138de4fb7a57f0d187ad0ab43abd6b35bfb62", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xenon1\/Zenith-7B", + "Average \u2b06\ufe0f": 57.39, + "ARC": 56.31, + "HellaSwag": 81.11, + "MMLU": 61.3, + "TruthfulQA": 55.76, + "Winogrande": 77.82, + "GSM8K": 12.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4d49920793f6c408ef75b1032e4ae66df1fae066", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Tiger-7B-v0.1-LaserRMT-Math-5-10-15-Neural-DPO", + "Average \u2b06\ufe0f": 57.36, + "ARC": 39.42, + "HellaSwag": 82.58, + "MMLU": 61.63, + "TruthfulQA": 48.16, + "Winogrande": 77.19, + "GSM8K": 35.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "65089a9263dc7c51a787deb6392955d78621f72f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chargoddard\/llama-polyglot-13b", + "Average \u2b06\ufe0f": 57.36, + "ARC": 59.81, + "HellaSwag": 81.27, + "MMLU": 55.04, + "TruthfulQA": 48.71, + "Winogrande": 76.72, + "GSM8K": 22.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "7a08a96118aa86e0405a5f980d7e40dadf86e1be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "allenai\/digital-socrates-13b", + "Average \u2b06\ufe0f": 57.34, + "ARC": 58.36, + "HellaSwag": 80.14, + "MMLU": 57.01, + "TruthfulQA": 44.47, + "Winogrande": 74.59, + "GSM8K": 29.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "c738ee4bb61e67eebb9d196c440dcb2d99e5f906", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/VicUnlocked-30B-LoRA-HF", + "Average \u2b06\ufe0f": 57.33, + "ARC": 59.73, + "HellaSwag": 84.02, + "MMLU": 57.81, + "TruthfulQA": 48.54, + "Winogrande": 79.48, + "GSM8K": 14.4, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3259cb3c2a10cfb429fb51c4a76fffa049f4c44d", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "jondurbin\/airoboros-33b-gpt4", + "Average \u2b06\ufe0f": 57.32, + "ARC": 63.74, + "HellaSwag": 84.87, + "MMLU": 58.54, + "TruthfulQA": 47.06, + "Winogrande": 77.03, + "GSM8K": 12.66, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "5b6bd680b1c008e52521dc8c663dbc87820da3d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/BrainDerp2", + "Average \u2b06\ufe0f": 57.32, + "ARC": 60.92, + "HellaSwag": 81.94, + "MMLU": 58.9, + "TruthfulQA": 57.19, + "Winogrande": 75.93, + "GSM8K": 9.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "948ee7af94a8b092807df4becfc0a8c1cd042878", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/OpenOrca-Platypus2-13B-QLoRA-0.80-epoch", + "Average \u2b06\ufe0f": 57.31, + "ARC": 62.37, + "HellaSwag": 82.99, + "MMLU": 59.38, + "TruthfulQA": 52.2, + "Winogrande": 75.77, + "GSM8K": 11.14, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "39ae03b77b4f1d453b02468ce6bb4ddeb6526b77", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "adonlee\/LLaMA_2_13B_SFT_v0", + "Average \u2b06\ufe0f": 57.31, + "ARC": 62.03, + "HellaSwag": 83.8, + "MMLU": 58.39, + "TruthfulQA": 49.92, + "Winogrande": 77.27, + "GSM8K": 12.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a6790d83337578f38d2bcd51038a779eaa8d0fac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "codellama\/CodeLlama-34b-Instruct-hf", + "Average \u2b06\ufe0f": 57.29, + "ARC": 54.27, + "HellaSwag": 76.92, + "MMLU": 55.54, + "TruthfulQA": 44.44, + "Winogrande": 74.59, + "GSM8K": 37.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 256.0, + "Available on the hub": true, + "Model sha": "bf5e5060fa30f33149efe84bbcc682001a00ab94", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Open-Orca\/OpenOrca-Platypus2-13B", + "Average \u2b06\ufe0f": 57.28, + "ARC": 62.8, + "HellaSwag": 83.15, + "MMLU": 59.39, + "TruthfulQA": 53.08, + "Winogrande": 76.24, + "GSM8K": 9.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 223.0, + "Available on the hub": true, + "Model sha": "e7a40134f7eb687c6ab66d445dc7251257f8d391", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PulsarAI\/2x-LoRA-Assemble-Nova-13B", + "Average \u2b06\ufe0f": 57.26, + "ARC": 62.63, + "HellaSwag": 83.24, + "MMLU": 58.64, + "TruthfulQA": 51.88, + "Winogrande": 76.95, + "GSM8K": 10.24, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2a344b91b28ce4d0bd48b9b5a6cc87b71123eab5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ArianAskari\/SOLID-SFT-DPO-MixQV2-SOLIDRejected-SFTChosen-Zephyr-7b-beta", + "Average \u2b06\ufe0f": 57.26, + "ARC": 58.96, + "HellaSwag": 79.82, + "MMLU": 60.14, + "TruthfulQA": 52.36, + "Winogrande": 73.24, + "GSM8K": 19.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f03058e7f15c0d1c542e32c88f7813a4dac7c33f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/MLewd-ReMM-L2-Chat-20B-Inverted", + "Average \u2b06\ufe0f": 57.25, + "ARC": 61.69, + "HellaSwag": 85.32, + "MMLU": 58.0, + "TruthfulQA": 53.77, + "Winogrande": 75.61, + "GSM8K": 9.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "b5b501b4d23ec7ab24b827f79e48b2c67e548ddb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nisten\/bigdoc-c34b-instruct-tf32", + "Average \u2b06\ufe0f": 57.24, + "ARC": 54.44, + "HellaSwag": 76.91, + "MMLU": 55.62, + "TruthfulQA": 44.46, + "Winogrande": 74.43, + "GSM8K": 37.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-3.0", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a20a49f517dbc82705e1c67f78ef47f794777f91", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abacusai\/Giraffe-13b-32k-v3", + "Average \u2b06\ufe0f": 57.24, + "ARC": 59.04, + "HellaSwag": 79.59, + "MMLU": 55.01, + "TruthfulQA": 46.68, + "Winogrande": 76.95, + "GSM8K": 26.16, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "bbc483fc0a3b88740fd6e04a7fd0c7d98b85cd1d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "pankajmathur\/orca_mini_v3_13b", + "Average \u2b06\ufe0f": 57.24, + "ARC": 63.14, + "HellaSwag": 82.35, + "MMLU": 56.52, + "TruthfulQA": 51.81, + "Winogrande": 76.48, + "GSM8K": 13.12, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": true, + "Model sha": "72eec98f68d240a71d3da8a266917b6e754ae831", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/orca_mini_v3_13b", + "Average \u2b06\ufe0f": 57.24, + "ARC": 63.14, + "HellaSwag": 82.35, + "MMLU": 56.52, + "TruthfulQA": 51.81, + "Winogrande": 76.48, + "GSM8K": 13.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "99904e4119575f2c1606ca1e31d288f38a9f20b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/MLewd-Chat-v2-13B", + "Average \u2b06\ufe0f": 57.23, + "ARC": 61.86, + "HellaSwag": 83.81, + "MMLU": 57.0, + "TruthfulQA": 54.51, + "Winogrande": 75.77, + "GSM8K": 10.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "f6181961a6a2f9ca534e1a8907b4a4459be6b6bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "IkariDev\/Athena-v4", + "Average \u2b06\ufe0f": 57.23, + "ARC": 62.54, + "HellaSwag": 84.19, + "MMLU": 57.33, + "TruthfulQA": 50.87, + "Winogrande": 76.48, + "GSM8K": 11.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "dde640538a44a08f6f456a2b7634e31a5d7a1245", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/LLaMA2-13B-Estopia", + "Average \u2b06\ufe0f": 57.21, + "ARC": 62.29, + "HellaSwag": 82.51, + "MMLU": 55.12, + "TruthfulQA": 54.14, + "Winogrande": 75.77, + "GSM8K": 13.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "cfbf7f1372454aefb45d27504b11431828ad14f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zangs3011\/mistral_7b_2EPOCH_DolphinCoder", + "Average \u2b06\ufe0f": 57.17, + "ARC": 60.75, + "HellaSwag": 81.15, + "MMLU": 59.37, + "TruthfulQA": 44.65, + "Winogrande": 73.24, + "GSM8K": 23.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "521da4841efa9eee3716294f08fd3326d271b574", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-llama2-hermes-orca-platypus-13b", + "Average \u2b06\ufe0f": 57.17, + "ARC": 60.92, + "HellaSwag": 83.5, + "MMLU": 59.39, + "TruthfulQA": 54.29, + "Winogrande": 75.22, + "GSM8K": 9.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "f227ad33b16726b099e35e5dc47f4db1f22665a7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/airoboros-33b-2.1", + "Average \u2b06\ufe0f": 57.16, + "ARC": 63.65, + "HellaSwag": 84.97, + "MMLU": 57.37, + "TruthfulQA": 52.17, + "Winogrande": 78.22, + "GSM8K": 6.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "12ccd0e6c9ef12c7d3c2eab8266cd32c0b2f7683", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-33b-gpt4-m2.0", + "Average \u2b06\ufe0f": 57.16, + "ARC": 64.68, + "HellaSwag": 84.95, + "MMLU": 57.77, + "TruthfulQA": 47.44, + "Winogrande": 77.74, + "GSM8K": 10.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "57bd88e24d603dc4bbe4016ed0871db7c0e529d5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/BrainDerp3", + "Average \u2b06\ufe0f": 57.13, + "ARC": 60.92, + "HellaSwag": 82.1, + "MMLU": 58.91, + "TruthfulQA": 57.18, + "Winogrande": 75.61, + "GSM8K": 8.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0b575b9245406cca92942ce2ababb5b868109bed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Doctor-Shotgun\/CalliopeDS-v2-L2-13B", + "Average \u2b06\ufe0f": 57.12, + "ARC": 62.8, + "HellaSwag": 84.14, + "MMLU": 56.14, + "TruthfulQA": 51.06, + "Winogrande": 76.01, + "GSM8K": 12.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e63d24870c840d47e82b029e7f405baa10ad9ea4", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gradientputri\/MegaMix-S1-13B", + "Average \u2b06\ufe0f": 57.12, + "ARC": 62.46, + "HellaSwag": 83.65, + "MMLU": 57.88, + "TruthfulQA": 44.52, + "Winogrande": 75.85, + "GSM8K": 18.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "afca2c9488cf8738faec4db6721f6a4c755a5d81", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/BrainDerp", + "Average \u2b06\ufe0f": 57.11, + "ARC": 60.75, + "HellaSwag": 82.1, + "MMLU": 58.81, + "TruthfulQA": 56.9, + "Winogrande": 75.85, + "GSM8K": 8.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ba21a7ed5458b3fa2b05ce6aab431acd1f857516", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ArianAskari\/SOLID-SFT-WoDPO-MixQV2-Zephyr-7b-beta", + "Average \u2b06\ufe0f": 57.1, + "ARC": 59.73, + "HellaSwag": 81.72, + "MMLU": 60.47, + "TruthfulQA": 53.77, + "Winogrande": 74.66, + "GSM8K": 12.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ced2cbdeef8389e754a8f4895b70032580d54b99", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/ReMM-v2.2-L2-13B", + "Average \u2b06\ufe0f": 57.1, + "ARC": 61.26, + "HellaSwag": 84.16, + "MMLU": 56.22, + "TruthfulQA": 51.35, + "Winogrande": 75.61, + "GSM8K": 14.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "d55031fbcd41d749bc0c0ffbcd85636718d373b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "IkariDev\/Athena-v3", + "Average \u2b06\ufe0f": 57.09, + "ARC": 61.69, + "HellaSwag": 84.34, + "MMLU": 57.87, + "TruthfulQA": 51.26, + "Winogrande": 75.77, + "GSM8K": 11.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "5e4024b6694bb13f1a81ce4277ac9141f0b226df", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/vicuna-33b-coder", + "Average \u2b06\ufe0f": 57.07, + "ARC": 60.41, + "HellaSwag": 83.27, + "MMLU": 57.17, + "TruthfulQA": 51.79, + "Winogrande": 76.87, + "GSM8K": 12.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "67f6e669d7a15c1104a1478057f3752a503e83c0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Emerhyst-20B", + "Average \u2b06\ufe0f": 57.07, + "ARC": 61.69, + "HellaSwag": 84.98, + "MMLU": 56.98, + "TruthfulQA": 54.16, + "Winogrande": 76.09, + "GSM8K": 8.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 32.0, + "Available on the hub": true, + "Model sha": "e4c23af4f5dd88cb27d245e2bfc3b81db652632c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DangFutures\/BIG_DANG_BOT", + "Average \u2b06\ufe0f": 57.06, + "ARC": 60.32, + "HellaSwag": 82.02, + "MMLU": 70.02, + "TruthfulQA": 49.07, + "Winogrande": 80.9, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b97d945f17c9e41dbe1809210c8f818b1cecca7c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Cinder-Phi-2-Test-1", + "Average \u2b06\ufe0f": 57.05, + "ARC": 57.34, + "HellaSwag": 72.6, + "MMLU": 50.81, + "TruthfulQA": 45.23, + "Winogrande": 73.8, + "GSM8K": 42.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ed772a328dc0461fc3feb7b92fa1f8dcfedfa1cb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "stabilityai\/StableBeluga-13B", + "Average \u2b06\ufe0f": 57.05, + "ARC": 62.03, + "HellaSwag": 82.27, + "MMLU": 57.71, + "TruthfulQA": 49.61, + "Winogrande": 76.87, + "GSM8K": 13.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 113.0, + "Available on the hub": false, + "Model sha": "1d6eef4cc2b73f39600a568803ad8183f2da4514", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "circulus\/Llama-2-13b-orca-v1", + "Average \u2b06\ufe0f": 57.05, + "ARC": 62.03, + "HellaSwag": 82.27, + "MMLU": 57.71, + "TruthfulQA": 49.61, + "Winogrande": 76.87, + "GSM8K": 13.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "e77ec90f432bdffa210a0e4310d117e5d1c662df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen1.5-4B", + "Average \u2b06\ufe0f": 57.05, + "ARC": 48.46, + "HellaSwag": 71.58, + "MMLU": 56.52, + "TruthfulQA": 47.27, + "Winogrande": 66.22, + "GSM8K": 52.24, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "294dbdee5dacecc52c9cc6ba2dba4084addc7b2c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-33b-gpt4-m2.0", + "Average \u2b06\ufe0f": 57.03, + "ARC": 63.4, + "HellaSwag": 85.19, + "MMLU": 57.46, + "TruthfulQA": 48.15, + "Winogrande": 78.37, + "GSM8K": 9.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "84a89dee5bf3447079f115a3ef4d58ef8f924798", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BioMistral\/BioMistral-7B-DARE", + "Average \u2b06\ufe0f": 57.03, + "ARC": 58.28, + "HellaSwag": 79.87, + "MMLU": 57.34, + "TruthfulQA": 55.61, + "Winogrande": 76.09, + "GSM8K": 15.01, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "fc46b30e1cf0fe45280fd9b0a948fd9344b31112", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/zephyr-beta-Nebula-v2-7B", + "Average \u2b06\ufe0f": 57.03, + "ARC": 56.57, + "HellaSwag": 82.53, + "MMLU": 56.4, + "TruthfulQA": 58.68, + "Winogrande": 70.48, + "GSM8K": 17.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "226caedb50a12730232c1f8fe9c96b6dcf818ba7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-33b-gpt4-2.0", + "Average \u2b06\ufe0f": 57.02, + "ARC": 63.91, + "HellaSwag": 85.67, + "MMLU": 57.95, + "TruthfulQA": 45.54, + "Winogrande": 77.98, + "GSM8K": 11.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "a4e1b721add286900c5a6f529c3d7a3e0049b2e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MisterRid\/wendigo-14b-alpha2", + "Average \u2b06\ufe0f": 57.02, + "ARC": 56.66, + "HellaSwag": 77.19, + "MMLU": 58.0, + "TruthfulQA": 53.71, + "Winogrande": 73.64, + "GSM8K": 22.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f8332eddcb7f8ab2b5195486d4b508c4628992f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WebraftAI\/synapsellm-7b-mistral-v0.3-preview", + "Average \u2b06\ufe0f": 57.01, + "ARC": 53.84, + "HellaSwag": 74.86, + "MMLU": 54.81, + "TruthfulQA": 55.03, + "Winogrande": 74.59, + "GSM8K": 28.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4e509275c5e51bee6e82c2c15082a6cc50d87b5b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MisterRid\/wendigo-14b-alpha1", + "Average \u2b06\ufe0f": 57.01, + "ARC": 56.48, + "HellaSwag": 77.2, + "MMLU": 57.83, + "TruthfulQA": 53.76, + "Winogrande": 73.01, + "GSM8K": 23.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0024ee75d8ed5d9373ff42df72c21f3217ba9d2e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-33b-gpt4-2.0", + "Average \u2b06\ufe0f": 57.01, + "ARC": 63.82, + "HellaSwag": 85.65, + "MMLU": 58.44, + "TruthfulQA": 45.57, + "Winogrande": 77.9, + "GSM8K": 10.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "ddc598f492f5098a8e308f51a82834f98f29a4ce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yulan-team\/YuLan-Chat-2-13b-fp16", + "Average \u2b06\ufe0f": 57.01, + "ARC": 59.04, + "HellaSwag": 80.66, + "MMLU": 56.72, + "TruthfulQA": 52.18, + "Winogrande": 79.64, + "GSM8K": 13.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "2d439187efd6edd91a0c0146f08dff52d92aa7bc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/ReMM-v2-L2-13B", + "Average \u2b06\ufe0f": 56.99, + "ARC": 61.95, + "HellaSwag": 84.0, + "MMLU": 56.14, + "TruthfulQA": 50.81, + "Winogrande": 75.85, + "GSM8K": 13.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "bc42c77f88482c37c72c85c66135e99972bbca1b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "inswave\/AISquare-Instruct-llama2-koen-13b-v0.9.24", + "Average \u2b06\ufe0f": 56.98, + "ARC": 55.63, + "HellaSwag": 81.35, + "MMLU": 51.76, + "TruthfulQA": 53.0, + "Winogrande": 76.95, + "GSM8K": 23.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.16, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0302553f7fe0a74925719b197b9c119aad0586c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/OpenOrca-Platypus2-13B-GPTQ", + "Average \u2b06\ufe0f": 56.98, + "ARC": 62.54, + "HellaSwag": 82.67, + "MMLU": 58.56, + "TruthfulQA": 51.93, + "Winogrande": 76.8, + "GSM8K": 9.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 16.24, + "Hub \u2764\ufe0f": 49.0, + "Available on the hub": true, + "Model sha": "0fa9a56066656fbc94e3ec088bc900fd1d4d38e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PulsarAI\/GenAI-Nova-13B", + "Average \u2b06\ufe0f": 56.98, + "ARC": 62.29, + "HellaSwag": 83.27, + "MMLU": 59.47, + "TruthfulQA": 51.79, + "Winogrande": 77.35, + "GSM8K": 7.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ce62a64ca53cd5feb18f523a96dd3be86e6513d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-33b-gpt4-m2.0", + "Average \u2b06\ufe0f": 56.97, + "ARC": 63.14, + "HellaSwag": 85.19, + "MMLU": 57.28, + "TruthfulQA": 48.07, + "Winogrande": 78.45, + "GSM8K": 9.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "96af3dc6c9f2248d964cf14cef6e5f2e5894583a", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "huggyllama\/llama-30b", + "Average \u2b06\ufe0f": 56.96, + "ARC": 61.43, + "HellaSwag": 84.73, + "MMLU": 58.45, + "TruthfulQA": 42.27, + "Winogrande": 80.03, + "GSM8K": 14.86, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "2b1edcdb3c7ced7bce6c1aa75c94545777c3118b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Radiantloom\/radintloom-mistral-7b-fusion-dpo", + "Average \u2b06\ufe0f": 56.95, + "ARC": 63.14, + "HellaSwag": 83.68, + "MMLU": 63.42, + "TruthfulQA": 51.14, + "Winogrande": 79.95, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8f11b7ed191f06add8c7de1a830505289db0afde", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yhyu13\/llama-30B-hf-openassitant", + "Average \u2b06\ufe0f": 56.94, + "ARC": 61.26, + "HellaSwag": 84.73, + "MMLU": 58.47, + "TruthfulQA": 42.27, + "Winogrande": 80.03, + "GSM8K": 14.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fba493af11a73cf5a2ee7857dd7aecb98c659dc4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "huggingface\/llama-30b", + "Average \u2b06\ufe0f": 56.94, + "ARC": 61.26, + "HellaSwag": 84.73, + "MMLU": 58.47, + "TruthfulQA": 42.27, + "Winogrande": 80.03, + "GSM8K": 14.86, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "13c77caa472bfa79d4f3f0ec82cbdc9dd88e5d22", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "hon9kon9ize\/CantoneseLLM-6B-preview202402", + "Average \u2b06\ufe0f": 56.93, + "ARC": 55.63, + "HellaSwag": 75.8, + "MMLU": 63.07, + "TruthfulQA": 42.26, + "Winogrande": 74.11, + "GSM8K": 30.71, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "71474831ebfa33d02692e22f2ed7267d534f9e06", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/UndiMix-v4-13B", + "Average \u2b06\ufe0f": 56.93, + "ARC": 61.95, + "HellaSwag": 83.88, + "MMLU": 56.9, + "TruthfulQA": 48.96, + "Winogrande": 76.16, + "GSM8K": 13.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "6dd97c74cfe1d22432d5c993814e230f333ba401", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rombodawg\/LosslessMegaCoder-llama2-13b-mini", + "Average \u2b06\ufe0f": 56.92, + "ARC": 60.58, + "HellaSwag": 81.26, + "MMLU": 57.92, + "TruthfulQA": 48.89, + "Winogrande": 76.95, + "GSM8K": 15.92, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "1f5609ffd40bc3af2dcbc5c88e9312d47a73c4b4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andreaskoepf\/llama2-13b-megacode2_min100", + "Average \u2b06\ufe0f": 56.92, + "ARC": 60.58, + "HellaSwag": 81.26, + "MMLU": 57.92, + "TruthfulQA": 48.89, + "Winogrande": 76.95, + "GSM8K": 15.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "b38d1b53c358a0313c69bcceebe97628327ada82", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "circulus\/Llama-2-13b-orca-v1", + "Average \u2b06\ufe0f": 56.91, + "ARC": 62.2, + "HellaSwag": 82.32, + "MMLU": 57.67, + "TruthfulQA": 49.6, + "Winogrande": 76.8, + "GSM8K": 12.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "e77ec90f432bdffa210a0e4310d117e5d1c662df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Emerald-13B", + "Average \u2b06\ufe0f": 56.89, + "ARC": 62.29, + "HellaSwag": 83.69, + "MMLU": 55.7, + "TruthfulQA": 50.94, + "Winogrande": 75.93, + "GSM8K": 12.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f7696299463d8ec402a4e1eb001f3a447f1c5552", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lamhieu\/ghost-7b-v0.9.0", + "Average \u2b06\ufe0f": 56.89, + "ARC": 53.07, + "HellaSwag": 77.93, + "MMLU": 55.09, + "TruthfulQA": 47.79, + "Winogrande": 73.72, + "GSM8K": 33.74, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "78441c9cec230d2dc76a746854078fa776a019c6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/ReMM-Mistral-13B", + "Average \u2b06\ufe0f": 56.89, + "ARC": 62.2, + "HellaSwag": 83.82, + "MMLU": 55.43, + "TruthfulQA": 53.32, + "Winogrande": 74.51, + "GSM8K": 12.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a5ef9385d9430a81778183d71b58eb2b869d6a7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HenryJJ\/Instruct_Yi-6B_Dolly15K", + "Average \u2b06\ufe0f": 56.85, + "ARC": 54.86, + "HellaSwag": 75.87, + "MMLU": 63.37, + "TruthfulQA": 42.84, + "Winogrande": 74.9, + "GSM8K": 29.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2c0644cf206bdc94f5e6db2aca63129af0fa4a45", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/OpenOrcaxOpenChat-Preview2-13B-GPTQ", + "Average \u2b06\ufe0f": 56.84, + "ARC": 61.26, + "HellaSwag": 82.14, + "MMLU": 57.85, + "TruthfulQA": 50.22, + "Winogrande": 77.11, + "GSM8K": 12.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 16.24, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "ec9eb4f471b5bb6a7e5e505369628586c0c72252", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dsvv-cair\/alpaca-cleaned-llama-30b-bf16", + "Average \u2b06\ufe0f": 56.82, + "ARC": 61.77, + "HellaSwag": 85.06, + "MMLU": 57.52, + "TruthfulQA": 51.49, + "Winogrande": 77.35, + "GSM8K": 7.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "2424b6346e9e8fd749b9a6734f5d7125b5926daf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Danielbrdz\/Barcenas-Orca-2-7b", + "Average \u2b06\ufe0f": 56.81, + "ARC": 55.2, + "HellaSwag": 77.08, + "MMLU": 56.02, + "TruthfulQA": 43.72, + "Winogrande": 75.53, + "GSM8K": 33.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "dd4cc9f2be4fb8acb30b5bc79ad759ae2906300c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ArianAskari\/SOLID_SFT-WoDPO-WoMixQ", + "Average \u2b06\ufe0f": 56.8, + "ARC": 59.64, + "HellaSwag": 81.69, + "MMLU": 60.1, + "TruthfulQA": 55.25, + "Winogrande": 74.66, + "GSM8K": 9.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5a31a78c59bd70f66ffafb91f2a507286354fb72", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TIGER-Lab\/TIGERScore-13B", + "Average \u2b06\ufe0f": 56.79, + "ARC": 59.04, + "HellaSwag": 82.79, + "MMLU": 55.07, + "TruthfulQA": 40.38, + "Winogrande": 74.74, + "GSM8K": 28.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "4a71ce15f9af6fd25b0cde1612e56a7ee589c3e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Locutusque\/Orca-2-13b-SFT_v5", + "Average \u2b06\ufe0f": 56.77, + "ARC": 59.22, + "HellaSwag": 80.09, + "MMLU": 60.19, + "TruthfulQA": 51.84, + "Winogrande": 80.9, + "GSM8K": 8.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3c1b86e1a4e89119e373198ff018838988cc74d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "01-ai\/Yi-6B-200K", + "Average \u2b06\ufe0f": 56.76, + "ARC": 53.75, + "HellaSwag": 75.57, + "MMLU": 64.65, + "TruthfulQA": 41.56, + "Winogrande": 73.64, + "GSM8K": 31.39, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 154.0, + "Available on the hub": true, + "Model sha": "6cb672ed8441c35d043dd3cda448466daa3b38b1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/Platypus2xOpenOrca-13B-IA3-v3", + "Average \u2b06\ufe0f": 56.74, + "ARC": 62.54, + "HellaSwag": 82.1, + "MMLU": 58.67, + "TruthfulQA": 46.96, + "Winogrande": 77.82, + "GSM8K": 12.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "17493c1f2e4620a44d7947edad0386d338e805ce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Orca-Nova-13B", + "Average \u2b06\ufe0f": 56.72, + "ARC": 62.37, + "HellaSwag": 82.47, + "MMLU": 57.44, + "TruthfulQA": 45.97, + "Winogrande": 77.58, + "GSM8K": 14.48, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5a6c3686749ecb76971a915403da8c07a98078a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/ReMM-v2.1-L2-13B", + "Average \u2b06\ufe0f": 56.71, + "ARC": 61.43, + "HellaSwag": 83.92, + "MMLU": 55.95, + "TruthfulQA": 50.3, + "Winogrande": 75.93, + "GSM8K": 12.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e6b5ac97f74355cb281a621261debe5720fb4da2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Open-Orca\/OpenOrcaxOpenChat-Preview2-13B", + "Average \u2b06\ufe0f": 56.7, + "ARC": 62.71, + "HellaSwag": 81.99, + "MMLU": 57.51, + "TruthfulQA": 47.45, + "Winogrande": 76.8, + "GSM8K": 13.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 102.0, + "Available on the hub": true, + "Model sha": "26d1bc5c54c1f60a5de0b1ed4d0b16f285aee230", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "01-ai\/Yi-6B-200K", + "Average \u2b06\ufe0f": 56.69, + "ARC": 53.58, + "HellaSwag": 75.58, + "MMLU": 64.65, + "TruthfulQA": 41.74, + "Winogrande": 74.27, + "GSM8K": 30.33, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 154.0, + "Available on the hub": true, + "Model sha": "6cb672ed8441c35d043dd3cda448466daa3b38b1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/k2s3_test_24001", + "Average \u2b06\ufe0f": 56.68, + "ARC": 55.72, + "HellaSwag": 80.69, + "MMLU": 54.6, + "TruthfulQA": 43.57, + "Winogrande": 75.69, + "GSM8K": 29.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cceec03919d9a8e47dd98e4b2468503d52d37ef9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Changgil\/k2s3_test_24001", + "Average \u2b06\ufe0f": 56.67, + "ARC": 55.8, + "HellaSwag": 80.59, + "MMLU": 54.42, + "TruthfulQA": 43.62, + "Winogrande": 75.69, + "GSM8K": 29.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "60f5918773275ff16e43a945a24dd4ad8ddfeacf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alnrg2arg\/test3_sft_4bit", + "Average \u2b06\ufe0f": 56.66, + "ARC": 61.52, + "HellaSwag": 83.89, + "MMLU": 64.79, + "TruthfulQA": 47.83, + "Winogrande": 81.93, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "45e1dcfb08c47a66c602aa5a3b37229ef69dcf41", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ArianAskari\/SOLID-SFT-DPO-MixQV2-SOLIDChosen-SFTRejected-Zephyr-7b-beta", + "Average \u2b06\ufe0f": 56.66, + "ARC": 60.75, + "HellaSwag": 83.68, + "MMLU": 59.42, + "TruthfulQA": 58.1, + "Winogrande": 76.32, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "993476d6a1c2b8ee4894f9b63b449b6d42c6495f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vicgalle\/SOLAR-13B-Instruct-v1.0", + "Average \u2b06\ufe0f": 56.65, + "ARC": 57.25, + "HellaSwag": 78.03, + "MMLU": 55.75, + "TruthfulQA": 61.99, + "Winogrande": 70.24, + "GSM8K": 16.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 12.48, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "9608d346324d603a67e7cb52a9ebe8cb1ed9e42f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/Platypus2xOpenOrca-13B-IA3", + "Average \u2b06\ufe0f": 56.65, + "ARC": 62.12, + "HellaSwag": 82.1, + "MMLU": 58.84, + "TruthfulQA": 47.88, + "Winogrande": 77.11, + "GSM8K": 11.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5ca46029dd22c007d4dc1706f6284a32be4546c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/storytime-13b", + "Average \u2b06\ufe0f": 56.64, + "ARC": 62.03, + "HellaSwag": 83.96, + "MMLU": 57.48, + "TruthfulQA": 52.5, + "Winogrande": 75.53, + "GSM8K": 8.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "233568319a636b6a7b02a4def2c51d08a3e0fbfc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ZoidBB\/unraveled-7b-a1", + "Average \u2b06\ufe0f": 56.63, + "ARC": 59.81, + "HellaSwag": 82.8, + "MMLU": 63.39, + "TruthfulQA": 42.23, + "Winogrande": 77.19, + "GSM8K": 14.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fac05775fa8121b58cda8031b7001323bd43983d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/duplicitous-slurpbeast-13b", + "Average \u2b06\ufe0f": 56.62, + "ARC": 62.12, + "HellaSwag": 83.92, + "MMLU": 57.53, + "TruthfulQA": 52.33, + "Winogrande": 75.06, + "GSM8K": 8.79, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "88dc61b7afebf2220ca42898e1286c59961ed440", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Amethyst-13B", + "Average \u2b06\ufe0f": 56.62, + "ARC": 62.63, + "HellaSwag": 83.17, + "MMLU": 55.91, + "TruthfulQA": 52.43, + "Winogrande": 74.74, + "GSM8K": 10.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "d4a85b1006f0b9439e64f0e7400533a7b867c24d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Amethyst-13B-Mistral", + "Average \u2b06\ufe0f": 56.62, + "ARC": 62.63, + "HellaSwag": 83.17, + "MMLU": 55.91, + "TruthfulQA": 52.43, + "Winogrande": 74.74, + "GSM8K": 10.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4328809e568f01e3f0a05764e3bb58e901310415", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BELLE-2\/BELLE-Llama2-13B-chat-0.4M", + "Average \u2b06\ufe0f": 56.62, + "ARC": 60.67, + "HellaSwag": 82.31, + "MMLU": 55.94, + "TruthfulQA": 50.85, + "Winogrande": 75.53, + "GSM8K": 14.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 29.0, + "Available on the hub": true, + "Model sha": "1776feacbf1052cff02eb3d7531a854555d3f6dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Clover3-17B", + "Average \u2b06\ufe0f": 56.61, + "ARC": 59.9, + "HellaSwag": 81.18, + "MMLU": 60.47, + "TruthfulQA": 40.72, + "Winogrande": 78.61, + "GSM8K": 18.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 16.84, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "428f6f58869426baae2c49442b207a15bc2da3cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elinas\/chronos-33b", + "Average \u2b06\ufe0f": 56.59, + "ARC": 62.2, + "HellaSwag": 83.48, + "MMLU": 55.87, + "TruthfulQA": 46.67, + "Winogrande": 78.3, + "GSM8K": 13.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "3c11f81d9180618f13777276b1eb0eb70ab99cf0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Open-Orca\/LlongOrca-13B-16k", + "Average \u2b06\ufe0f": 56.59, + "ARC": 62.46, + "HellaSwag": 82.75, + "MMLU": 55.54, + "TruthfulQA": 50.11, + "Winogrande": 76.4, + "GSM8K": 12.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "8ea1fb205553cadbc90069d80a7e58281b6281c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenAssistant\/llama2-13b-megacode2-oasst", + "Average \u2b06\ufe0f": 56.59, + "ARC": 60.67, + "HellaSwag": 81.93, + "MMLU": 57.38, + "TruthfulQA": 47.85, + "Winogrande": 76.16, + "GSM8K": 15.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "2c45ecf161da2ff2aa984900f2e4d2b7a7311ab8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Brouz\/Slerpeno", + "Average \u2b06\ufe0f": 56.59, + "ARC": 61.69, + "HellaSwag": 84.1, + "MMLU": 56.77, + "TruthfulQA": 48.05, + "Winogrande": 76.4, + "GSM8K": 12.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "7ff32abd17851a769a031659e91e660f219be363", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NovoCode\/Novocode7b-v2", + "Average \u2b06\ufe0f": 56.57, + "ARC": 61.01, + "HellaSwag": 84.12, + "MMLU": 64.05, + "TruthfulQA": 42.21, + "Winogrande": 79.87, + "GSM8K": 8.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "45db1dd584c06c31e72f9744ebfb531a54898212", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/NyakuraV2.1-m7", + "Average \u2b06\ufe0f": 56.57, + "ARC": 58.62, + "HellaSwag": 81.89, + "MMLU": 58.46, + "TruthfulQA": 45.01, + "Winogrande": 72.77, + "GSM8K": 22.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0a1cd69beed347cd80a290ce5b568c03264ec595", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/duplicitous-mammal-13b", + "Average \u2b06\ufe0f": 56.57, + "ARC": 61.69, + "HellaSwag": 83.79, + "MMLU": 57.5, + "TruthfulQA": 52.27, + "Winogrande": 75.06, + "GSM8K": 9.1, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a05d0562b8da2ac2e76aa65984e8063249bc85c8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/OpenRP-13B", + "Average \u2b06\ufe0f": 56.57, + "ARC": 62.12, + "HellaSwag": 82.6, + "MMLU": 57.5, + "TruthfulQA": 48.29, + "Winogrande": 76.01, + "GSM8K": 12.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "d11815287c51ef51485fb003f8f72773cf6f19a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fangzhaoz\/pearl7B_tuneonGSM8K", + "Average \u2b06\ufe0f": 56.56, + "ARC": 55.63, + "HellaSwag": 73.31, + "MMLU": 44.95, + "TruthfulQA": 54.16, + "Winogrande": 71.35, + "GSM8K": 39.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1b5ac00479a05bb39077a6644e78f1d3a93daf93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/MM-ReMM-L2-20B", + "Average \u2b06\ufe0f": 56.55, + "ARC": 60.84, + "HellaSwag": 85.18, + "MMLU": 56.45, + "TruthfulQA": 53.33, + "Winogrande": 75.77, + "GSM8K": 7.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "37869800c15fb37d017ea83bb50fec6d6141f6ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sauce1337\/BerrySauce-L2-13b", + "Average \u2b06\ufe0f": 56.55, + "ARC": 62.29, + "HellaSwag": 83.78, + "MMLU": 57.1, + "TruthfulQA": 48.3, + "Winogrande": 76.09, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c8788874b78c84bc5593586d16fbd8ae7b5b2991", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bn22\/DolphinMini-Mistral-7B", + "Average \u2b06\ufe0f": 56.53, + "ARC": 61.18, + "HellaSwag": 84.25, + "MMLU": 61.94, + "TruthfulQA": 52.34, + "Winogrande": 79.32, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "16ddf12ee58e71664f7e76551294ba54794c7903", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/MLewdBoros-L2-13B", + "Average \u2b06\ufe0f": 56.51, + "ARC": 62.54, + "HellaSwag": 83.9, + "MMLU": 56.57, + "TruthfulQA": 48.14, + "Winogrande": 76.95, + "GSM8K": 10.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "a3033ac5825662f1c66418d7543648dc76980185", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/Platypus2xOpenOrca-13B-IA3-v4", + "Average \u2b06\ufe0f": 56.49, + "ARC": 61.43, + "HellaSwag": 81.84, + "MMLU": 59.02, + "TruthfulQA": 48.64, + "Winogrande": 77.19, + "GSM8K": 10.84, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3aa9abe9cb2e5c699f80935e04fbb351cdfbf21b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PulsarAI\/EnsembleV5-Nova-13B", + "Average \u2b06\ufe0f": 56.49, + "ARC": 62.71, + "HellaSwag": 82.55, + "MMLU": 56.79, + "TruthfulQA": 49.86, + "Winogrande": 76.24, + "GSM8K": 10.77, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3e25556187ba576082a85c270d2d4b4ea6ea9f6f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/EnsembleV5-Nova-13B", + "Average \u2b06\ufe0f": 56.49, + "ARC": 62.71, + "HellaSwag": 82.55, + "MMLU": 56.79, + "TruthfulQA": 49.86, + "Winogrande": 76.24, + "GSM8K": 10.77, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7ba38d309709d35149b4a18f94096875885035ae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PygmalionAI\/mythalion-13b", + "Average \u2b06\ufe0f": 56.48, + "ARC": 61.26, + "HellaSwag": 83.81, + "MMLU": 56.53, + "TruthfulQA": 46.56, + "Winogrande": 77.43, + "GSM8K": 13.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 119.0, + "Available on the hub": true, + "Model sha": "24916f62b8243a7e4646ea53eeb45d890cbd308f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jingyeom\/SOLAR_KO_1.3_deup", + "Average \u2b06\ufe0f": 56.47, + "ARC": 55.97, + "HellaSwag": 79.97, + "MMLU": 55.88, + "TruthfulQA": 47.55, + "Winogrande": 76.87, + "GSM8K": 22.59, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3218e4304fe55ec950347c96018f14f60baca25d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-code-mistral-7b-v2.0", + "Average \u2b06\ufe0f": 56.47, + "ARC": 52.47, + "HellaSwag": 75.61, + "MMLU": 51.31, + "TruthfulQA": 52.05, + "Winogrande": 71.43, + "GSM8K": 35.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "8371b49e786758da62de015daa006c0e58b7ce82", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/WizardLM-30B-Uncensored", + "Average \u2b06\ufe0f": 56.46, + "ARC": 60.24, + "HellaSwag": 82.93, + "MMLU": 56.8, + "TruthfulQA": 51.57, + "Winogrande": 74.35, + "GSM8K": 12.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "761783745fcb97831ad8035d3cbd5de484aca3ce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SciPhi\/SciPhi-Self-RAG-Mistral-7B-32k", + "Average \u2b06\ufe0f": 56.46, + "ARC": 57.34, + "HellaSwag": 80.44, + "MMLU": 60.81, + "TruthfulQA": 45.63, + "Winogrande": 74.82, + "GSM8K": 19.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 76.0, + "Available on the hub": true, + "Model sha": "640192e2ba5898f87c407a9f771fc270f7628dee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "royallab\/Pygmalion-2-13b-SuperCOT", + "Average \u2b06\ufe0f": 56.46, + "ARC": 63.23, + "HellaSwag": 83.68, + "MMLU": 54.9, + "TruthfulQA": 53.14, + "Winogrande": 77.51, + "GSM8K": 6.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "763b3fd5afc3e7fb6c7c8768d40f06901c8d5913", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jefferylovely\/AiMaven-Orca2", + "Average \u2b06\ufe0f": 56.45, + "ARC": 54.69, + "HellaSwag": 79.0, + "MMLU": 54.61, + "TruthfulQA": 53.43, + "Winogrande": 74.35, + "GSM8K": 22.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fbba65dad747e1461c2b024fe6cc690a3b20db24", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Stheno-Inverted-L2-13B", + "Average \u2b06\ufe0f": 56.44, + "ARC": 59.3, + "HellaSwag": 82.9, + "MMLU": 56.45, + "TruthfulQA": 52.04, + "Winogrande": 74.74, + "GSM8K": 13.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "efaf592c95ae8e769e0d56d36ba4ed23e3bf4059", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Nova-13B", + "Average \u2b06\ufe0f": 56.44, + "ARC": 62.71, + "HellaSwag": 82.57, + "MMLU": 57.98, + "TruthfulQA": 51.34, + "Winogrande": 77.27, + "GSM8K": 6.75, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ae1145f9fa846ab8d39d8b7da888287ef917efb5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Deita-4b", + "Average \u2b06\ufe0f": 56.43, + "ARC": 46.08, + "HellaSwag": 71.81, + "MMLU": 55.46, + "TruthfulQA": 50.23, + "Winogrande": 66.14, + "GSM8K": 48.9, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "a22c9858867e4015268c63fcb495ef922f95a097", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Stheno-L2-13B", + "Average \u2b06\ufe0f": 56.43, + "ARC": 61.01, + "HellaSwag": 83.95, + "MMLU": 56.33, + "TruthfulQA": 50.18, + "Winogrande": 75.14, + "GSM8K": 11.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "c4e7b771e30fdbfd6bd2e66a6928024bd5692bbd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Mythical-Destroyer-L2-13B", + "Average \u2b06\ufe0f": 56.39, + "ARC": 58.7, + "HellaSwag": 82.0, + "MMLU": 57.66, + "TruthfulQA": 56.35, + "Winogrande": 74.66, + "GSM8K": 8.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7c87376b201b1c30c4e12c0b7bc2f28f017ce7bc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yeen214\/llama2_7b_merge_orcafamily", + "Average \u2b06\ufe0f": 56.38, + "ARC": 56.91, + "HellaSwag": 81.17, + "MMLU": 51.49, + "TruthfulQA": 49.68, + "Winogrande": 75.93, + "GSM8K": 23.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fb65f697de632f2f3fef57fc3cd12fb5e4913a89", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PocketDoc\/Dans-AdventurousWinds-Mk2-7b", + "Average \u2b06\ufe0f": 56.38, + "ARC": 58.19, + "HellaSwag": 83.48, + "MMLU": 61.8, + "TruthfulQA": 43.56, + "Winogrande": 76.32, + "GSM8K": 14.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "cfcc969a7e97275b2298253f1eabf4575e5a3768", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/MLewd-v2.4-13B", + "Average \u2b06\ufe0f": 56.37, + "ARC": 61.69, + "HellaSwag": 83.83, + "MMLU": 55.1, + "TruthfulQA": 53.34, + "Winogrande": 74.51, + "GSM8K": 9.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "6f6ec6024ee054020e49fd96f149919692848f0b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-code-mistral-7b-v2.0", + "Average \u2b06\ufe0f": 56.37, + "ARC": 52.3, + "HellaSwag": 75.61, + "MMLU": 51.28, + "TruthfulQA": 52.05, + "Winogrande": 71.35, + "GSM8K": 35.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "8371b49e786758da62de015daa006c0e58b7ce82", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/airoboros-l2-13b-2.2.1", + "Average \u2b06\ufe0f": 56.36, + "ARC": 60.92, + "HellaSwag": 83.77, + "MMLU": 56.47, + "TruthfulQA": 49.42, + "Winogrande": 76.01, + "GSM8K": 11.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "9b2dbc1f6f17a162228799df6e9449c903ddf04d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_v3.1", + "Average \u2b06\ufe0f": 56.36, + "ARC": 59.81, + "HellaSwag": 82.8, + "MMLU": 56.76, + "TruthfulQA": 44.45, + "Winogrande": 76.24, + "GSM8K": 18.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "a95be7130d32da99bcd484f6f436b2dd49341110", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bartowski\/internlm2-math-20b-llama", + "Average \u2b06\ufe0f": 56.35, + "ARC": 59.98, + "HellaSwag": 81.64, + "MMLU": 65.07, + "TruthfulQA": 52.9, + "Winogrande": 76.4, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.86, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "fb39351b1b98849aa87f486fa3130d97c92cb0fa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/Darewin-7B-v2", + "Average \u2b06\ufe0f": 56.34, + "ARC": 62.63, + "HellaSwag": 78.28, + "MMLU": 53.01, + "TruthfulQA": 50.99, + "Winogrande": 73.95, + "GSM8K": 19.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c0b08aff3f8cc55470b3e3861e45c86d543f2ac1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Doctor-Shotgun\/CalliopeDS-L2-13B", + "Average \u2b06\ufe0f": 56.34, + "ARC": 60.49, + "HellaSwag": 83.38, + "MMLU": 55.8, + "TruthfulQA": 51.32, + "Winogrande": 77.03, + "GSM8K": 10.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "agpl-3.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "b373eda586a6527e62382eda5480204652a82499", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "iGenius-AI-Team\/LLAMA-13B-test-finetuning", + "Average \u2b06\ufe0f": 56.34, + "ARC": 58.02, + "HellaSwag": 82.36, + "MMLU": 54.27, + "TruthfulQA": 44.14, + "Winogrande": 76.72, + "GSM8K": 22.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5bd0eb026b12c59fd198f307c0c17188af69744c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v4-qwen1_5-4b", + "Average \u2b06\ufe0f": 56.34, + "ARC": 46.08, + "HellaSwag": 70.8, + "MMLU": 55.11, + "TruthfulQA": 47.29, + "Winogrande": 67.64, + "GSM8K": 51.1, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "574e846dbb8842b1b578b7e44eec318588579cc6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Gryphe\/MythoMix-L2-13b", + "Average \u2b06\ufe0f": 56.31, + "ARC": 61.09, + "HellaSwag": 83.86, + "MMLU": 55.42, + "TruthfulQA": 52.08, + "Winogrande": 75.45, + "GSM8K": 9.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "eca790fb9394c9c61be27ef709080b3b92783a45", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/mistral-7b_open_platypus", + "Average \u2b06\ufe0f": 56.29, + "ARC": 55.8, + "HellaSwag": 82.13, + "MMLU": 59.76, + "TruthfulQA": 48.87, + "Winogrande": 78.61, + "GSM8K": 12.59, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b9a60b9ad0fe06bd314ffe99d543f1df6ecd10da", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/Platypus2xOpenOrca-13B-IA3-v2.1", + "Average \u2b06\ufe0f": 56.29, + "ARC": 62.29, + "HellaSwag": 82.09, + "MMLU": 57.91, + "TruthfulQA": 47.03, + "Winogrande": 77.43, + "GSM8K": 10.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "31e1e3235515717a151915131bc970be188d964e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Uncensored-Jordan-13B", + "Average \u2b06\ufe0f": 56.27, + "ARC": 57.42, + "HellaSwag": 82.7, + "MMLU": 55.75, + "TruthfulQA": 50.51, + "Winogrande": 76.16, + "GSM8K": 15.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c56a396342133bbd75ab3f79622c85cb55be49a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-code-mistral-orca-7b-v1.0", + "Average \u2b06\ufe0f": 56.24, + "ARC": 59.64, + "HellaSwag": 82.25, + "MMLU": 61.33, + "TruthfulQA": 48.45, + "Winogrande": 77.51, + "GSM8K": 8.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "f7db67fe6c82657b35d0ffcf8b7ff1568d979482", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/StableBeluga-13B-instruct-PL-lora_unload", + "Average \u2b06\ufe0f": 56.24, + "ARC": 60.92, + "HellaSwag": 82.13, + "MMLU": 56.99, + "TruthfulQA": 48.64, + "Winogrande": 76.56, + "GSM8K": 12.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "6e1a6e1f91f6ac97b643be1bd24be6096e2e7dd3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r8_a16", + "Average \u2b06\ufe0f": 56.23, + "ARC": 59.73, + "HellaSwag": 82.3, + "MMLU": 55.73, + "TruthfulQA": 37.95, + "Winogrande": 77.11, + "GSM8K": 24.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "afa40d22d578e631c90017ae0cc67734d6f0b5d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "arlineka\/Brunhilde-13b", + "Average \u2b06\ufe0f": 56.2, + "ARC": 60.49, + "HellaSwag": 83.49, + "MMLU": 56.18, + "TruthfulQA": 52.35, + "Winogrande": 75.53, + "GSM8K": 9.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ce50fccfb850fc07618c6d215823b754b42346ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KatyTheCutie\/EstopianMaid-13B", + "Average \u2b06\ufe0f": 56.2, + "ARC": 60.49, + "HellaSwag": 83.49, + "MMLU": 56.18, + "TruthfulQA": 52.35, + "Winogrande": 75.53, + "GSM8K": 9.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5770d488c48c4c97ee53572dd8577aae584f9230", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "adamo1139\/Yi-6B-200K-AEZAKMI-v2-rawrr1-DPO", + "Average \u2b06\ufe0f": 56.2, + "ARC": 52.47, + "HellaSwag": 77.04, + "MMLU": 62.57, + "TruthfulQA": 47.15, + "Winogrande": 71.03, + "GSM8K": 26.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9271df80f5221362cb5ffd71f463f8f8d08c31dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Gryphe\/MythoLogic-L2-13b", + "Average \u2b06\ufe0f": 56.19, + "ARC": 61.01, + "HellaSwag": 83.93, + "MMLU": 55.7, + "TruthfulQA": 48.64, + "Winogrande": 76.09, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "665948fc79acc2bcce3e9e7d2b0689ca43ae62d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/Synatra-11B-Testbench", + "Average \u2b06\ufe0f": 56.17, + "ARC": 57.34, + "HellaSwag": 78.66, + "MMLU": 55.56, + "TruthfulQA": 51.97, + "Winogrande": 75.77, + "GSM8K": 17.74, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 11.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9399ea6c2a1d955e31d6b4d68b2b86115aea0e59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r128_a16", + "Average \u2b06\ufe0f": 56.16, + "ARC": 59.9, + "HellaSwag": 82.31, + "MMLU": 55.59, + "TruthfulQA": 38.22, + "Winogrande": 77.03, + "GSM8K": 23.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6e8f872757721020c2ae983b6e186fe36105ef2d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Stheno-1.2-L2-13B", + "Average \u2b06\ufe0f": 56.15, + "ARC": 60.75, + "HellaSwag": 83.67, + "MMLU": 56.27, + "TruthfulQA": 50.32, + "Winogrande": 74.98, + "GSM8K": 10.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e76f35fe771ef142d6629092bd4a93301fd6cd4a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/Orca-2-13b-SFT-v6", + "Average \u2b06\ufe0f": 56.15, + "ARC": 60.41, + "HellaSwag": 80.46, + "MMLU": 59.51, + "TruthfulQA": 54.01, + "Winogrande": 77.43, + "GSM8K": 5.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "c31bf6f2d18f8fa4f6a25444ace549c4394b2b5a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elyza\/ELYZA-japanese-Llama-2-13b", + "Average \u2b06\ufe0f": 56.14, + "ARC": 57.0, + "HellaSwag": 80.89, + "MMLU": 54.38, + "TruthfulQA": 40.43, + "Winogrande": 76.87, + "GSM8K": 27.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "24be61d31af8ac3e8c57d924c749ca3cf5f681ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/SpeechlessV1-Nova-13B", + "Average \u2b06\ufe0f": 56.14, + "ARC": 61.77, + "HellaSwag": 82.68, + "MMLU": 57.75, + "TruthfulQA": 51.44, + "Winogrande": 77.43, + "GSM8K": 5.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fbe6f0e32b5ecf9d75510d0b11a286466f46d79e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r32_a16", + "Average \u2b06\ufe0f": 56.14, + "ARC": 59.9, + "HellaSwag": 82.33, + "MMLU": 55.67, + "TruthfulQA": 38.3, + "Winogrande": 77.03, + "GSM8K": 23.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5cae6af3eb89c28c8cd90322685dd4d0235d9946", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HenryJJ\/Instruct_Yi-6B_Dolly_CodeAlpaca", + "Average \u2b06\ufe0f": 56.11, + "ARC": 53.16, + "HellaSwag": 75.3, + "MMLU": 63.06, + "TruthfulQA": 41.42, + "Winogrande": 75.37, + "GSM8K": 28.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "97c31498b579cf4808195dd21a858a258d40b2dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WhoTookMyAmogusNickname\/NewHope_HF_not_official", + "Average \u2b06\ufe0f": 56.11, + "ARC": 61.09, + "HellaSwag": 84.03, + "MMLU": 55.73, + "TruthfulQA": 44.96, + "Winogrande": 74.98, + "GSM8K": 15.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f587f4a31de6818f4200d9cdc7f116ca8ba1cdc2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Austism\/chronos-hermes-13b-v2", + "Average \u2b06\ufe0f": 56.1, + "ARC": 60.32, + "HellaSwag": 83.21, + "MMLU": 55.05, + "TruthfulQA": 50.91, + "Winogrande": 75.37, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "2f0e2cb734685a6ce0736a9f3e909a795d7592cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PulsarAI\/Nebula-7B", + "Average \u2b06\ufe0f": 56.1, + "ARC": 59.3, + "HellaSwag": 83.46, + "MMLU": 57.0, + "TruthfulQA": 45.56, + "Winogrande": 76.4, + "GSM8K": 14.86, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "569f848698a468fb03d37033c67f3734bbaec127", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r8_a4", + "Average \u2b06\ufe0f": 56.1, + "ARC": 59.9, + "HellaSwag": 82.47, + "MMLU": 55.47, + "TruthfulQA": 38.04, + "Winogrande": 77.03, + "GSM8K": 23.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8793eb75fb25d1cbbcd2811cbbe8f571291f2bdd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kaist-ai\/prometheus-13b-v1.0", + "Average \u2b06\ufe0f": 56.09, + "ARC": 53.24, + "HellaSwag": 80.75, + "MMLU": 51.49, + "TruthfulQA": 45.66, + "Winogrande": 73.72, + "GSM8K": 31.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 89.0, + "Available on the hub": true, + "Model sha": "9088377314f91af4b48940e09a0c76d0878f5020", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e4", + "Average \u2b06\ufe0f": 56.08, + "ARC": 60.07, + "HellaSwag": 82.45, + "MMLU": 55.37, + "TruthfulQA": 38.52, + "Winogrande": 76.95, + "GSM8K": 23.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dbe93078c2e3b8744ca4fc6fbba9fa1f43dd6dcd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/BigMaid-20B-v1.0", + "Average \u2b06\ufe0f": 56.07, + "ARC": 61.35, + "HellaSwag": 85.26, + "MMLU": 57.15, + "TruthfulQA": 55.29, + "Winogrande": 75.3, + "GSM8K": 2.05, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d37d99b4656190a23ec51baaad4d1bf6421e67c5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "augtoma\/qCammel-13", + "Average \u2b06\ufe0f": 56.05, + "ARC": 60.84, + "HellaSwag": 83.66, + "MMLU": 56.73, + "TruthfulQA": 47.54, + "Winogrande": 76.16, + "GSM8K": 11.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "af473e64f6a4fa02a7e24ee7679eea9505eb179d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r2_a4", + "Average \u2b06\ufe0f": 56.03, + "ARC": 59.98, + "HellaSwag": 82.37, + "MMLU": 55.42, + "TruthfulQA": 38.14, + "Winogrande": 76.56, + "GSM8K": 23.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7253a71f780be10eb6c3590bf484cfe0975c3a4c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/ReMM-SLERP-L2-13B", + "Average \u2b06\ufe0f": 56.03, + "ARC": 60.92, + "HellaSwag": 83.56, + "MMLU": 55.33, + "TruthfulQA": 51.97, + "Winogrande": 75.22, + "GSM8K": 9.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "27baccf242bc1dc34fc39661a40bbf867cbea8b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "The-Face-Of-Goonery\/Huginn-13b-v1.2", + "Average \u2b06\ufe0f": 56.03, + "ARC": 60.92, + "HellaSwag": 83.56, + "MMLU": 55.33, + "TruthfulQA": 51.97, + "Winogrande": 75.22, + "GSM8K": 9.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": false, + "Model sha": "cb3562e7aae05a95fe61610b7b8f4957d3529ce7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/carl-33b", + "Average \u2b06\ufe0f": 56.03, + "ARC": 64.59, + "HellaSwag": 85.27, + "MMLU": 58.38, + "TruthfulQA": 45.32, + "Winogrande": 76.24, + "GSM8K": 6.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "5f80b372b493d901cab4490b4f23c71499023615", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WebraftAI\/synapsellm-7b-mistral-v0.5-preview", + "Average \u2b06\ufe0f": 56.03, + "ARC": 52.73, + "HellaSwag": 76.51, + "MMLU": 54.67, + "TruthfulQA": 55.16, + "Winogrande": 74.35, + "GSM8K": 22.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d1b4d9a4657d145ce7cda431ed46076c1518af55", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vilm\/Quyen-v0.1", + "Average \u2b06\ufe0f": 56.02, + "ARC": 48.21, + "HellaSwag": 72.49, + "MMLU": 52.88, + "TruthfulQA": 51.53, + "Winogrande": 65.11, + "GSM8K": 45.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "e171839fa60645d775b1555c86a1ab52e7de82f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/neural-chat-7b-v3-1-Nebula-v2-7B", + "Average \u2b06\ufe0f": 56.01, + "ARC": 61.77, + "HellaSwag": 80.21, + "MMLU": 59.07, + "TruthfulQA": 58.56, + "Winogrande": 71.82, + "GSM8K": 4.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0b98e4ca35764da09cabcaaebbdac1f827629219", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Gryphe\/MythoMax-L2-13b", + "Average \u2b06\ufe0f": 56.0, + "ARC": 60.92, + "HellaSwag": 83.56, + "MMLU": 55.33, + "TruthfulQA": 51.97, + "Winogrande": 75.22, + "GSM8K": 9.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 209.0, + "Available on the hub": true, + "Model sha": "faa4ef8c87dbb00d447904ceb048d49b6a463d07", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "The-Face-Of-Goonery\/huginnv1.2", + "Average \u2b06\ufe0f": 55.98, + "ARC": 62.37, + "HellaSwag": 84.28, + "MMLU": 57.02, + "TruthfulQA": 47.81, + "Winogrande": 75.22, + "GSM8K": 9.17, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aed4ddc951c657993939fa5b87a4088550569a3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Nous-Hermes-Llama2-13b", + "Average \u2b06\ufe0f": 55.97, + "ARC": 61.52, + "HellaSwag": 83.29, + "MMLU": 55.11, + "TruthfulQA": 50.38, + "Winogrande": 75.45, + "GSM8K": 10.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": [ + "mit" + ], + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 277.0, + "Available on the hub": true, + "Model sha": "8f95aa9cd207db7b24179fc779c2b8973e71bee2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/Samantha-1.11-13b", + "Average \u2b06\ufe0f": 55.97, + "ARC": 60.84, + "HellaSwag": 82.99, + "MMLU": 55.96, + "TruthfulQA": 47.72, + "Winogrande": 76.01, + "GSM8K": 12.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e355ead3a939f471fe2586201156fb972fad0f4b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/LongQLoRA-Vicuna-13b-8k", + "Average \u2b06\ufe0f": 55.96, + "ARC": 56.4, + "HellaSwag": 81.05, + "MMLU": 53.68, + "TruthfulQA": 47.07, + "Winogrande": 74.51, + "GSM8K": 23.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "470c90e30f9e49e948e066373c3ea6878ee5f171", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r2_a64", + "Average \u2b06\ufe0f": 55.95, + "ARC": 60.07, + "HellaSwag": 82.0, + "MMLU": 55.18, + "TruthfulQA": 37.41, + "Winogrande": 76.87, + "GSM8K": 24.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5249d8dde98eccf4671d89a8e1fd7504edb1464e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Walter-SOLAR-11B", + "Average \u2b06\ufe0f": 55.95, + "ARC": 60.41, + "HellaSwag": 84.86, + "MMLU": 64.99, + "TruthfulQA": 44.88, + "Winogrande": 79.56, + "GSM8K": 0.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "e7bbf8ba7572aced748c7fc7368dc024e2df7df0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ArianAskari\/SOLID-SFT-DPO-MixQV3-SOLIDChosen-SFTRejected-Zephyr-7b-beta", + "Average \u2b06\ufe0f": 55.93, + "ARC": 59.56, + "HellaSwag": 82.53, + "MMLU": 59.6, + "TruthfulQA": 57.58, + "Winogrande": 74.9, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d23df4c9e2bc46656e4d894475d57584181b3a24", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Nous-Hermes-13B-Code", + "Average \u2b06\ufe0f": 55.93, + "ARC": 61.18, + "HellaSwag": 83.21, + "MMLU": 55.13, + "TruthfulQA": 50.56, + "Winogrande": 75.14, + "GSM8K": 10.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "5a45cb2a6442581ce32cc19c561c49cec1db4ebb", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "PulsarAI\/Chat-AYB-Platypus2-13B", + "Average \u2b06\ufe0f": 55.93, + "ARC": 60.49, + "HellaSwag": 84.03, + "MMLU": 57.83, + "TruthfulQA": 54.52, + "Winogrande": 75.77, + "GSM8K": 2.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5a54eb9d5a66df4720ec52422f5627ccd94d5fd6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WebraftAI\/synapsellm-7b-mistral-v0.4-preview2", + "Average \u2b06\ufe0f": 55.93, + "ARC": 52.99, + "HellaSwag": 74.54, + "MMLU": 54.6, + "TruthfulQA": 53.79, + "Winogrande": 73.95, + "GSM8K": 25.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "59e4ad04a24b656401fab0e8f20de387aaa95512", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WebraftAI\/synapsellm-7b-mistral-v0.5-preview2", + "Average \u2b06\ufe0f": 55.93, + "ARC": 52.22, + "HellaSwag": 75.54, + "MMLU": 51.64, + "TruthfulQA": 55.47, + "Winogrande": 73.09, + "GSM8K": 27.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b6378fa3b7d39f946d3ce1e0b854622c2866cf7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r2_a16", + "Average \u2b06\ufe0f": 55.92, + "ARC": 59.73, + "HellaSwag": 82.38, + "MMLU": 55.27, + "TruthfulQA": 38.66, + "Winogrande": 76.64, + "GSM8K": 22.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f470726821c72a58bb400e2dc3a5571f8f650a79", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r32_a4", + "Average \u2b06\ufe0f": 55.91, + "ARC": 59.81, + "HellaSwag": 82.42, + "MMLU": 55.56, + "TruthfulQA": 38.13, + "Winogrande": 76.87, + "GSM8K": 22.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d4d0d9ed2124d79d9e5cbda8ebf45528c4f1e32d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r128_a4", + "Average \u2b06\ufe0f": 55.91, + "ARC": 59.9, + "HellaSwag": 82.43, + "MMLU": 55.44, + "TruthfulQA": 38.05, + "Winogrande": 76.8, + "GSM8K": 22.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "029666001d8c6be175e42206969a593a4a3f4cb5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sauce1337\/AppleSauce-L2-13b", + "Average \u2b06\ufe0f": 55.91, + "ARC": 61.01, + "HellaSwag": 83.61, + "MMLU": 57.07, + "TruthfulQA": 47.81, + "Winogrande": 75.93, + "GSM8K": 10.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ba253c52eb85e24987c81e5d36b5a9a00e276ce7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-13B-v1.2", + "Average \u2b06\ufe0f": 55.9, + "ARC": 61.26, + "HellaSwag": 82.93, + "MMLU": 56.47, + "TruthfulQA": 47.27, + "Winogrande": 76.48, + "GSM8K": 10.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "60d4937ac3c4dcb84c40bbf7265c5cc7f5f3d4f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openBuddy\/openbuddy-llama2-34b-v11.1-bf16", + "Average \u2b06\ufe0f": 55.88, + "ARC": 50.0, + "HellaSwag": 71.19, + "MMLU": 55.71, + "TruthfulQA": 53.01, + "Winogrande": 70.8, + "GSM8K": 34.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 33.53, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "21ac0d26c0097e5ac5b4a757493574b156da7731", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-codellama2-34b-v11.1-bf16", + "Average \u2b06\ufe0f": 55.88, + "ARC": 50.0, + "HellaSwag": 71.19, + "MMLU": 55.71, + "TruthfulQA": 53.01, + "Winogrande": 70.8, + "GSM8K": 34.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "1b361b3634bf59913b47c9dad1b138e99833472b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "namirocks\/tutor-model-13b-ep3", + "Average \u2b06\ufe0f": 55.88, + "ARC": 57.34, + "HellaSwag": 81.51, + "MMLU": 57.02, + "TruthfulQA": 52.99, + "Winogrande": 74.35, + "GSM8K": 12.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "714f04010ca1c3d72bbeead4a14695576ad36a88", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-class-tutor-13b-ep3", + "Average \u2b06\ufe0f": 55.88, + "ARC": 57.34, + "HellaSwag": 81.51, + "MMLU": 57.02, + "TruthfulQA": 52.99, + "Winogrande": 74.35, + "GSM8K": 12.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2cf2424169d31299caff38cd7ac68e69974d6535", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-llama2-13b-v1.2", + "Average \u2b06\ufe0f": 55.87, + "ARC": 60.67, + "HellaSwag": 80.46, + "MMLU": 56.51, + "TruthfulQA": 51.03, + "Winogrande": 74.82, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "97279d20a8c7e2d0576c9ff4b2e15a421c40d58a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Radiantloom\/radintloom-mistral-7b-fusion", + "Average \u2b06\ufe0f": 55.86, + "ARC": 62.03, + "HellaSwag": 82.26, + "MMLU": 63.82, + "TruthfulQA": 47.19, + "Winogrande": 79.87, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "654f37927cbc789f0206dcc333201de1b30edd03", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/Synatra-V0.1-7B-Instruct", + "Average \u2b06\ufe0f": 55.86, + "ARC": 55.29, + "HellaSwag": 76.63, + "MMLU": 55.29, + "TruthfulQA": 55.76, + "Winogrande": 72.77, + "GSM8K": 19.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "7ee3416f31a3c7e8d5ab4295ac1b641075f36345", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "maywell\/Synatra-V0.1-7B", + "Average \u2b06\ufe0f": 55.86, + "ARC": 55.29, + "HellaSwag": 76.63, + "MMLU": 55.29, + "TruthfulQA": 55.76, + "Winogrande": 72.77, + "GSM8K": 19.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7ee3416f31a3c7e8d5ab4295ac1b641075f36345", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/Newton-7B", + "Average \u2b06\ufe0f": 55.85, + "ARC": 63.99, + "HellaSwag": 81.72, + "MMLU": 62.78, + "TruthfulQA": 44.36, + "Winogrande": 78.85, + "GSM8K": 3.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "cfa9b51541b423bafc1e87d942000d8ab052e065", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_attn_only", + "Average \u2b06\ufe0f": 55.85, + "ARC": 60.75, + "HellaSwag": 82.09, + "MMLU": 55.52, + "TruthfulQA": 38.16, + "Winogrande": 75.85, + "GSM8K": 22.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0ecc726751e2e07255ac4cab41040bbf24321042", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/7B-DPO-alpha", + "Average \u2b06\ufe0f": 55.84, + "ARC": 50.85, + "HellaSwag": 73.0, + "MMLU": 63.39, + "TruthfulQA": 57.58, + "Winogrande": 67.56, + "GSM8K": 22.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "wtfpl", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 57.0, + "Available on the hub": true, + "Model sha": "36501a519950fb80c2e7df77e12c9110dca580f4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "janhq\/Mistral-7B-Instruct-v0.2-DARE", + "Average \u2b06\ufe0f": 55.84, + "ARC": 61.95, + "HellaSwag": 75.62, + "MMLU": 49.99, + "TruthfulQA": 54.36, + "Winogrande": 74.98, + "GSM8K": 18.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "98731ddd2dd52fd1b2c69c4cb95bbb1ac03ce496", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Danielbrdz\/Barcenas-13b", + "Average \u2b06\ufe0f": 55.83, + "ARC": 61.26, + "HellaSwag": 82.13, + "MMLU": 56.25, + "TruthfulQA": 46.67, + "Winogrande": 76.32, + "GSM8K": 12.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fa988ba73f67ad0c8e7fa8f408106ea040070258", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "feidfoe\/Metamath-reproduce-7b", + "Average \u2b06\ufe0f": 55.81, + "ARC": 47.18, + "HellaSwag": 73.65, + "MMLU": 42.94, + "TruthfulQA": 41.58, + "Winogrande": 71.35, + "GSM8K": 58.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9955b88b535863a36ee9d9a255260bbc2cdab47b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/very-test", + "Average \u2b06\ufe0f": 55.8, + "ARC": 63.91, + "HellaSwag": 81.71, + "MMLU": 62.89, + "TruthfulQA": 44.28, + "Winogrande": 78.69, + "GSM8K": 3.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "198a56764da3541778771d7882b6facf3debb107", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-OpenOrca_5w", + "Average \u2b06\ufe0f": 55.8, + "ARC": 61.01, + "HellaSwag": 82.82, + "MMLU": 56.09, + "TruthfulQA": 44.87, + "Winogrande": 77.74, + "GSM8K": 12.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ddd810c9150492d7318656acac44849651edbf2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abacusai\/Fewshot-Metamath-OrcaVicuna-Mistral-10B", + "Average \u2b06\ufe0f": 55.79, + "ARC": 56.4, + "HellaSwag": 78.12, + "MMLU": 59.52, + "TruthfulQA": 50.98, + "Winogrande": 76.48, + "GSM8K": 13.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5fc7d7bb8ee87dab18d74bb1e25024eba3019a0b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Nous-Hermes-Llama2-13b", + "Average \u2b06\ufe0f": 55.75, + "ARC": 61.26, + "HellaSwag": 83.26, + "MMLU": 55.04, + "TruthfulQA": 50.41, + "Winogrande": 75.37, + "GSM8K": 9.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": [ + "mit" + ], + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 277.0, + "Available on the hub": true, + "Model sha": "8f95aa9cd207db7b24179fc779c2b8973e71bee2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "garage-bAInd\/Stable-Platypus2-13B", + "Average \u2b06\ufe0f": 55.75, + "ARC": 62.71, + "HellaSwag": 82.29, + "MMLU": 58.3, + "TruthfulQA": 52.52, + "Winogrande": 76.87, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "0e54aa49c24617e30a23a20c0c5da61419b9fe68", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lu-vae\/llama2-13B-sharegpt4-orca-openplatypus-8w", + "Average \u2b06\ufe0f": 55.75, + "ARC": 62.8, + "HellaSwag": 84.04, + "MMLU": 55.13, + "TruthfulQA": 45.66, + "Winogrande": 75.14, + "GSM8K": 11.75, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ad086aacf0176911133b6cccfb34364afce9de5a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fionazhang\/mistral-experiment-6", + "Average \u2b06\ufe0f": 55.75, + "ARC": 55.8, + "HellaSwag": 81.45, + "MMLU": 55.57, + "TruthfulQA": 45.69, + "Winogrande": 73.8, + "GSM8K": 22.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "df18562607b2ba0fc296da17c398b9d3451c6a89", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PulsarAI\/CollectiveCognition-v1.1-Nebula-7B", + "Average \u2b06\ufe0f": 55.72, + "ARC": 58.11, + "HellaSwag": 82.39, + "MMLU": 57.03, + "TruthfulQA": 53.53, + "Winogrande": 73.72, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c41d373a2d49b79236d6c4d0dfc4086e709c07eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_v3.1", + "Average \u2b06\ufe0f": 55.71, + "ARC": 60.15, + "HellaSwag": 82.84, + "MMLU": 56.84, + "TruthfulQA": 44.38, + "Winogrande": 76.24, + "GSM8K": 13.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "cc708183e430234b8718c08d9f90474569eabeac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Stheno-1.1-L2-13B", + "Average \u2b06\ufe0f": 55.71, + "ARC": 60.75, + "HellaSwag": 83.64, + "MMLU": 56.39, + "TruthfulQA": 50.3, + "Winogrande": 75.22, + "GSM8K": 7.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0f45a9f834dd216ce25ffa606b3b1ef2c99e7acd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lu-vae\/llama2-13b-sharegpt4-test", + "Average \u2b06\ufe0f": 55.69, + "ARC": 58.02, + "HellaSwag": 82.65, + "MMLU": 55.99, + "TruthfulQA": 48.27, + "Winogrande": 76.09, + "GSM8K": 13.12, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2be36a2dab4ed0f97727a1508367f53d59950818", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r128_a64", + "Average \u2b06\ufe0f": 55.69, + "ARC": 59.04, + "HellaSwag": 82.27, + "MMLU": 55.54, + "TruthfulQA": 37.2, + "Winogrande": 76.72, + "GSM8K": 23.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6446e661b63b07af1c57b623de637ca1c6fcb7b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "meta-llama\/Llama-2-13b-hf", + "Average \u2b06\ufe0f": 55.69, + "ARC": 59.39, + "HellaSwag": 82.13, + "MMLU": 55.77, + "TruthfulQA": 37.38, + "Winogrande": 76.64, + "GSM8K": 22.82, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 506.0, + "Available on the hub": false, + "Model sha": "7da18fb10421c3ae2a1eb92815bad75e84816e35", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_v3.2", + "Average \u2b06\ufe0f": 55.68, + "ARC": 59.64, + "HellaSwag": 82.68, + "MMLU": 56.68, + "TruthfulQA": 44.49, + "Winogrande": 76.95, + "GSM8K": 13.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "65320bf6dbe0cb4682d45a9e55dbc876502f8b66", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-llama2-13b", + "Average \u2b06\ufe0f": 55.68, + "ARC": 59.13, + "HellaSwag": 81.99, + "MMLU": 55.49, + "TruthfulQA": 51.57, + "Winogrande": 74.66, + "GSM8K": 11.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": false, + "Model sha": "6e918dc8beb1e764def5938fdb8e3f64ba40a456", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5", + "Average \u2b06\ufe0f": 55.67, + "ARC": 59.22, + "HellaSwag": 82.41, + "MMLU": 55.67, + "TruthfulQA": 37.65, + "Winogrande": 76.95, + "GSM8K": 22.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e3ba7c482d57dfe65e52a27b21d75a1da59230f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elyza\/ELYZA-japanese-Llama-2-13b-fast", + "Average \u2b06\ufe0f": 55.67, + "ARC": 55.89, + "HellaSwag": 80.73, + "MMLU": 54.4, + "TruthfulQA": 40.31, + "Winogrande": 77.19, + "GSM8K": 25.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "f2d798d1a7dc6c254575b7a4fe24f4c76652e6d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-hermes-coig-lite-13b", + "Average \u2b06\ufe0f": 55.65, + "ARC": 59.47, + "HellaSwag": 82.28, + "MMLU": 55.18, + "TruthfulQA": 47.6, + "Winogrande": 78.61, + "GSM8K": 10.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": [ + "mit" + ], + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2ee11d9c7acaefb723796227e2ad099b165f0dd9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/U-Amethyst-20B", + "Average \u2b06\ufe0f": 55.65, + "ARC": 62.2, + "HellaSwag": 83.11, + "MMLU": 55.88, + "TruthfulQA": 53.2, + "Winogrande": 74.19, + "GSM8K": 5.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.99, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "c0cbe0b3c88041bb6beef27dbe85146af8dddec9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Enno-Ai\/ennodata-13b-8bit-raw-15epoch", + "Average \u2b06\ufe0f": 55.65, + "ARC": 61.6, + "HellaSwag": 82.2, + "MMLU": 57.55, + "TruthfulQA": 53.58, + "Winogrande": 77.51, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ee2ceaae9cb806bc30df84ba4d598fdf32e53b17", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Uncensored-Frank-13B", + "Average \u2b06\ufe0f": 55.64, + "ARC": 61.6, + "HellaSwag": 82.62, + "MMLU": 54.55, + "TruthfulQA": 48.34, + "Winogrande": 74.74, + "GSM8K": 11.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "73a27445e5e5a72857626e551c70542ec607f60c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "The-Face-Of-Goonery\/Huginn-V5-10.7B", + "Average \u2b06\ufe0f": 55.62, + "ARC": 63.31, + "HellaSwag": 78.8, + "MMLU": 54.22, + "TruthfulQA": 44.52, + "Winogrande": 73.72, + "GSM8K": 19.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a3d7e197ba2a96ff73bbbb2b315d38f43a1e5508", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/a", + "Average \u2b06\ufe0f": 55.61, + "ARC": 63.48, + "HellaSwag": 86.49, + "MMLU": 56.76, + "TruthfulQA": 44.55, + "Winogrande": 82.4, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dc60deab5bfc4c39904c23e6a5fd545b38301d5f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r32_a64", + "Average \u2b06\ufe0f": 55.61, + "ARC": 58.96, + "HellaSwag": 82.31, + "MMLU": 55.23, + "TruthfulQA": 37.41, + "Winogrande": 76.72, + "GSM8K": 23.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a2f587f367c78e478713c2eedeb99b2d343ad9f1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TFLai\/Nova-13B-50-step", + "Average \u2b06\ufe0f": 55.61, + "ARC": 61.6, + "HellaSwag": 82.31, + "MMLU": 57.27, + "TruthfulQA": 51.53, + "Winogrande": 76.56, + "GSM8K": 4.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1a827ccb7f00157b3cc9ce538d61a6ba8d5a65db", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Severian\/ANIMA-Phi-Neptune-Mistral-7B-v4", + "Average \u2b06\ufe0f": 55.61, + "ARC": 55.46, + "HellaSwag": 77.63, + "MMLU": 53.12, + "TruthfulQA": 59.01, + "Winogrande": 73.48, + "GSM8K": 14.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a8e18f970f7ca994740177d6c228adee9e17aba9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "defog\/sqlcoder-34b-alpha", + "Average \u2b06\ufe0f": 55.59, + "ARC": 54.18, + "HellaSwag": 75.93, + "MMLU": 54.42, + "TruthfulQA": 40.63, + "Winogrande": 73.48, + "GSM8K": 34.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 159.0, + "Available on the hub": true, + "Model sha": "6712da4d486caec81d6b1b650d0596517052cffe", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Stable-Platypus2-13B-QLoRA-0.80-epoch", + "Average \u2b06\ufe0f": 55.56, + "ARC": 62.29, + "HellaSwag": 82.46, + "MMLU": 57.09, + "TruthfulQA": 51.41, + "Winogrande": 76.56, + "GSM8K": 3.56, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0c15b8540335b3e21a976a5fc5c33b47927fea6c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Severian\/ANIMA-Phi-Neptune-Mistral-7B", + "Average \u2b06\ufe0f": 55.54, + "ARC": 55.97, + "HellaSwag": 76.22, + "MMLU": 52.89, + "TruthfulQA": 59.76, + "Winogrande": 73.48, + "GSM8K": 14.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "artistic-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": true, + "Model sha": "e8e9a4804c842b84def9e9aaae38236d4754f277", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "internlm\/internlm-20b-chat", + "Average \u2b06\ufe0f": 55.53, + "ARC": 55.38, + "HellaSwag": 78.58, + "MMLU": 58.53, + "TruthfulQA": 43.22, + "Winogrande": 78.77, + "GSM8K": 18.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "79946225fa7a215e0ebcf4440a9cce88e475deaa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-dolphin_5w", + "Average \u2b06\ufe0f": 55.53, + "ARC": 60.67, + "HellaSwag": 82.69, + "MMLU": 56.23, + "TruthfulQA": 44.41, + "Winogrande": 77.35, + "GSM8K": 11.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ec406128968b41a9b7a5f18c358f7638d696b56", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-hermes-coig-lite-13b", + "Average \u2b06\ufe0f": 55.51, + "ARC": 59.56, + "HellaSwag": 82.26, + "MMLU": 55.3, + "TruthfulQA": 47.56, + "Winogrande": 78.53, + "GSM8K": 9.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": [ + "mit" + ], + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2ee11d9c7acaefb723796227e2ad099b165f0dd9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "augmxnt\/shisa-gamma-7b-v1", + "Average \u2b06\ufe0f": 55.5, + "ARC": 53.16, + "HellaSwag": 77.3, + "MMLU": 55.23, + "TruthfulQA": 50.73, + "Winogrande": 73.88, + "GSM8K": 22.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "49bf4a58453d191845668b8ff17e4b8f0e9ccae6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Stheno-Inverted-1.2-L2-13B", + "Average \u2b06\ufe0f": 55.5, + "ARC": 59.39, + "HellaSwag": 83.01, + "MMLU": 55.77, + "TruthfulQA": 51.22, + "Winogrande": 74.66, + "GSM8K": 8.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8d2e9087093eef1c9173e167beb40b9d034a4655", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kingbri\/airolima-chronos-grad-l2-13B", + "Average \u2b06\ufe0f": 55.5, + "ARC": 59.56, + "HellaSwag": 83.5, + "MMLU": 55.78, + "TruthfulQA": 44.67, + "Winogrande": 75.85, + "GSM8K": 13.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "d2ad57b2b50361485b2b04e59a989161599cb08b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/UndiMix-v1-13b", + "Average \u2b06\ufe0f": 55.5, + "ARC": 59.47, + "HellaSwag": 82.45, + "MMLU": 55.83, + "TruthfulQA": 49.78, + "Winogrande": 75.45, + "GSM8K": 10.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fd311f52648825d6988d2f945918468ceb32289f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kingbri\/chronolima-airo-grad-l2-13B", + "Average \u2b06\ufe0f": 55.5, + "ARC": 59.56, + "HellaSwag": 83.47, + "MMLU": 55.8, + "TruthfulQA": 44.58, + "Winogrande": 75.61, + "GSM8K": 13.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "agpl-3.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "9195bd6ea775daf347a275e190665e10bf1fb54b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_v3.2", + "Average \u2b06\ufe0f": 55.49, + "ARC": 59.47, + "HellaSwag": 82.6, + "MMLU": 56.82, + "TruthfulQA": 44.51, + "Winogrande": 76.09, + "GSM8K": 13.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "bc771c901529dedbf04864d0b81452f62301f882", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Suprit\/Zhongjing-LLaMA-base", + "Average \u2b06\ufe0f": 55.47, + "ARC": 55.12, + "HellaSwag": 79.72, + "MMLU": 48.23, + "TruthfulQA": 48.88, + "Winogrande": 74.82, + "GSM8K": 26.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1b53d10b830b864d88032ae467016f8a1d7ba239", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r8_a64", + "Average \u2b06\ufe0f": 55.45, + "ARC": 59.56, + "HellaSwag": 82.18, + "MMLU": 55.32, + "TruthfulQA": 37.08, + "Winogrande": 76.16, + "GSM8K": 22.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "337b96d91b5323b1e4dc0775bccb08f5ae6928ea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-13b-v1.5", + "Average \u2b06\ufe0f": 55.41, + "ARC": 57.08, + "HellaSwag": 81.24, + "MMLU": 56.67, + "TruthfulQA": 51.51, + "Winogrande": 74.66, + "GSM8K": 11.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 159.0, + "Available on the hub": true, + "Model sha": "3deb0106f72a3a433f0c6ea0cb978bdf14bcd3a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dddsaty\/Open_Ko_SOLAR_DPO_Merge_v0.1", + "Average \u2b06\ufe0f": 55.41, + "ARC": 55.12, + "HellaSwag": 78.18, + "MMLU": 54.19, + "TruthfulQA": 40.17, + "Winogrande": 75.69, + "GSM8K": 29.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "94acda37b62a5f19af558f921c06a296081b3e30", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/model_007_13b_v2", + "Average \u2b06\ufe0f": 55.41, + "ARC": 61.95, + "HellaSwag": 82.48, + "MMLU": 57.32, + "TruthfulQA": 53.5, + "Winogrande": 75.85, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1c959d4b5d5b8683b051f07475bb5c1ab24c8bb0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Expert68\/llama2_13b_instructed_version2", + "Average \u2b06\ufe0f": 55.41, + "ARC": 60.07, + "HellaSwag": 84.05, + "MMLU": 55.61, + "TruthfulQA": 46.12, + "Winogrande": 75.61, + "GSM8K": 10.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ea321257d81e0f41c985f5155297b7fbd6ac375a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-13B", + "Average \u2b06\ufe0f": 55.41, + "ARC": 59.98, + "HellaSwag": 81.86, + "MMLU": 56.11, + "TruthfulQA": 47.41, + "Winogrande": 76.09, + "GSM8K": 10.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "fbb23bc41438b016f1df1e9180c6c350a03557ea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Enno-Ai\/ennodata-raw-pankajmathur-13b-peft", + "Average \u2b06\ufe0f": 55.4, + "ARC": 61.95, + "HellaSwag": 82.21, + "MMLU": 57.44, + "TruthfulQA": 53.57, + "Winogrande": 75.93, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "206553873db96a6730d36477837335dbbcc906fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/nash-vicuna-13b-v1dot5-ep2-w-rag-w-simple", + "Average \u2b06\ufe0f": 55.4, + "ARC": 59.13, + "HellaSwag": 80.64, + "MMLU": 56.12, + "TruthfulQA": 51.29, + "Winogrande": 74.66, + "GSM8K": 10.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "848ef91ab46a72260542283918a971347c6bfa93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-orca-platypus-coig-lite-2k-0.6e-13b", + "Average \u2b06\ufe0f": 55.4, + "ARC": 59.9, + "HellaSwag": 80.76, + "MMLU": 58.34, + "TruthfulQA": 47.97, + "Winogrande": 77.9, + "GSM8K": 7.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "65214c9923d55795ecd6e7f9e0fcee5ba5f26929", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pleisto\/yuren-13b-chatml", + "Average \u2b06\ufe0f": 55.39, + "ARC": 53.07, + "HellaSwag": 78.03, + "MMLU": 56.34, + "TruthfulQA": 42.32, + "Winogrande": 74.43, + "GSM8K": 28.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d9479c8c554ef335b5fd5b9a2e328de03c35d50e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mosaicml\/mpt-30b-chat", + "Average \u2b06\ufe0f": 55.38, + "ARC": 58.7, + "HellaSwag": 82.54, + "MMLU": 51.16, + "TruthfulQA": 52.42, + "Winogrande": 75.3, + "GSM8K": 12.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 192.0, + "Available on the hub": false, + "Model sha": "54f33278a04aa4e612bca482b82f801ab658e890", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "llm-agents\/tora-13b-v1.0", + "Average \u2b06\ufe0f": 55.37, + "ARC": 58.96, + "HellaSwag": 82.31, + "MMLU": 54.59, + "TruthfulQA": 40.22, + "Winogrande": 75.37, + "GSM8K": 20.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "0636c1f582c979a5a292cc5f3dc293800b1494e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/minotaur-llama2-13b-qlora", + "Average \u2b06\ufe0f": 55.37, + "ARC": 60.07, + "HellaSwag": 82.42, + "MMLU": 55.87, + "TruthfulQA": 45.57, + "Winogrande": 76.24, + "GSM8K": 12.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "22c83f7d68e547fb0b59acfa01c60b108c59fe55", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SicariusSicariiStuff\/Tinybra_13B", + "Average \u2b06\ufe0f": 55.36, + "ARC": 55.72, + "HellaSwag": 80.99, + "MMLU": 54.37, + "TruthfulQA": 49.14, + "Winogrande": 73.8, + "GSM8K": 18.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fa81ddf8b87ec339b2519044c4271bc59c4b65aa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gaodrew\/gaodrew-gorgonzola-13b", + "Average \u2b06\ufe0f": 55.35, + "ARC": 53.84, + "HellaSwag": 78.86, + "MMLU": 71.54, + "TruthfulQA": 42.58, + "Winogrande": 75.3, + "GSM8K": 10.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "a53fbe358d4cb546916847d861ccfaf7c724a103", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Luban-Platypus2-13B-QLora-0.80-epoch", + "Average \u2b06\ufe0f": 55.34, + "ARC": 60.24, + "HellaSwag": 82.22, + "MMLU": 58.03, + "TruthfulQA": 55.26, + "Winogrande": 75.37, + "GSM8K": 0.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "15a99bc147cf9b744cbab7a7c8c5f232cd0c8d10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/SthenoWriter-L2-13B", + "Average \u2b06\ufe0f": 55.33, + "ARC": 62.29, + "HellaSwag": 83.28, + "MMLU": 56.14, + "TruthfulQA": 44.72, + "Winogrande": 74.35, + "GSM8K": 11.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a6d9e26ab765eb170cc0aa428ee5e25b08524657", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "minlik\/chinese-alpaca-33b-merged", + "Average \u2b06\ufe0f": 55.33, + "ARC": 59.3, + "HellaSwag": 78.43, + "MMLU": 57.69, + "TruthfulQA": 52.45, + "Winogrande": 76.09, + "GSM8K": 8.04, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": false, + "Model sha": "fc2535104c0b48afc42575f9fe10bbcbb7612ec3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PulsarAI\/2x-LoRA-Assemble-Platypus2-13B", + "Average \u2b06\ufe0f": 55.33, + "ARC": 60.58, + "HellaSwag": 82.56, + "MMLU": 58.25, + "TruthfulQA": 54.77, + "Winogrande": 74.9, + "GSM8K": 0.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f147bf8428c174d1dc0332da626d4b039690ceab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "codellama\/CodeLlama-34b-hf", + "Average \u2b06\ufe0f": 55.33, + "ARC": 54.1, + "HellaSwag": 75.82, + "MMLU": 55.02, + "TruthfulQA": 39.11, + "Winogrande": 73.56, + "GSM8K": 34.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 157.0, + "Available on the hub": true, + "Model sha": "d3e967887d285343b8e239e26c6778c26931a536", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ArianAskari\/SOLID-SFT-DPO-MixQV3-SOLIDRejected-SFTChosen-Zephyr-7b-beta", + "Average \u2b06\ufe0f": 55.31, + "ARC": 59.3, + "HellaSwag": 81.34, + "MMLU": 60.23, + "TruthfulQA": 49.76, + "Winogrande": 75.53, + "GSM8K": 5.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6f3914fb205bfa5c37f14dd82f690319c210c876", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/llama-2-13b-Guanaco-QLoRA", + "Average \u2b06\ufe0f": 55.31, + "ARC": 61.09, + "HellaSwag": 82.99, + "MMLU": 55.47, + "TruthfulQA": 44.12, + "Winogrande": 77.19, + "GSM8K": 10.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "67e68284234538d3851d5c0c334383daffec57a2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r128_a256", + "Average \u2b06\ufe0f": 55.31, + "ARC": 59.73, + "HellaSwag": 82.08, + "MMLU": 54.81, + "TruthfulQA": 37.82, + "Winogrande": 76.32, + "GSM8K": 21.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3cc31d64036d6abf160c13adf4645a8980280c7f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/mistral-se-inst-ppo", + "Average \u2b06\ufe0f": 55.3, + "ARC": 56.31, + "HellaSwag": 79.49, + "MMLU": 60.91, + "TruthfulQA": 51.34, + "Winogrande": 78.14, + "GSM8K": 5.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f9d25d717f3972f80336fd15450329e2d8ee3ed4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xwin-LM\/Xwin-LM-13B-V0.1", + "Average \u2b06\ufe0f": 55.29, + "ARC": 62.54, + "HellaSwag": 82.8, + "MMLU": 56.53, + "TruthfulQA": 45.96, + "Winogrande": 74.27, + "GSM8K": 9.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 58.0, + "Available on the hub": true, + "Model sha": "32938856dc3d713dcba706aded7c82791b6ff647", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "codellama\/CodeLlama-34b-hf", + "Average \u2b06\ufe0f": 55.28, + "ARC": 54.18, + "HellaSwag": 75.82, + "MMLU": 54.92, + "TruthfulQA": 39.11, + "Winogrande": 73.32, + "GSM8K": 34.34, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 157.0, + "Available on the hub": true, + "Model sha": "c778b02fdecd4663d2b0a42bfb340fd29969533b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-OpenOrca_20w", + "Average \u2b06\ufe0f": 55.28, + "ARC": 59.9, + "HellaSwag": 82.51, + "MMLU": 56.3, + "TruthfulQA": 43.14, + "Winogrande": 77.19, + "GSM8K": 12.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f01882672e89b164f76093cf3bd26cfc6ecf72ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-llama2-13b-v11.1-bf16", + "Average \u2b06\ufe0f": 55.28, + "ARC": 51.79, + "HellaSwag": 76.23, + "MMLU": 56.13, + "TruthfulQA": 49.7, + "Winogrande": 73.48, + "GSM8K": 24.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": false, + "Model sha": "76fb7d00836eb2f1d9c9605d8881d73b782cf324", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elinas\/chronos-13b-v2", + "Average \u2b06\ufe0f": 55.25, + "ARC": 58.7, + "HellaSwag": 82.52, + "MMLU": 53.39, + "TruthfulQA": 50.55, + "Winogrande": 75.06, + "GSM8K": 11.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "e5d411138e72370c5613dfea0f66ded99f6e62f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/SOLAR-Platypus-10.7B-v2", + "Average \u2b06\ufe0f": 55.25, + "ARC": 59.39, + "HellaSwag": 83.57, + "MMLU": 59.93, + "TruthfulQA": 43.15, + "Winogrande": 81.45, + "GSM8K": 4.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "39a8673aa6d98a994661200e87cbd4069b8b6aa8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/CreativityEngine", + "Average \u2b06\ufe0f": 55.25, + "ARC": 59.3, + "HellaSwag": 82.42, + "MMLU": 53.55, + "TruthfulQA": 52.46, + "Winogrande": 74.19, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7870cc50b82b5cbebfa9935b6d73a9d20170299a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "beaugogh\/Llama2-13b-sharegpt4", + "Average \u2b06\ufe0f": 55.25, + "ARC": 61.77, + "HellaSwag": 84.53, + "MMLU": 55.21, + "TruthfulQA": 45.94, + "Winogrande": 75.22, + "GSM8K": 8.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "294c40349bf0c5377f71d92e7539bf5de3176a74", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "teknium\/OpenHermes-13B", + "Average \u2b06\ufe0f": 55.24, + "ARC": 59.81, + "HellaSwag": 82.24, + "MMLU": 56.35, + "TruthfulQA": 46.01, + "Winogrande": 75.45, + "GSM8K": 11.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 46.0, + "Available on the hub": true, + "Model sha": "f09d0fe655ad57cce9179b7b40ea6f81e07db18c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/vicuna-13b-v1.5-PL-lora_unload", + "Average \u2b06\ufe0f": 55.24, + "ARC": 56.91, + "HellaSwag": 81.22, + "MMLU": 56.06, + "TruthfulQA": 49.76, + "Winogrande": 75.22, + "GSM8K": 12.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "5c8aeb722e11d1c7258abd45f9f2840f57976c28", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shareAI\/llama2-13b-Chinese-chat", + "Average \u2b06\ufe0f": 55.22, + "ARC": 60.58, + "HellaSwag": 82.19, + "MMLU": 55.45, + "TruthfulQA": 45.11, + "Winogrande": 76.64, + "GSM8K": 11.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "31103acf93479d5c3865fb9b51dcb38e10d8b801", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/OrcaMini-Platypus2-13B-QLoRA-0.80-epoch", + "Average \u2b06\ufe0f": 55.22, + "ARC": 60.84, + "HellaSwag": 82.56, + "MMLU": 56.42, + "TruthfulQA": 53.32, + "Winogrande": 75.93, + "GSM8K": 2.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1f81c0439f60d848e3cbc7f06fcd58b5161a8557", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/Chronorctypus-Limarobormes-13b", + "Average \u2b06\ufe0f": 55.22, + "ARC": 59.9, + "HellaSwag": 82.75, + "MMLU": 58.45, + "TruthfulQA": 51.9, + "Winogrande": 74.43, + "GSM8K": 3.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": false, + "Model sha": "75c1bf5f4b40cf61873ff6487ccd3efc4f684330", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-13b-3.0", + "Average \u2b06\ufe0f": 55.21, + "ARC": 59.81, + "HellaSwag": 83.71, + "MMLU": 54.86, + "TruthfulQA": 47.79, + "Winogrande": 76.16, + "GSM8K": 8.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "2fcef275782b2c1061cf671d889aea652d13236c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Mythical-Destroyer-V2-L2-13B", + "Average \u2b06\ufe0f": 55.2, + "ARC": 59.3, + "HellaSwag": 82.66, + "MMLU": 57.39, + "TruthfulQA": 57.09, + "Winogrande": 74.74, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "cbc8b2e4a3beafc311b9e61f8fa9f7526a77c360", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/minotaur-13b-fixed", + "Average \u2b06\ufe0f": 55.19, + "ARC": 59.04, + "HellaSwag": 81.66, + "MMLU": 50.1, + "TruthfulQA": 50.36, + "Winogrande": 76.87, + "GSM8K": 13.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "5dac6f7559dba1c6fb59fee18c3e713cc3c83db7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decem\/Dionysus-Mistral-n1-v1", + "Average \u2b06\ufe0f": 55.18, + "ARC": 60.24, + "HellaSwag": 81.6, + "MMLU": 59.32, + "TruthfulQA": 47.94, + "Winogrande": 71.35, + "GSM8K": 10.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d60ffacb4671aa412dde58d6c58173296cb0d566", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "qblocks\/zephyr_7b_norobots", + "Average \u2b06\ufe0f": 55.16, + "ARC": 56.48, + "HellaSwag": 79.64, + "MMLU": 55.52, + "TruthfulQA": 44.6, + "Winogrande": 74.11, + "GSM8K": 20.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "312485e3c11a5cace45ad04dcf87a89df6e69571", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Qwen\/Qwen1.5-7B-Chat", + "Average \u2b06\ufe0f": 55.15, + "ARC": 55.89, + "HellaSwag": 78.56, + "MMLU": 61.65, + "TruthfulQA": 53.54, + "Winogrande": 67.72, + "GSM8K": 13.57, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 55.0, + "Available on the hub": true, + "Model sha": "0addb6bfd79e59bce8f61ed60cdafd906c04d447", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/Platypus2xOpenOrca-13B-LoRa", + "Average \u2b06\ufe0f": 55.15, + "ARC": 60.75, + "HellaSwag": 82.09, + "MMLU": 58.77, + "TruthfulQA": 45.15, + "Winogrande": 77.03, + "GSM8K": 7.13, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8b2f5d65c03d415b7c43530def622e133e1ef014", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/airoboros-c34b-2.2.1", + "Average \u2b06\ufe0f": 55.15, + "ARC": 54.69, + "HellaSwag": 76.84, + "MMLU": 55.43, + "TruthfulQA": 51.36, + "Winogrande": 72.53, + "GSM8K": 20.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "79d9761af231fecbfaf6066d6d405a0f8c04f4ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dfurman\/Llama-2-13B-Instruct-v0.2", + "Average \u2b06\ufe0f": 55.14, + "ARC": 60.58, + "HellaSwag": 81.96, + "MMLU": 55.46, + "TruthfulQA": 45.71, + "Winogrande": 77.82, + "GSM8K": 9.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "ac4b0962df8430f0b31c76a3d97a61134114c87e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/WizardLM-1.0-Uncensored-Llama2-13b", + "Average \u2b06\ufe0f": 55.14, + "ARC": 55.72, + "HellaSwag": 80.34, + "MMLU": 55.4, + "TruthfulQA": 51.44, + "Winogrande": 74.66, + "GSM8K": 13.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "134cea14627fd875f6f277cad92f988024855478", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bofenghuang\/vigogne-2-13b-instruct", + "Average \u2b06\ufe0f": 55.14, + "ARC": 61.18, + "HellaSwag": 83.25, + "MMLU": 55.92, + "TruthfulQA": 51.08, + "Winogrande": 77.35, + "GSM8K": 2.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": false, + "Model sha": "ac1f326ea75a28197c4b8e7c015071e8eef64485", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/athene-noctua-13b", + "Average \u2b06\ufe0f": 55.13, + "ARC": 57.17, + "HellaSwag": 81.52, + "MMLU": 55.91, + "TruthfulQA": 47.49, + "Winogrande": 73.4, + "GSM8K": 15.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7b5e2639d2d9f0b94c7e6834e6082f7c10fc8e12", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen1.5-7B-Chat", + "Average \u2b06\ufe0f": 55.13, + "ARC": 55.89, + "HellaSwag": 78.56, + "MMLU": 61.7, + "TruthfulQA": 53.65, + "Winogrande": 67.8, + "GSM8K": 13.19, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.72, + "Hub \u2764\ufe0f": 55.0, + "Available on the hub": true, + "Model sha": "0addb6bfd79e59bce8f61ed60cdafd906c04d447", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CalderaAI\/13B-Legerdemain-L2", + "Average \u2b06\ufe0f": 55.13, + "ARC": 61.26, + "HellaSwag": 83.26, + "MMLU": 56.0, + "TruthfulQA": 41.99, + "Winogrande": 75.22, + "GSM8K": 13.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "d6624ce1bcc6b50c86b86e879a8c9822218b84d2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PygmalionAI\/pygmalion-2-13b", + "Average \u2b06\ufe0f": 55.12, + "ARC": 60.32, + "HellaSwag": 82.37, + "MMLU": 56.02, + "TruthfulQA": 42.22, + "Winogrande": 78.06, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 64.0, + "Available on the hub": true, + "Model sha": "3cdc103995ccd5fc7fd2cb5f51f71b510466f5fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "totally-not-an-llm\/PuddleJumper-13b", + "Average \u2b06\ufe0f": 55.11, + "ARC": 58.7, + "HellaSwag": 81.18, + "MMLU": 58.25, + "TruthfulQA": 56.44, + "Winogrande": 72.77, + "GSM8K": 3.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "f3a8a475ff0c6ae37ac8ae0690980be11cac731a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/WizardLM-1.0-Uncensored-Llama2-13b", + "Average \u2b06\ufe0f": 55.1, + "ARC": 55.8, + "HellaSwag": 80.41, + "MMLU": 55.59, + "TruthfulQA": 51.42, + "Winogrande": 74.11, + "GSM8K": 13.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "134cea14627fd875f6f277cad92f988024855478", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lamhieu\/ghost-7b-v0.9.1", + "Average \u2b06\ufe0f": 55.1, + "ARC": 55.38, + "HellaSwag": 77.03, + "MMLU": 54.78, + "TruthfulQA": 43.96, + "Winogrande": 72.53, + "GSM8K": 26.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "afc39cbb0a3451d31442ff3d4a7a2752e3b0b67b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/Llama-2-13b-FINETUNE4", + "Average \u2b06\ufe0f": 55.09, + "ARC": 58.7, + "HellaSwag": 81.93, + "MMLU": 57.21, + "TruthfulQA": 43.26, + "Winogrande": 76.95, + "GSM8K": 12.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "939d06081210fa943c60210a47583f43b60901ad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenAssistant\/llama2-13b-orca-8k-3319", + "Average \u2b06\ufe0f": 55.09, + "ARC": 60.75, + "HellaSwag": 81.91, + "MMLU": 57.06, + "TruthfulQA": 42.64, + "Winogrande": 77.19, + "GSM8K": 10.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 129.0, + "Available on the hub": true, + "Model sha": "160f58ec85ef25ad935eb583f14c7e8c7f7e7839", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "speechlessai\/speechless-llama2-dolphin-orca-platypus-13b", + "Average \u2b06\ufe0f": 55.09, + "ARC": 59.64, + "HellaSwag": 82.65, + "MMLU": 57.9, + "TruthfulQA": 43.44, + "Winogrande": 77.19, + "GSM8K": 9.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "fd23b7d052eb7c18ecd2acc1be77c66b7b8d6dad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FlagAlpha\/Llama2-Chinese-13b-Chat", + "Average \u2b06\ufe0f": 55.07, + "ARC": 55.97, + "HellaSwag": 82.05, + "MMLU": 54.74, + "TruthfulQA": 48.9, + "Winogrande": 76.16, + "GSM8K": 12.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 258.0, + "Available on the hub": true, + "Model sha": "cb69cda10a72bc9736b1c10181ac41f28b69ff9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jphme\/Llama-2-13b-chat-german", + "Average \u2b06\ufe0f": 55.07, + "ARC": 57.85, + "HellaSwag": 81.66, + "MMLU": 54.45, + "TruthfulQA": 46.32, + "Winogrande": 76.48, + "GSM8K": 13.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 58.0, + "Available on the hub": false, + "Model sha": "d72667bd92fd6f76835466d302563d213e0b1ee1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "royallab\/PsyOrca2-13b-DARE", + "Average \u2b06\ufe0f": 55.07, + "ARC": 60.58, + "HellaSwag": 83.83, + "MMLU": 55.69, + "TruthfulQA": 53.27, + "Winogrande": 74.9, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4d3b1d7a4a5e243d3b8882abaa4b4a13d0ecbce4", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-dolphin_20w", + "Average \u2b06\ufe0f": 55.06, + "ARC": 59.56, + "HellaSwag": 82.55, + "MMLU": 55.89, + "TruthfulQA": 42.67, + "Winogrande": 77.27, + "GSM8K": 12.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c75073d7545a4d222f40dc519021c55a81850d75", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Python-Code-33B", + "Average \u2b06\ufe0f": 55.06, + "ARC": 56.31, + "HellaSwag": 81.01, + "MMLU": 54.22, + "TruthfulQA": 44.39, + "Winogrande": 75.22, + "GSM8K": 19.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "cf9a561b57145748455fd3e193d2b0e4ae0a0fce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MayaPH\/GodziLLa-30B", + "Average \u2b06\ufe0f": 55.05, + "ARC": 61.52, + "HellaSwag": 82.13, + "MMLU": 54.21, + "TruthfulQA": 55.91, + "Winogrande": 76.16, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "aa9912a2ac60abeac28b4566731cd903dcc582ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WizardLM\/WizardLM-13B-V1.1", + "Average \u2b06\ufe0f": 55.05, + "ARC": 60.24, + "HellaSwag": 81.39, + "MMLU": 50.92, + "TruthfulQA": 54.56, + "Winogrande": 75.06, + "GSM8K": 8.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 72.0, + "Available on the hub": false, + "Model sha": "badd80f8a6f46fb15310fedf6d4db54959854897", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/llama-2-16b-nastychat", + "Average \u2b06\ufe0f": 55.04, + "ARC": 57.42, + "HellaSwag": 80.59, + "MMLU": 55.99, + "TruthfulQA": 53.45, + "Winogrande": 74.66, + "GSM8K": 8.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 16.19, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "6fb7f82d486b3eee53d750f83cc7eae434349809", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r32_a256", + "Average \u2b06\ufe0f": 55.04, + "ARC": 60.15, + "HellaSwag": 81.98, + "MMLU": 54.99, + "TruthfulQA": 36.75, + "Winogrande": 76.48, + "GSM8K": 19.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f3192de7e37e861a697c0741dd4e641724b6fdbc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "royallab\/PsyOrca2-13b-DARE", + "Average \u2b06\ufe0f": 55.03, + "ARC": 60.32, + "HellaSwag": 83.85, + "MMLU": 55.62, + "TruthfulQA": 53.33, + "Winogrande": 74.59, + "GSM8K": 2.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4d3b1d7a4a5e243d3b8882abaa4b4a13d0ecbce4", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "augmxnt\/shisa-7b-v1", + "Average \u2b06\ufe0f": 55.01, + "ARC": 56.14, + "HellaSwag": 78.63, + "MMLU": 23.12, + "TruthfulQA": 52.49, + "Winogrande": 78.06, + "GSM8K": 41.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.96, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "131c2f3bf4955d1e2b6762380132bdd8688c0646", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "duliadotio\/dulia-13b-8k-alpha", + "Average \u2b06\ufe0f": 55.0, + "ARC": 60.67, + "HellaSwag": 82.0, + "MMLU": 56.87, + "TruthfulQA": 42.59, + "Winogrande": 77.19, + "GSM8K": 10.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c3bcafd7f6133a7e7c069f8765a99fe84989d926", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Aspik101\/Redmond-Puffin-13B-instruct-PL-lora_unload", + "Average \u2b06\ufe0f": 55.0, + "ARC": 60.92, + "HellaSwag": 82.43, + "MMLU": 55.61, + "TruthfulQA": 44.26, + "Winogrande": 75.69, + "GSM8K": 11.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b933009635299bca32c694336aa2007d756a2dda", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_v3.2_super", + "Average \u2b06\ufe0f": 54.99, + "ARC": 59.81, + "HellaSwag": 82.5, + "MMLU": 55.9, + "TruthfulQA": 42.3, + "Winogrande": 75.93, + "GSM8K": 13.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": true, + "Model sha": "aab7ce4d48b31a295a0116b61569d8e87a09bb7a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ziqingyang\/chinese-alpaca-2-13b", + "Average \u2b06\ufe0f": 54.99, + "ARC": 58.7, + "HellaSwag": 79.74, + "MMLU": 55.1, + "TruthfulQA": 50.22, + "Winogrande": 75.69, + "GSM8K": 10.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.97, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "576094cbf4988baf88b3bb66678be1db70bd720a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "prithivida\/Asimov-7B-v1", + "Average \u2b06\ufe0f": 54.98, + "ARC": 59.04, + "HellaSwag": 80.04, + "MMLU": 56.35, + "TruthfulQA": 51.15, + "Winogrande": 73.95, + "GSM8K": 9.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0b33ad0a6dde60156ee6008ff47f7cfa6cd27937", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e6", + "Average \u2b06\ufe0f": 54.98, + "ARC": 58.87, + "HellaSwag": 81.9, + "MMLU": 55.03, + "TruthfulQA": 36.03, + "Winogrande": 76.72, + "GSM8K": 21.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "701562febb55ca9660f3c4d7be2249f3dbd5f0b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-13b-v1.5-16k", + "Average \u2b06\ufe0f": 54.97, + "ARC": 56.74, + "HellaSwag": 80.37, + "MMLU": 55.28, + "TruthfulQA": 51.96, + "Winogrande": 72.38, + "GSM8K": 13.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 211.0, + "Available on the hub": true, + "Model sha": "277697af19d4b267626ebc9f4e078d19a9a0fddf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LLMs\/WizardLM-13B-V1.0", + "Average \u2b06\ufe0f": 54.97, + "ARC": 57.25, + "HellaSwag": 80.88, + "MMLU": 52.92, + "TruthfulQA": 50.55, + "Winogrande": 74.11, + "GSM8K": 14.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "f802ea7c01e2da27b0f7091c70d3ecfd8fc042b9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/Medusa-7B-bf16", + "Average \u2b06\ufe0f": 54.96, + "ARC": 60.58, + "HellaSwag": 79.98, + "MMLU": 57.71, + "TruthfulQA": 55.74, + "Winogrande": 73.95, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dfe9982247761c6a54b76803483fe0d412e182f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/Hippolyta-7B-bf16", + "Average \u2b06\ufe0f": 54.96, + "ARC": 60.58, + "HellaSwag": 79.98, + "MMLU": 57.71, + "TruthfulQA": 55.74, + "Winogrande": 73.95, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "dfe9982247761c6a54b76803483fe0d412e182f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mistralai\/Mistral-7B-Instruct-v0.1", + "Average \u2b06\ufe0f": 54.96, + "ARC": 54.52, + "HellaSwag": 75.63, + "MMLU": 55.38, + "TruthfulQA": 56.28, + "Winogrande": 73.72, + "GSM8K": 14.25, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1329.0, + "Available on the hub": true, + "Model sha": "7961f5aa9b736bf8e364b2e6f201190f97a27931", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WebraftAI\/synapsellm-7b-mistral-v0.4-preview3", + "Average \u2b06\ufe0f": 54.94, + "ARC": 51.28, + "HellaSwag": 74.83, + "MMLU": 52.93, + "TruthfulQA": 52.35, + "Winogrande": 73.48, + "GSM8K": 24.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "67c0d0fe71c620f0be410a06f58b928f89218639", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "FPHam\/Sydney_Overthinker_13b_HF", + "Average \u2b06\ufe0f": 54.94, + "ARC": 58.96, + "HellaSwag": 80.85, + "MMLU": 51.28, + "TruthfulQA": 45.7, + "Winogrande": 73.95, + "GSM8K": 18.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "c4d2617fb452a55ac3a39c64128a98874595adb1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/wizardLM-13B-1.0-fp16", + "Average \u2b06\ufe0f": 54.93, + "ARC": 57.25, + "HellaSwag": 80.88, + "MMLU": 52.9, + "TruthfulQA": 50.55, + "Winogrande": 74.11, + "GSM8K": 13.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b79733805e98e668ff9a459975c259881b1b8014", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "adamo1139\/Yi-6B-200K-AEZAKMI-v2", + "Average \u2b06\ufe0f": 54.93, + "ARC": 52.99, + "HellaSwag": 71.2, + "MMLU": 63.0, + "TruthfulQA": 46.79, + "Winogrande": 70.48, + "GSM8K": 25.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0c4dd0e7119bbef9fa5b28b5a581b60822cebaf5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "adamo1139\/Mistral-7B-AEZAKMI-v1", + "Average \u2b06\ufe0f": 54.92, + "ARC": 58.87, + "HellaSwag": 82.01, + "MMLU": 58.72, + "TruthfulQA": 53.54, + "Winogrande": 75.69, + "GSM8K": 0.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fec4e695e5af743bb49d1976de83fa695be5f105", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "digitous\/13B-Chimera", + "Average \u2b06\ufe0f": 54.92, + "ARC": 57.59, + "HellaSwag": 81.5, + "MMLU": 49.86, + "TruthfulQA": 52.59, + "Winogrande": 77.27, + "GSM8K": 10.69, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "85cfe8e6db2bee804873cfdb48955696cc5b0689", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "meta-llama\/Llama-2-13b-chat-hf", + "Average \u2b06\ufe0f": 54.91, + "ARC": 59.04, + "HellaSwag": 81.94, + "MMLU": 54.64, + "TruthfulQA": 44.12, + "Winogrande": 74.51, + "GSM8K": 15.24, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 869.0, + "Available on the hub": false, + "Model sha": "f848cf15ab9a51ae5735ab28120a9a0773eeb541", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "deepse\/CodeUp-Llama-2-13b-chat-hf", + "Average \u2b06\ufe0f": 54.91, + "ARC": 59.04, + "HellaSwag": 81.93, + "MMLU": 54.63, + "TruthfulQA": 44.12, + "Winogrande": 74.51, + "GSM8K": 15.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail++", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": true, + "Model sha": "d4af0b233a5b6a214e96582e103396e99dcf5f95", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NewstaR\/Morningstar-13b-hf", + "Average \u2b06\ufe0f": 54.91, + "ARC": 59.04, + "HellaSwag": 81.93, + "MMLU": 54.63, + "TruthfulQA": 44.12, + "Winogrande": 74.51, + "GSM8K": 15.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2605b5b3b0ecba906ac26d39aab40f33c2ec81c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Kimiko-v2-13B-fp16", + "Average \u2b06\ufe0f": 54.91, + "ARC": 61.01, + "HellaSwag": 83.32, + "MMLU": 55.17, + "TruthfulQA": 40.65, + "Winogrande": 76.8, + "GSM8K": 12.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "0fed305667508e50330e71a2d43e9cee5ea73783", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "The-Face-Of-Goonery\/Huginn-13b-FP16", + "Average \u2b06\ufe0f": 54.89, + "ARC": 60.58, + "HellaSwag": 82.53, + "MMLU": 53.71, + "TruthfulQA": 54.46, + "Winogrande": 73.72, + "GSM8K": 4.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": false, + "Model sha": "69615d9a8e1547f2407afd3380868a99f780e008", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "garage-bAInd\/Platypus2-13B", + "Average \u2b06\ufe0f": 54.89, + "ARC": 61.26, + "HellaSwag": 82.56, + "MMLU": 56.7, + "TruthfulQA": 44.86, + "Winogrande": 76.87, + "GSM8K": 7.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "b5e926e3d6c03e83c7983e87eb71098b5e80a62e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_addto15k_4.5w-r16-gate_up_down", + "Average \u2b06\ufe0f": 54.88, + "ARC": 58.53, + "HellaSwag": 82.27, + "MMLU": 55.9, + "TruthfulQA": 40.26, + "Winogrande": 76.95, + "GSM8K": 15.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fdc145fe1b47cdda483535c018e35a5ab249a552", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/LewdEngine", + "Average \u2b06\ufe0f": 54.88, + "ARC": 60.49, + "HellaSwag": 83.08, + "MMLU": 54.84, + "TruthfulQA": 43.63, + "Winogrande": 74.9, + "GSM8K": 12.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6e918ff9f563552af4ad66f4308f6d040e24af4b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mikael110\/llama-2-13b-guanaco-fp16", + "Average \u2b06\ufe0f": 54.86, + "ARC": 60.92, + "HellaSwag": 83.18, + "MMLU": 54.58, + "TruthfulQA": 44.0, + "Winogrande": 74.9, + "GSM8K": 11.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "feb7ef47ceca6aec9548264a39622b63fdcb853c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/manticore-13b", + "Average \u2b06\ufe0f": 54.86, + "ARC": 58.7, + "HellaSwag": 81.63, + "MMLU": 50.84, + "TruthfulQA": 49.17, + "Winogrande": 76.64, + "GSM8K": 12.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 113.0, + "Available on the hub": false, + "Model sha": "aed786b0200251c9962ac200c50f7e367f264b46", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Redmond-Puffin-13B", + "Average \u2b06\ufe0f": 54.86, + "ARC": 60.41, + "HellaSwag": 83.2, + "MMLU": 55.36, + "TruthfulQA": 42.12, + "Winogrande": 76.64, + "GSM8K": 11.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": [ + "mit" + ], + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 109.0, + "Available on the hub": true, + "Model sha": "12af25fa7ea02c4fc636952ea8b9dc9cf48e35be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/OpenOrcaPlatypus2-Platypus2-13B-QLora-0.80-epoch", + "Average \u2b06\ufe0f": 54.86, + "ARC": 59.81, + "HellaSwag": 82.69, + "MMLU": 56.96, + "TruthfulQA": 52.92, + "Winogrande": 74.43, + "GSM8K": 2.35, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5427ceec420f943a0b011a4d96f3efc292306933", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CausalLM\/7B", + "Average \u2b06\ufe0f": 54.86, + "ARC": 50.0, + "HellaSwag": 74.58, + "MMLU": 61.79, + "TruthfulQA": 50.13, + "Winogrande": 69.69, + "GSM8K": 22.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "wtfpl", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 119.0, + "Available on the hub": true, + "Model sha": "3f4f76e2d94308ea6b0edc3de83f18c213a8fde5", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r8_a256", + "Average \u2b06\ufe0f": 54.85, + "ARC": 59.81, + "HellaSwag": 81.79, + "MMLU": 53.22, + "TruthfulQA": 38.04, + "Winogrande": 76.09, + "GSM8K": 20.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c7fedbbc9bad7326196826cd290f9928e6e7342e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Code-13B", + "Average \u2b06\ufe0f": 54.81, + "ARC": 57.34, + "HellaSwag": 83.28, + "MMLU": 53.17, + "TruthfulQA": 42.46, + "Winogrande": 73.56, + "GSM8K": 19.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "91f5a6d5cdf93aeb86dd8965e195d51522957fc6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/Samantha-1.11-CodeLlama-34b", + "Average \u2b06\ufe0f": 54.8, + "ARC": 56.57, + "HellaSwag": 75.47, + "MMLU": 53.51, + "TruthfulQA": 50.46, + "Winogrande": 73.48, + "GSM8K": 19.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 33.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3fd110de9282e52f56f999bf1da1a76425f00e29", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/llama-13b-FINETUNE3", + "Average \u2b06\ufe0f": 54.79, + "ARC": 59.3, + "HellaSwag": 81.53, + "MMLU": 57.46, + "TruthfulQA": 41.63, + "Winogrande": 76.72, + "GSM8K": 12.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bacd035db122dafaf86bf52bb9ca8c613070cc58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Ensemble5-Platypus2-13B-QLora-0.80-epoch", + "Average \u2b06\ufe0f": 54.76, + "ARC": 59.73, + "HellaSwag": 82.66, + "MMLU": 56.94, + "TruthfulQA": 52.92, + "Winogrande": 74.43, + "GSM8K": 1.9, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2af03c3287c60c4ba2fb6afa86c26cf722ab001d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WizardLM\/WizardLM-13B-V1.2", + "Average \u2b06\ufe0f": 54.76, + "ARC": 59.04, + "HellaSwag": 82.21, + "MMLU": 54.64, + "TruthfulQA": 47.27, + "Winogrande": 71.9, + "GSM8K": 13.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 212.0, + "Available on the hub": true, + "Model sha": "6760d0c07ffdc2405295ed7a29437cf4dc414bac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Redmond-Puffin-13B", + "Average \u2b06\ufe0f": 54.74, + "ARC": 60.49, + "HellaSwag": 83.21, + "MMLU": 54.95, + "TruthfulQA": 42.08, + "Winogrande": 76.48, + "GSM8K": 11.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": [ + "mit" + ], + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 109.0, + "Available on the hub": true, + "Model sha": "12af25fa7ea02c4fc636952ea8b9dc9cf48e35be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "The-Face-Of-Goonery\/Chronos-Beluga-v2-13bfp16", + "Average \u2b06\ufe0f": 54.74, + "ARC": 60.75, + "HellaSwag": 81.94, + "MMLU": 54.08, + "TruthfulQA": 53.23, + "Winogrande": 73.8, + "GSM8K": 4.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "6d50e6681bc26c9bc0c8377c26c438e295ee0c2f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/TekniumAiroboros-Nebula-7B", + "Average \u2b06\ufe0f": 54.74, + "ARC": 57.17, + "HellaSwag": 81.72, + "MMLU": 55.25, + "TruthfulQA": 51.64, + "Winogrande": 73.24, + "GSM8K": 9.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ef964d514cc25a600b0de78fc469d1acbec34591", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/MythoMix-Platypus2-13B-QLoRA-0.80-epoch", + "Average \u2b06\ufe0f": 54.74, + "ARC": 60.32, + "HellaSwag": 83.72, + "MMLU": 55.74, + "TruthfulQA": 52.18, + "Winogrande": 75.53, + "GSM8K": 0.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3d91f63d82abd598d5b80d24d74feb6b00b7d80f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "CalderaAI\/13B-Thorns-l2", + "Average \u2b06\ufe0f": 54.72, + "ARC": 62.88, + "HellaSwag": 83.57, + "MMLU": 56.95, + "TruthfulQA": 49.52, + "Winogrande": 74.51, + "GSM8K": 0.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": false, + "Model sha": "adc5e7befcc3d0a26f46198fdda4a098a2742fe6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Medusa-13b", + "Average \u2b06\ufe0f": 54.72, + "ARC": 58.19, + "HellaSwag": 81.35, + "MMLU": 57.39, + "TruthfulQA": 51.24, + "Winogrande": 73.32, + "GSM8K": 6.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "be755c9eef8233ca59e0178db75de878f5859222", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elyza\/ELYZA-japanese-Llama-2-13b-instruct", + "Average \u2b06\ufe0f": 54.72, + "ARC": 58.36, + "HellaSwag": 82.2, + "MMLU": 55.65, + "TruthfulQA": 42.4, + "Winogrande": 75.22, + "GSM8K": 14.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "ed15089024f3ecad9a8c4ce1db302cc01aa9f4ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abacusai\/Giraffe-beta-13b-32k", + "Average \u2b06\ufe0f": 54.69, + "ARC": 55.63, + "HellaSwag": 80.42, + "MMLU": 53.61, + "TruthfulQA": 42.58, + "Winogrande": 74.59, + "GSM8K": 21.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "259f3fe9ebbff7532498f44286f253d56699da6f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/LLaMA2-13B-Psyfighter2", + "Average \u2b06\ufe0f": 54.66, + "ARC": 60.07, + "HellaSwag": 84.02, + "MMLU": 55.07, + "TruthfulQA": 53.0, + "Winogrande": 74.35, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "cc51a4e64b0821feda101dc04737486b4ff60735", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-codellama-34b-v1.9", + "Average \u2b06\ufe0f": 54.64, + "ARC": 54.27, + "HellaSwag": 75.2, + "MMLU": 56.12, + "TruthfulQA": 43.92, + "Winogrande": 73.56, + "GSM8K": 24.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "68aad9f8452b2abf7d5415d48c09bd55d5b7ca05", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE5_4w-r8-q_k_v_o", + "Average \u2b06\ufe0f": 54.64, + "ARC": 57.25, + "HellaSwag": 81.73, + "MMLU": 55.72, + "TruthfulQA": 41.53, + "Winogrande": 77.58, + "GSM8K": 14.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "209da26cff560ab34064f277190ab63f8c970b93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Secbone\/llama-2-13B-instructed", + "Average \u2b06\ufe0f": 54.63, + "ARC": 59.39, + "HellaSwag": 83.88, + "MMLU": 55.57, + "TruthfulQA": 46.89, + "Winogrande": 74.03, + "GSM8K": 8.04, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e676fbd9015beacfba5d71426beace7605200477", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE5_4w-r16-q_k_v_o", + "Average \u2b06\ufe0f": 54.63, + "ARC": 58.7, + "HellaSwag": 81.66, + "MMLU": 53.87, + "TruthfulQA": 43.02, + "Winogrande": 76.72, + "GSM8K": 13.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "33fd8a46a711ab8c45698dae9601678dfd7b3d33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/UltraLM-13B-fp16", + "Average \u2b06\ufe0f": 54.62, + "ARC": 57.59, + "HellaSwag": 80.2, + "MMLU": 51.85, + "TruthfulQA": 51.56, + "Winogrande": 75.85, + "GSM8K": 10.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "734f5641f6c548474517d1536c46024517f120e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Chat-Stheno-L2-13B", + "Average \u2b06\ufe0f": 54.61, + "ARC": 58.45, + "HellaSwag": 80.96, + "MMLU": 54.8, + "TruthfulQA": 43.31, + "Winogrande": 75.37, + "GSM8K": 14.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "20419fdd5b4bdcbbf075223c33b396958c48a6cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/Llama-2-13b-hf-ds_eli5_1024_r_64_alpha_16", + "Average \u2b06\ufe0f": 54.61, + "ARC": 60.41, + "HellaSwag": 82.58, + "MMLU": 55.86, + "TruthfulQA": 43.61, + "Winogrande": 76.72, + "GSM8K": 8.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "891be2d8f205baa04c8a92f6ab1225f0d0c3e5bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Nous-Hermes-Platypus2-13B-QLoRA-0.80-epoch", + "Average \u2b06\ufe0f": 54.6, + "ARC": 59.9, + "HellaSwag": 83.29, + "MMLU": 56.69, + "TruthfulQA": 51.08, + "Winogrande": 75.22, + "GSM8K": 1.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6e49d3d205e7f2e15c01ace0901da8931bbaab3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/Samantha-Nebula-7B", + "Average \u2b06\ufe0f": 54.58, + "ARC": 57.0, + "HellaSwag": 82.25, + "MMLU": 54.21, + "TruthfulQA": 49.58, + "Winogrande": 73.09, + "GSM8K": 11.37, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a7d4b8a1683e33dd3c60064d7dd9d5c35691323f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BAAI\/Aquila2-34B", + "Average \u2b06\ufe0f": 54.57, + "ARC": 52.47, + "HellaSwag": 81.9, + "MMLU": 76.03, + "TruthfulQA": 40.85, + "Winogrande": 75.53, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "356733caf6221e9dd898cde8ff189a98175526ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ankhamun\/xxxI-Ixxx", + "Average \u2b06\ufe0f": 54.56, + "ARC": 54.18, + "HellaSwag": 72.55, + "MMLU": 52.02, + "TruthfulQA": 54.42, + "Winogrande": 70.24, + "GSM8K": 23.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4063a7f7f22b9f6f22cfaf518e85743bdce4dc11", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gaodrew\/OpenOrca-Platypus2-13B-thera-1250", + "Average \u2b06\ufe0f": 54.56, + "ARC": 59.22, + "HellaSwag": 81.02, + "MMLU": 57.04, + "TruthfulQA": 48.43, + "Winogrande": 73.09, + "GSM8K": 8.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b1c2ebcda387211732e87911e39edca503502a33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "microsoft\/Orca-2-7b", + "Average \u2b06\ufe0f": 54.55, + "ARC": 54.1, + "HellaSwag": 76.19, + "MMLU": 56.37, + "TruthfulQA": 52.45, + "Winogrande": 73.48, + "GSM8K": 14.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 191.0, + "Available on the hub": true, + "Model sha": "60e31e6bdcf582ad103b807cb74b73ee1d2c4b17", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "KoboldAI\/LLaMA2-13B-Holomax", + "Average \u2b06\ufe0f": 54.52, + "ARC": 60.49, + "HellaSwag": 82.86, + "MMLU": 54.67, + "TruthfulQA": 42.97, + "Winogrande": 74.66, + "GSM8K": 11.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "2c4fddeb097636d6462b7628a8e053ad3ff4678c", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-class-shishya-all-hal-13b-ep3", + "Average \u2b06\ufe0f": 54.51, + "ARC": 48.63, + "HellaSwag": 80.28, + "MMLU": 56.4, + "TruthfulQA": 42.75, + "Winogrande": 73.16, + "GSM8K": 25.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d773c696778d4f6fe63282d206ed042003346ed1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/LLaMA2-13B-Tiefighter", + "Average \u2b06\ufe0f": 54.51, + "ARC": 59.9, + "HellaSwag": 84.0, + "MMLU": 54.98, + "TruthfulQA": 53.02, + "Winogrande": 74.51, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 56.0, + "Available on the hub": true, + "Model sha": "0d193a4562d6836724485cb7df6e58ca846bbfeb", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chansung\/gpt4-alpaca-lora-13b-decapoda-1024", + "Average \u2b06\ufe0f": 54.51, + "ARC": 59.39, + "HellaSwag": 81.87, + "MMLU": 47.75, + "TruthfulQA": 52.59, + "Winogrande": 77.35, + "GSM8K": 8.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7aedafea409de07a997d70a84e30242c7b86877c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/Mistral-7B-length-100000", + "Average \u2b06\ufe0f": 54.5, + "ARC": 51.71, + "HellaSwag": 78.32, + "MMLU": 55.75, + "TruthfulQA": 44.95, + "Winogrande": 76.72, + "GSM8K": 19.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "69a99c77648c137a5f898e6dba0a22724c0da825", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE3_3.3w-r16-q_k_v_o_gate_up_down", + "Average \u2b06\ufe0f": 54.5, + "ARC": 59.22, + "HellaSwag": 81.52, + "MMLU": 54.94, + "TruthfulQA": 42.83, + "Winogrande": 76.87, + "GSM8K": 11.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a759c4fae8dc5fcd264bf58b89b9fd13d06784ae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "BAAI\/Aquila2-34B", + "Average \u2b06\ufe0f": 54.5, + "ARC": 52.65, + "HellaSwag": 81.99, + "MMLU": 76.02, + "TruthfulQA": 40.8, + "Winogrande": 75.06, + "GSM8K": 0.45, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "356733caf6221e9dd898cde8ff189a98175526ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/Platypus2-13B-LoRa", + "Average \u2b06\ufe0f": 54.48, + "ARC": 60.67, + "HellaSwag": 82.5, + "MMLU": 56.34, + "TruthfulQA": 43.91, + "Winogrande": 75.93, + "GSM8K": 7.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1450c541cf9e378e81862fabeb234b8e0a2bdf5a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "hywu\/Camelidae-8x7B", + "Average \u2b06\ufe0f": 54.47, + "ARC": 55.63, + "HellaSwag": 79.18, + "MMLU": 50.1, + "TruthfulQA": 42.86, + "Winogrande": 76.24, + "GSM8K": 22.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "c12485aa7b31943113d992076cc2d79dce2a73a4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Limarp-Platypus2-13B-QLoRA-0.80-epoch", + "Average \u2b06\ufe0f": 54.46, + "ARC": 60.49, + "HellaSwag": 82.76, + "MMLU": 56.52, + "TruthfulQA": 44.14, + "Winogrande": 76.8, + "GSM8K": 6.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0a8560232ff73ca3c3f8e217b4517fa6c4f55558", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/Llama-2-13b-FINETUNE4_TEST2", + "Average \u2b06\ufe0f": 54.46, + "ARC": 58.45, + "HellaSwag": 81.7, + "MMLU": 56.61, + "TruthfulQA": 40.19, + "Winogrande": 76.64, + "GSM8K": 13.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e312c4c59cab9d130c33288c92aad7c0cb5331d5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Radu1999\/Mister", + "Average \u2b06\ufe0f": 54.46, + "ARC": 61.69, + "HellaSwag": 71.74, + "MMLU": 43.53, + "TruthfulQA": 65.85, + "Winogrande": 75.22, + "GSM8K": 8.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "36cc93cd7bc754a5b23b2d47760ee7ed814d84f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CallComply\/zephyr-7b-beta-128k", + "Average \u2b06\ufe0f": 54.45, + "ARC": 58.28, + "HellaSwag": 81.0, + "MMLU": 53.57, + "TruthfulQA": 46.1, + "Winogrande": 74.74, + "GSM8K": 13.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fc4c02de7b878edf07999d35efa91b62b6bfa35c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bhenrym14\/airophin-13b-pntk-16k-fp16", + "Average \u2b06\ufe0f": 54.44, + "ARC": 61.18, + "HellaSwag": 82.86, + "MMLU": 55.19, + "TruthfulQA": 43.2, + "Winogrande": 76.16, + "GSM8K": 8.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "6b5418b69e8270df659eacb192f469e7c3af70b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/Medorca-2x7b", + "Average \u2b06\ufe0f": 54.43, + "ARC": 54.1, + "HellaSwag": 76.04, + "MMLU": 53.3, + "TruthfulQA": 48.04, + "Winogrande": 74.51, + "GSM8K": 20.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 11.07, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "597c5b2e36b7b5375f0c05c05acc2699ec2a26cd", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/MT7Bi-alpha-dpo-v0.2", + "Average \u2b06\ufe0f": 54.4, + "ARC": 54.69, + "HellaSwag": 75.89, + "MMLU": 52.82, + "TruthfulQA": 45.48, + "Winogrande": 71.59, + "GSM8K": 25.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "14f5dfce0fc441490450aa3c3935a495ebebd7d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NekoPunchBBB\/Llama-2-13b-hf_Open-Platypus-QLoRA-multigpu", + "Average \u2b06\ufe0f": 54.4, + "ARC": 57.51, + "HellaSwag": 82.49, + "MMLU": 54.83, + "TruthfulQA": 43.81, + "Winogrande": 77.27, + "GSM8K": 10.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f65029ea8f030731ace568e40bab33a7097a13de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE1_17w-r16", + "Average \u2b06\ufe0f": 54.37, + "ARC": 57.25, + "HellaSwag": 82.27, + "MMLU": 56.16, + "TruthfulQA": 39.75, + "Winogrande": 77.43, + "GSM8K": 13.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5da5c92f3cf85a62c1be90a0bb2ae8dffce64a7d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-huangyt_Fintune_1_17w-q_k_v_o_proj", + "Average \u2b06\ufe0f": 54.35, + "ARC": 59.73, + "HellaSwag": 81.06, + "MMLU": 54.53, + "TruthfulQA": 38.64, + "Winogrande": 78.14, + "GSM8K": 14.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aeeded8db9eea97e2e6a2e19a006ce1acd110a82", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xriminact\/TarsDolly", + "Average \u2b06\ufe0f": 54.35, + "ARC": 59.3, + "HellaSwag": 81.85, + "MMLU": 56.26, + "TruthfulQA": 42.29, + "Winogrande": 76.24, + "GSM8K": 10.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e8dab99d2af077e63200a07a60bafe3247d8eb09", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xwin-LM\/XwinCoder-34B", + "Average \u2b06\ufe0f": 54.35, + "ARC": 51.02, + "HellaSwag": 74.02, + "MMLU": 49.53, + "TruthfulQA": 43.82, + "Winogrande": 68.35, + "GSM8K": 39.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "c331e0f9203efcdfcc8916a24fcec52cd8897dcc", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/orca_mini_v3_7B-GPTQ", + "Average \u2b06\ufe0f": 54.35, + "ARC": 54.52, + "HellaSwag": 78.53, + "MMLU": 51.85, + "TruthfulQA": 51.2, + "Winogrande": 74.66, + "GSM8K": 15.31, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "other", + "#Params (B)": 9.05, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "4f06a6151128861d5bb256275620f7eadcab3238", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lajonbot\/Llama-2-13b-hf-instruct-pl-lora_unload", + "Average \u2b06\ufe0f": 54.34, + "ARC": 59.47, + "HellaSwag": 82.16, + "MMLU": 54.83, + "TruthfulQA": 41.45, + "Winogrande": 76.24, + "GSM8K": 11.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "4ef2c736641c2983996c4662bf481782a9de5055", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bofenghuang\/vigogne-13b-instruct", + "Average \u2b06\ufe0f": 54.34, + "ARC": 57.94, + "HellaSwag": 81.32, + "MMLU": 47.62, + "TruthfulQA": 50.23, + "Winogrande": 77.11, + "GSM8K": 11.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "a13e08a36c355d64fae59f28162e5fa542a8d235", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "anhnv125\/llama-op-v4", + "Average \u2b06\ufe0f": 54.34, + "ARC": 61.52, + "HellaSwag": 79.21, + "MMLU": 57.01, + "TruthfulQA": 42.72, + "Winogrande": 75.93, + "GSM8K": 9.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6cd644049de2b944beaefcc6aa34965c00e08529", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE3_3.3w-r16-gate_up_down", + "Average \u2b06\ufe0f": 54.32, + "ARC": 58.7, + "HellaSwag": 81.89, + "MMLU": 56.08, + "TruthfulQA": 38.95, + "Winogrande": 77.35, + "GSM8K": 12.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4c3a4cb54c0487666bd58589b50f90c22de80969", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "garage-bAInd\/Camel-Platypus2-13B", + "Average \u2b06\ufe0f": 54.32, + "ARC": 60.75, + "HellaSwag": 83.61, + "MMLU": 56.51, + "TruthfulQA": 49.6, + "Winogrande": 75.37, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "0480a52799cb8e8de73bb41994df8b6b793937c7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-Open-Platypus_2.5w", + "Average \u2b06\ufe0f": 54.32, + "ARC": 59.56, + "HellaSwag": 82.46, + "MMLU": 56.06, + "TruthfulQA": 42.45, + "Winogrande": 76.8, + "GSM8K": 8.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bc55678af8226e1323305f743a4882da31994e0c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "StudentLLM\/Alpagasus-2-13b-QLoRA-merged", + "Average \u2b06\ufe0f": 54.31, + "ARC": 61.09, + "HellaSwag": 82.46, + "MMLU": 55.27, + "TruthfulQA": 38.53, + "Winogrande": 77.35, + "GSM8K": 11.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "dacbafa40716a2d87e593240cc5c1dc883b5066a", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/WizardLM-13B-V1.1-GPTQ", + "Average \u2b06\ufe0f": 54.28, + "ARC": 58.53, + "HellaSwag": 80.66, + "MMLU": 49.59, + "TruthfulQA": 54.35, + "Winogrande": 74.43, + "GSM8K": 8.11, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "9df807ac64034bc6e7387326689d6e39656ce5e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/wizard-mega-13b", + "Average \u2b06\ufe0f": 54.27, + "ARC": 57.34, + "HellaSwag": 81.09, + "MMLU": 50.59, + "TruthfulQA": 50.22, + "Winogrande": 76.32, + "GSM8K": 10.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 105.0, + "Available on the hub": false, + "Model sha": "76e90314541be6cfa2b55208831c99f1351c1a33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-13b-v1.3", + "Average \u2b06\ufe0f": 54.27, + "ARC": 54.61, + "HellaSwag": 80.41, + "MMLU": 52.88, + "TruthfulQA": 52.14, + "Winogrande": 74.82, + "GSM8K": 10.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 185.0, + "Available on the hub": false, + "Model sha": "7900eeb715a49affee9e6390f824e62eea3f3fb1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mwitiderrick\/SwahiliInstruct-v0.2", + "Average \u2b06\ufe0f": 54.25, + "ARC": 55.2, + "HellaSwag": 78.22, + "MMLU": 50.3, + "TruthfulQA": 57.08, + "Winogrande": 73.24, + "GSM8K": 11.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1b822c08b1065d5843cc48bf3a841ac5cd9d3b40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "layoric\/llama-2-13b-code-alpaca", + "Average \u2b06\ufe0f": 54.25, + "ARC": 60.84, + "HellaSwag": 82.14, + "MMLU": 55.93, + "TruthfulQA": 38.27, + "Winogrande": 76.4, + "GSM8K": 11.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aa1d543fe3391fe9f0e6143ef785fffe9c871225", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/13B-HyperMantis", + "Average \u2b06\ufe0f": 54.25, + "ARC": 58.53, + "HellaSwag": 82.2, + "MMLU": 50.61, + "TruthfulQA": 47.5, + "Winogrande": 76.24, + "GSM8K": 10.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "aa828ef92c363a5577ffd7d29e678277b9d2eb3c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "sethuiyer\/OpenDolphinHermes_Llama2_7B", + "Average \u2b06\ufe0f": 54.24, + "ARC": 55.03, + "HellaSwag": 78.74, + "MMLU": 52.25, + "TruthfulQA": 46.1, + "Winogrande": 73.16, + "GSM8K": 20.17, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3b6713b4ab2e2ea79535802f126287dd9d7036ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "totally-not-an-llm\/EverythingLM-13b-V3-peft", + "Average \u2b06\ufe0f": 54.24, + "ARC": 58.36, + "HellaSwag": 81.03, + "MMLU": 54.7, + "TruthfulQA": 52.98, + "Winogrande": 72.85, + "GSM8K": 5.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7a2eed5038addcf4fa3b8dd358b45eb96134e749", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/Platypus2-13B-IA3", + "Average \u2b06\ufe0f": 54.23, + "ARC": 61.09, + "HellaSwag": 82.65, + "MMLU": 56.32, + "TruthfulQA": 38.35, + "Winogrande": 75.69, + "GSM8K": 11.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b738c64d536df02f5c137a94bc7a32a4c486012b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/llama-2-13b-hf-platypus", + "Average \u2b06\ufe0f": 54.22, + "ARC": 58.87, + "HellaSwag": 82.14, + "MMLU": 54.98, + "TruthfulQA": 42.84, + "Winogrande": 77.11, + "GSM8K": 9.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "39e07f6213a64d79cf31e9c0773dea6224f7f021", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NekoPunchBBB\/Llama-2-13b-hf_Open-Platypus", + "Average \u2b06\ufe0f": 54.22, + "ARC": 58.87, + "HellaSwag": 82.14, + "MMLU": 54.98, + "TruthfulQA": 42.84, + "Winogrande": 77.11, + "GSM8K": 9.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c318a24121bd69509f395e17a9636093213ece21", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FPHam\/Free_Sydney_13b_HF", + "Average \u2b06\ufe0f": 54.22, + "ARC": 59.39, + "HellaSwag": 81.4, + "MMLU": 53.73, + "TruthfulQA": 45.63, + "Winogrande": 76.01, + "GSM8K": 9.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "5474ecbccd1f2a2cda9f77a157993f55c97377ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "budecosystem\/genz-13b-v2", + "Average \u2b06\ufe0f": 54.2, + "ARC": 55.97, + "HellaSwag": 79.98, + "MMLU": 54.3, + "TruthfulQA": 48.09, + "Winogrande": 74.59, + "GSM8K": 12.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "98e0e2086df11b9f80e1571110540a657e52c2e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "StudentLLM\/Alpagasus-2-13b-QLoRA-merged", + "Average \u2b06\ufe0f": 54.2, + "ARC": 60.84, + "HellaSwag": 82.43, + "MMLU": 55.55, + "TruthfulQA": 38.65, + "Winogrande": 76.87, + "GSM8K": 10.84, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e324e828c8d68aa8510f50dfab133388a44fd821", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/llama2-13b-math1.2", + "Average \u2b06\ufe0f": 54.19, + "ARC": 56.91, + "HellaSwag": 80.71, + "MMLU": 53.21, + "TruthfulQA": 48.25, + "Winogrande": 74.74, + "GSM8K": 11.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b05b4c22893e950e8e33acb67087a9acc8f0ab97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "totally-not-an-llm\/PuddleJumper-13b-V2", + "Average \u2b06\ufe0f": 54.19, + "ARC": 57.0, + "HellaSwag": 81.06, + "MMLU": 58.3, + "TruthfulQA": 52.66, + "Winogrande": 72.45, + "GSM8K": 3.64, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1fe9494e334a32ba73dc2926f58246450850c534", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/llama2-13b-math1.1", + "Average \u2b06\ufe0f": 54.18, + "ARC": 57.25, + "HellaSwag": 80.74, + "MMLU": 53.56, + "TruthfulQA": 48.43, + "Winogrande": 74.43, + "GSM8K": 10.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3c4d83d3525e54a493ff510443fdcca44bf63b59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE1_17w-r4", + "Average \u2b06\ufe0f": 54.18, + "ARC": 56.74, + "HellaSwag": 82.27, + "MMLU": 56.18, + "TruthfulQA": 39.65, + "Winogrande": 77.03, + "GSM8K": 13.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7e0046627fabb0f23ace4b71f279d459ec4a0ff1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/Llama-2-13b-hf-ds_eli5_1024_r_64_alpha_16_merged", + "Average \u2b06\ufe0f": 54.16, + "ARC": 59.13, + "HellaSwag": 82.13, + "MMLU": 54.98, + "TruthfulQA": 44.23, + "Winogrande": 76.4, + "GSM8K": 8.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "aad13bce3b243721e52e9cda479f1102dda99f12", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/Metharme-13b-Merged", + "Average \u2b06\ufe0f": 54.15, + "ARC": 59.9, + "HellaSwag": 81.12, + "MMLU": 47.18, + "TruthfulQA": 51.18, + "Winogrande": 76.8, + "GSM8K": 8.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": false, + "Model sha": "90c02cc338afcdd890a948af06432674743363ad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/llama2-13b-math1.1", + "Average \u2b06\ufe0f": 54.14, + "ARC": 56.83, + "HellaSwag": 80.69, + "MMLU": 53.43, + "TruthfulQA": 48.48, + "Winogrande": 74.74, + "GSM8K": 10.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3c4d83d3525e54a493ff510443fdcca44bf63b59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/Wizard-Vicuna-13B-Uncensored", + "Average \u2b06\ufe0f": 54.14, + "ARC": 58.96, + "HellaSwag": 81.95, + "MMLU": 47.92, + "TruthfulQA": 51.69, + "Winogrande": 75.69, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "95bfd1640a54e76b3e857c2462fd3a77eca0b275", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Wizard-Vicuna-13B-Uncensored-HF", + "Average \u2b06\ufe0f": 54.14, + "ARC": 58.96, + "HellaSwag": 81.95, + "MMLU": 47.92, + "TruthfulQA": 51.69, + "Winogrande": 75.69, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 202.0, + "Available on the hub": true, + "Model sha": "fff9ac7f0e2e7b340f2301f5f089d989fc03be67", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/Llama-2-13b-hf-eli5-wiki-1024_r_64_alpha_16", + "Average \u2b06\ufe0f": 54.14, + "ARC": 59.98, + "HellaSwag": 82.43, + "MMLU": 55.41, + "TruthfulQA": 39.9, + "Winogrande": 76.56, + "GSM8K": 10.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6a0a2b6672c7b36c714a66c4a836e0b50c6cb5e6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xriminact\/TarsChattyBasev0.1", + "Average \u2b06\ufe0f": 54.14, + "ARC": 59.98, + "HellaSwag": 82.41, + "MMLU": 55.75, + "TruthfulQA": 41.41, + "Winogrande": 75.85, + "GSM8K": 9.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "472d986efb1336e3290518f9aad54db5faa510d5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-orca-platypus-coig-lite-4k-0.5e-13b", + "Average \u2b06\ufe0f": 54.13, + "ARC": 58.02, + "HellaSwag": 80.15, + "MMLU": 57.26, + "TruthfulQA": 48.04, + "Winogrande": 75.45, + "GSM8K": 5.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "081d1da5cfa2f6ad43abdf4fb5e41f8ec5846224", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/manticore-13b-chat-pyg", + "Average \u2b06\ufe0f": 54.13, + "ARC": 58.53, + "HellaSwag": 81.96, + "MMLU": 48.76, + "TruthfulQA": 48.76, + "Winogrande": 77.19, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": false, + "Model sha": "f9ef65a3cf50e3c09ccb443f99225148e08517aa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CalderaAI\/13B-BlueMethod", + "Average \u2b06\ufe0f": 54.12, + "ARC": 59.64, + "HellaSwag": 82.07, + "MMLU": 50.34, + "TruthfulQA": 47.74, + "Winogrande": 77.11, + "GSM8K": 7.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "315aa0924dd42840b8cced581c9db1240f9bae1d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "hfl\/chinese-alpaca-2-13b-16k", + "Average \u2b06\ufe0f": 54.12, + "ARC": 55.03, + "HellaSwag": 77.41, + "MMLU": 51.28, + "TruthfulQA": 46.5, + "Winogrande": 73.4, + "GSM8K": 21.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": true, + "Model sha": "ba4536aed022c49bda60e1b56a0dbefc2ea6a30a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-huangyt_Fintune_1_17w-gate_up_down_proj", + "Average \u2b06\ufe0f": 54.12, + "ARC": 57.17, + "HellaSwag": 82.26, + "MMLU": 55.89, + "TruthfulQA": 39.93, + "Winogrande": 76.56, + "GSM8K": 12.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c1a5ad1b5e490ed860eeb1b449a02e14da10717f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "IkariDev\/Athena-v1", + "Average \u2b06\ufe0f": 54.11, + "ARC": 60.07, + "HellaSwag": 82.64, + "MMLU": 55.61, + "TruthfulQA": 46.58, + "Winogrande": 74.82, + "GSM8K": 4.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "8f96e561c8c795e383ca0faeb1696fa1e33e87de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chickencaesar\/llama2-platypus-llama2-chat-13B-hf", + "Average \u2b06\ufe0f": 54.11, + "ARC": 62.97, + "HellaSwag": 82.75, + "MMLU": 56.86, + "TruthfulQA": 42.93, + "Winogrande": 76.32, + "GSM8K": 2.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e35bb473156d74c8b5ad23a5e9df815891e8139a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Fredithefish\/Guanaco-13B-Uncensored", + "Average \u2b06\ufe0f": 54.1, + "ARC": 59.56, + "HellaSwag": 82.7, + "MMLU": 53.65, + "TruthfulQA": 43.26, + "Winogrande": 76.32, + "GSM8K": 9.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "cf315234979f5924ad73399bcdcdf51b05a1fc98", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/llama-2-13b-Beluga-QLoRA", + "Average \u2b06\ufe0f": 54.09, + "ARC": 59.22, + "HellaSwag": 81.92, + "MMLU": 56.67, + "TruthfulQA": 48.23, + "Winogrande": 77.19, + "GSM8K": 1.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c0d3c0a5d4e9001ea933c6b71ca3adc99d1f71a2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "01-ai\/Yi-6B", + "Average \u2b06\ufe0f": 54.08, + "ARC": 55.55, + "HellaSwag": 76.57, + "MMLU": 64.11, + "TruthfulQA": 41.96, + "Winogrande": 74.19, + "GSM8K": 12.13, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 346.0, + "Available on the hub": true, + "Model sha": "e00f7cbde45745a22625ac85c6ad5d5b9f27098d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE3_3.3w-r16-q_k_v_o", + "Average \u2b06\ufe0f": 54.08, + "ARC": 59.3, + "HellaSwag": 81.2, + "MMLU": 55.58, + "TruthfulQA": 38.13, + "Winogrande": 76.8, + "GSM8K": 13.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "71224344025dbfada6821c6a89cade1d8358dad1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "stabilityai\/StableBeluga1-Delta", + "Average \u2b06\ufe0f": 54.08, + "ARC": 68.17, + "HellaSwag": 85.88, + "MMLU": 64.83, + "TruthfulQA": 55.81, + "Winogrande": 49.8, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 65.29, + "Hub \u2764\ufe0f": 57.0, + "Available on the hub": true, + "Model sha": "40a78d91d43ad9aef6663ff15ddc15be9922bce5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bhenrym14\/airophin-v2-13b-PI-8k-fp16", + "Average \u2b06\ufe0f": 54.07, + "ARC": 60.58, + "HellaSwag": 82.96, + "MMLU": 56.75, + "TruthfulQA": 40.14, + "Winogrande": 76.64, + "GSM8K": 7.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "26b7edfd282af223d86d5e539451357bb114247b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r8-q_k_v_o", + "Average \u2b06\ufe0f": 54.06, + "ARC": 57.68, + "HellaSwag": 81.91, + "MMLU": 54.95, + "TruthfulQA": 41.31, + "Winogrande": 76.48, + "GSM8K": 12.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f76f93dad8408523e69c59abbb96ce6b1b9b9f69", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/ReMM-L2-13B-PIPPA", + "Average \u2b06\ufe0f": 54.06, + "ARC": 59.73, + "HellaSwag": 83.12, + "MMLU": 54.1, + "TruthfulQA": 49.94, + "Winogrande": 74.51, + "GSM8K": 2.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "79e711178c6881496ae1f5635b08bc193f370709", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/ReMM-L2-13B", + "Average \u2b06\ufe0f": 54.06, + "ARC": 59.73, + "HellaSwag": 83.1, + "MMLU": 54.11, + "TruthfulQA": 49.94, + "Winogrande": 74.51, + "GSM8K": 2.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c4710577003a23ca8e9040d16dfb8f3e9bc5d636", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/llama2-13b-math1.2", + "Average \u2b06\ufe0f": 54.05, + "ARC": 57.08, + "HellaSwag": 80.61, + "MMLU": 53.05, + "TruthfulQA": 48.3, + "Winogrande": 74.27, + "GSM8K": 10.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b05b4c22893e950e8e33acb67087a9acc8f0ab97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/Llama-2-13b-FINETUNE4_compare8k2", + "Average \u2b06\ufe0f": 54.05, + "ARC": 58.28, + "HellaSwag": 81.39, + "MMLU": 56.87, + "TruthfulQA": 39.86, + "Winogrande": 76.01, + "GSM8K": 11.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fe1b604097aad9408ce63fa7ffc9c320cdd06e4f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/airoboros-13B-HF", + "Average \u2b06\ufe0f": 54.05, + "ARC": 58.28, + "HellaSwag": 81.05, + "MMLU": 50.03, + "TruthfulQA": 51.57, + "Winogrande": 76.24, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "9219b61a0e8bc880e4cd0f8bebc48a97ee0950c7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/Mistral-7B-attention-100000", + "Average \u2b06\ufe0f": 54.05, + "ARC": 52.99, + "HellaSwag": 78.54, + "MMLU": 54.79, + "TruthfulQA": 45.37, + "Winogrande": 75.61, + "GSM8K": 16.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "be7a7aa124108276788139ee1c7269553dd4f9d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Nous-Hermes-13b", + "Average \u2b06\ufe0f": 54.04, + "ARC": 56.57, + "HellaSwag": 82.11, + "MMLU": 50.44, + "TruthfulQA": 51.5, + "Winogrande": 75.3, + "GSM8K": 8.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 418.0, + "Available on the hub": true, + "Model sha": "24e8c03148ffd1f3e469744dfc24ad2ad82848f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "msy127\/mnsim-dpo-peftmerged-2-eos", + "Average \u2b06\ufe0f": 54.04, + "ARC": 55.63, + "HellaSwag": 77.82, + "MMLU": 51.25, + "TruthfulQA": 46.37, + "Winogrande": 76.24, + "GSM8K": 16.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.16, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "10d1299a6a062f59490588367102cd398c05e2fe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "The-Face-Of-Goonery\/Huginn-13b-V4", + "Average \u2b06\ufe0f": 54.04, + "ARC": 60.67, + "HellaSwag": 82.34, + "MMLU": 52.32, + "TruthfulQA": 50.62, + "Winogrande": 73.64, + "GSM8K": 4.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6186feee849e0c2b7e62d4cbdc4cdc48260ac684", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "The-Face-Of-Goonery\/Huginn-13b-v4.5", + "Average \u2b06\ufe0f": 54.04, + "ARC": 60.67, + "HellaSwag": 82.34, + "MMLU": 52.32, + "TruthfulQA": 50.62, + "Winogrande": 73.64, + "GSM8K": 4.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "f3be56d8bf71a8d3905974b1e5fcba7336b02159", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "The-Face-Of-Goonery\/Huginn-v3-13b", + "Average \u2b06\ufe0f": 54.04, + "ARC": 60.67, + "HellaSwag": 82.34, + "MMLU": 52.32, + "TruthfulQA": 50.62, + "Winogrande": 73.64, + "GSM8K": 4.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": false, + "Model sha": "6c2faf828c5380d28c51fcb4d3d0f1a420fb9a9a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-13b", + "Average \u2b06\ufe0f": 54.02, + "ARC": 58.28, + "HellaSwag": 81.05, + "MMLU": 50.03, + "TruthfulQA": 51.57, + "Winogrande": 76.24, + "GSM8K": 6.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 105.0, + "Available on the hub": true, + "Model sha": "44830f9e1559f318f5dad875bab40d1d1beddbfc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "01-ai\/Yi-6B", + "Average \u2b06\ufe0f": 54.02, + "ARC": 55.55, + "HellaSwag": 76.42, + "MMLU": 63.85, + "TruthfulQA": 41.86, + "Winogrande": 73.8, + "GSM8K": 12.66, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 346.0, + "Available on the hub": true, + "Model sha": "d8029c814d8faa68e1aef2e488f668a3af5d1a8a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/llama-13b-pretrained", + "Average \u2b06\ufe0f": 54.02, + "ARC": 56.31, + "HellaSwag": 79.32, + "MMLU": 47.03, + "TruthfulQA": 48.42, + "Winogrande": 76.95, + "GSM8K": 16.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c28cc0cf5a1a1bf4de96b23d06b02129dca85eb9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE5_4w-r8-gate_up_down", + "Average \u2b06\ufe0f": 54.02, + "ARC": 57.17, + "HellaSwag": 82.15, + "MMLU": 54.88, + "TruthfulQA": 40.23, + "Winogrande": 76.32, + "GSM8K": 13.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "86adab5c098c9338e098a8e5b0188b0aa39b2478", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/MythicalDestroyerV2-Platypus2-13B-QLora-0.80-epoch", + "Average \u2b06\ufe0f": 54.01, + "ARC": 57.34, + "HellaSwag": 81.24, + "MMLU": 55.64, + "TruthfulQA": 55.98, + "Winogrande": 73.88, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ada55b32fe8ed55b7691d997ad2e86f232c91aad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nvidia\/OpenMath-Mistral-7B-v0.1-hf", + "Average \u2b06\ufe0f": 54.0, + "ARC": 59.39, + "HellaSwag": 81.78, + "MMLU": 59.34, + "TruthfulQA": 46.13, + "Winogrande": 77.27, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "e378a80b22387a5a30ccbb9feaf3e9b0bc3cfc57", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/based-30b", + "Average \u2b06\ufe0f": 54.0, + "ARC": 63.91, + "HellaSwag": 85.67, + "MMLU": 58.28, + "TruthfulQA": 35.7, + "Winogrande": 80.11, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 32.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5818a6344f48dc5a324589b57cb288a9d54c0b79", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-orca-platypus-coig-lite-4k-0.6e-13b", + "Average \u2b06\ufe0f": 53.99, + "ARC": 58.79, + "HellaSwag": 79.93, + "MMLU": 56.77, + "TruthfulQA": 48.29, + "Winogrande": 75.93, + "GSM8K": 4.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6bf4cf6211489bdbea70585a4a5c0f39deefb4e5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE3_3.3w-r8-q_k_v_o", + "Average \u2b06\ufe0f": 53.99, + "ARC": 56.06, + "HellaSwag": 81.89, + "MMLU": 55.04, + "TruthfulQA": 40.12, + "Winogrande": 76.56, + "GSM8K": 14.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f907fffbb08698040325b3f2e47200a1b48b3ed9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/gpt4-alpaca-lora-13B-HF", + "Average \u2b06\ufe0f": 53.98, + "ARC": 59.56, + "HellaSwag": 82.09, + "MMLU": 47.48, + "TruthfulQA": 48.96, + "Winogrande": 76.72, + "GSM8K": 9.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "49678a2dd15fb4e1f1b99616ccc1ffd269912833", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KnutJaegersberg\/webMistral-7B", + "Average \u2b06\ufe0f": 53.97, + "ARC": 59.04, + "HellaSwag": 80.89, + "MMLU": 59.0, + "TruthfulQA": 39.71, + "Winogrande": 76.32, + "GSM8K": 8.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0b221c617df3d2f883cfd925f646ebd93de23037", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "WizardLM\/WizardMath-13B-V1.0", + "Average \u2b06\ufe0f": 53.97, + "ARC": 60.07, + "HellaSwag": 82.01, + "MMLU": 54.8, + "TruthfulQA": 42.7, + "Winogrande": 71.9, + "GSM8K": 12.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "209316bea6eab73d8b18fca2a730b1dff3dcf999", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openaccess-ai-collective\/minotaur-13b", + "Average \u2b06\ufe0f": 53.97, + "ARC": 56.4, + "HellaSwag": 79.13, + "MMLU": 49.61, + "TruthfulQA": 49.62, + "Winogrande": 76.56, + "GSM8K": 12.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "b5ae4519d4c8f4559a0aa80b6efe2008413ece01", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_v2_w", + "Average \u2b06\ufe0f": 53.96, + "ARC": 57.34, + "HellaSwag": 81.23, + "MMLU": 50.17, + "TruthfulQA": 50.7, + "Winogrande": 75.93, + "GSM8K": 8.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 30.0, + "Available on the hub": true, + "Model sha": "0eb53946b8fac30606dc72541f2fc073cb6a0e12", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_v2", + "Average \u2b06\ufe0f": 53.96, + "ARC": 57.17, + "HellaSwag": 81.14, + "MMLU": 50.58, + "TruthfulQA": 49.54, + "Winogrande": 76.24, + "GSM8K": 9.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "bd2a0968964c0f2dfae8f5a8950b43e35142f830", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/MT7Bi-alpha-dpo", + "Average \u2b06\ufe0f": 53.96, + "ARC": 55.03, + "HellaSwag": 75.45, + "MMLU": 52.63, + "TruthfulQA": 43.81, + "Winogrande": 71.03, + "GSM8K": 25.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "395626f9971b41065264e9c98c4daa53cdf609cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/Llama-2-13b-FINETUNE4_TEST3", + "Average \u2b06\ufe0f": 53.95, + "ARC": 59.04, + "HellaSwag": 81.65, + "MMLU": 56.37, + "TruthfulQA": 39.98, + "Winogrande": 75.45, + "GSM8K": 11.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e81b5d4550224711929fdea4effdd990cc0c7404", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Weyaxi\/Platypus-Nebula-v2-7B", + "Average \u2b06\ufe0f": 53.95, + "ARC": 55.38, + "HellaSwag": 83.02, + "MMLU": 56.07, + "TruthfulQA": 46.94, + "Winogrande": 72.22, + "GSM8K": 10.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2d95180bae03c0b268dff44a1f9806fc295adc09", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-huangyt_FINETUNE2_3w-gate_up_down_proj", + "Average \u2b06\ufe0f": 53.95, + "ARC": 57.42, + "HellaSwag": 82.42, + "MMLU": 55.57, + "TruthfulQA": 39.19, + "Winogrande": 77.03, + "GSM8K": 12.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "469c6674ad2190b639d6f5ce6bfecc1463825dfb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_compare15k_4.5w-r16-gate_up_down", + "Average \u2b06\ufe0f": 53.94, + "ARC": 58.36, + "HellaSwag": 82.33, + "MMLU": 56.14, + "TruthfulQA": 39.51, + "Winogrande": 76.4, + "GSM8K": 10.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d824054153586d58139b7c3527ba211f33a81382", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/MedMerge-6-7b-alpha-dpo", + "Average \u2b06\ufe0f": 53.94, + "ARC": 54.27, + "HellaSwag": 75.6, + "MMLU": 52.65, + "TruthfulQA": 43.94, + "Winogrande": 71.03, + "GSM8K": 26.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "862c90d07e4614122bce660b8e725d142f6526c4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Voicelab\/trurl-2-13b-academic", + "Average \u2b06\ufe0f": 53.94, + "ARC": 57.94, + "HellaSwag": 79.55, + "MMLU": 55.2, + "TruthfulQA": 43.46, + "Winogrande": 76.56, + "GSM8K": 10.92, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "2e95049edf02368bbd4b4f6ffb50bc8821e919bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jingyeom\/KoSoLAR-10.7B-v0.2_1.4_dedup", + "Average \u2b06\ufe0f": 53.93, + "ARC": 60.07, + "HellaSwag": 82.18, + "MMLU": 61.3, + "TruthfulQA": 45.38, + "Winogrande": 74.66, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0945d3f95080bc4adc06964ecbc8131d90456bd0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JosephusCheung\/Pwen-7B-Chat-20_30", + "Average \u2b06\ufe0f": 53.93, + "ARC": 51.45, + "HellaSwag": 73.99, + "MMLU": 62.08, + "TruthfulQA": 47.01, + "Winogrande": 68.43, + "GSM8K": 20.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e6c38a7d2f4ba7b867fff421c08c02ba1908224e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "euclaise\/Ferret-7B", + "Average \u2b06\ufe0f": 53.93, + "ARC": 62.29, + "HellaSwag": 81.31, + "MMLU": 60.27, + "TruthfulQA": 40.01, + "Winogrande": 77.66, + "GSM8K": 2.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b1ef5adff5ceb06d2d9808bccf5e06705f9e19dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/llama-2-13b-chat-platypus", + "Average \u2b06\ufe0f": 53.92, + "ARC": 53.84, + "HellaSwag": 80.67, + "MMLU": 54.44, + "TruthfulQA": 46.23, + "Winogrande": 76.01, + "GSM8K": 12.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "828aa1020fc7d394fe8ee2c596e3211df7656eac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bhenrym14\/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16", + "Average \u2b06\ufe0f": 53.92, + "ARC": 60.58, + "HellaSwag": 82.97, + "MMLU": 52.1, + "TruthfulQA": 46.1, + "Winogrande": 73.64, + "GSM8K": 8.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "24ebae726954e4c1f24a8b2cbe0ca863012a7338", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-huangyt_Fintune_1_17w", + "Average \u2b06\ufe0f": 53.91, + "ARC": 59.47, + "HellaSwag": 81.0, + "MMLU": 54.31, + "TruthfulQA": 38.17, + "Winogrande": 77.27, + "GSM8K": 13.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aa5b161b39900c5e80d5bb39d098f6333ad964f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Gryphe\/MythoBoros-13b", + "Average \u2b06\ufe0f": 53.9, + "ARC": 58.19, + "HellaSwag": 81.75, + "MMLU": 50.13, + "TruthfulQA": 48.93, + "Winogrande": 75.77, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "67695d15e6610bc8055fbcde82f298e48ad2d374", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/MaxiCPM-3x3B-Test", + "Average \u2b06\ufe0f": 53.9, + "ARC": 45.99, + "HellaSwag": 71.74, + "MMLU": 52.88, + "TruthfulQA": 41.06, + "Winogrande": 66.85, + "GSM8K": 44.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d353013fe9622a31794ea0837ba21e34a39ea465", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/llama-2-13b-QLoRA", + "Average \u2b06\ufe0f": 53.87, + "ARC": 58.02, + "HellaSwag": 82.33, + "MMLU": 55.8, + "TruthfulQA": 46.23, + "Winogrande": 77.58, + "GSM8K": 3.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d1a41d83c6bcc14378ee4859d65ef77a261d39d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-13b-gpt4-1.4-fp16", + "Average \u2b06\ufe0f": 53.87, + "ARC": 59.64, + "HellaSwag": 83.22, + "MMLU": 47.56, + "TruthfulQA": 48.82, + "Winogrande": 76.24, + "GSM8K": 7.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "037e369be06a8a0eef87f2cddfd3469670483f29", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-13b-gpt4-1.4", + "Average \u2b06\ufe0f": 53.87, + "ARC": 59.64, + "HellaSwag": 83.22, + "MMLU": 47.56, + "TruthfulQA": 48.82, + "Winogrande": 76.24, + "GSM8K": 7.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "d0d2687ed2b4a63a644ed6c5b3f6401844718659", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "euclaise\/Ferret_7B", + "Average \u2b06\ufe0f": 53.87, + "ARC": 62.29, + "HellaSwag": 81.33, + "MMLU": 60.09, + "TruthfulQA": 39.94, + "Winogrande": 77.51, + "GSM8K": 2.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "c1e1e2743ffa7b9369aebac751b04f7e8740f80d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "euclaise\/Ferret-7B", + "Average \u2b06\ufe0f": 53.87, + "ARC": 62.29, + "HellaSwag": 81.33, + "MMLU": 60.09, + "TruthfulQA": 39.94, + "Winogrande": 77.51, + "GSM8K": 2.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e96b5245ef97999f143a2c9f9739e5cf52ec0d64", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "zyh3826\/llama2-13b-ft-openllm-leaderboard-v1", + "Average \u2b06\ufe0f": 53.86, + "ARC": 59.64, + "HellaSwag": 83.14, + "MMLU": 60.93, + "TruthfulQA": 40.72, + "Winogrande": 77.35, + "GSM8K": 1.36, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "70404059013c74b0641ed69d293b3d1ad708cd1e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE5_4w-r4-gate_up_down", + "Average \u2b06\ufe0f": 53.86, + "ARC": 55.38, + "HellaSwag": 81.92, + "MMLU": 55.28, + "TruthfulQA": 40.76, + "Winogrande": 76.09, + "GSM8K": 13.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2ca747d779feaa99c475b8015c9b4a50aea41cd2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lajonbot\/WizardLM-13B-V1.2-PL-lora_unload", + "Average \u2b06\ufe0f": 53.86, + "ARC": 58.53, + "HellaSwag": 81.1, + "MMLU": 55.15, + "TruthfulQA": 46.18, + "Winogrande": 71.03, + "GSM8K": 11.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "5f14e6f5ea67fd2840791c46b3e00846cbdb32cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Gryphe\/MythoLogic-13b", + "Average \u2b06\ufe0f": 53.85, + "ARC": 58.45, + "HellaSwag": 81.56, + "MMLU": 49.36, + "TruthfulQA": 49.47, + "Winogrande": 75.61, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "d89d925ad1eeaee465c4de3e5c74240a5a40b585", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/platypus-2-22b-relora", + "Average \u2b06\ufe0f": 53.83, + "ARC": 57.68, + "HellaSwag": 82.44, + "MMLU": 55.33, + "TruthfulQA": 43.61, + "Winogrande": 77.35, + "GSM8K": 6.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 21.83, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "15bca3e9b25cc2f280fec21686ef3bc445217503", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Envoid\/Libra-19B", + "Average \u2b06\ufe0f": 53.83, + "ARC": 60.58, + "HellaSwag": 82.04, + "MMLU": 55.57, + "TruthfulQA": 48.41, + "Winogrande": 76.32, + "GSM8K": 0.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 19.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a4e1f8f62740d676c25eedb4f29f4e776dcc0c22", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-Open_Platypus_and_ccp_2.6w-3_epoch", + "Average \u2b06\ufe0f": 53.8, + "ARC": 58.62, + "HellaSwag": 82.56, + "MMLU": 55.84, + "TruthfulQA": 42.09, + "Winogrande": 76.64, + "GSM8K": 7.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "001a5f96daea57b5f256c2df270b35653b439f6f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Weyaxi\/test-help-steer-filtered-orig", + "Average \u2b06\ufe0f": 53.77, + "ARC": 57.59, + "HellaSwag": 80.42, + "MMLU": 57.24, + "TruthfulQA": 41.1, + "Winogrande": 76.64, + "GSM8K": 9.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bda6d45ddb3ef73df4d198d95416c66872429927", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NekoPunchBBB\/Llama-2-13b-hf_Open-Platypus-8bit-att", + "Average \u2b06\ufe0f": 53.75, + "ARC": 57.51, + "HellaSwag": 82.14, + "MMLU": 54.56, + "TruthfulQA": 42.21, + "Winogrande": 76.56, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "83a8e51d0a72dcfbe5de13dc7ee10dc20e91602e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Kimiko-13B-fp16", + "Average \u2b06\ufe0f": 53.75, + "ARC": 59.22, + "HellaSwag": 82.35, + "MMLU": 55.85, + "TruthfulQA": 39.55, + "Winogrande": 76.72, + "GSM8K": 8.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "27868769e2d6b1af46337f0997c71b0577952a3d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NobodyExistsOnTheInternet\/GiftedConvo13bLoraNoEconsE4", + "Average \u2b06\ufe0f": 53.74, + "ARC": 59.9, + "HellaSwag": 84.11, + "MMLU": 54.67, + "TruthfulQA": 41.94, + "Winogrande": 74.03, + "GSM8K": 7.81, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f3d421aadb29830345bf392f793ce3c33e7d68c5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-huangyt_FINETUNE2_3w-q_k_v_o_proj", + "Average \u2b06\ufe0f": 53.74, + "ARC": 58.53, + "HellaSwag": 82.47, + "MMLU": 53.9, + "TruthfulQA": 37.92, + "Winogrande": 76.8, + "GSM8K": 12.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d74752b931bfddaa063a292e7ea85dfb1d7a4998", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/Platypus2-13B-QLoRa", + "Average \u2b06\ufe0f": 53.74, + "ARC": 57.51, + "HellaSwag": 82.55, + "MMLU": 57.34, + "TruthfulQA": 43.38, + "Winogrande": 76.64, + "GSM8K": 5.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e62a8fafce0d64ac03d465a4e915bc1f50776a08", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/zarafusionex-1.2-l2-7b", + "Average \u2b06\ufe0f": 53.73, + "ARC": 56.66, + "HellaSwag": 79.16, + "MMLU": 51.94, + "TruthfulQA": 51.29, + "Winogrande": 74.74, + "GSM8K": 8.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "68ca01427848528ab21263fd06720a081b09d063", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r16-q_k_v_o_gate_up_down", + "Average \u2b06\ufe0f": 53.71, + "ARC": 57.25, + "HellaSwag": 81.49, + "MMLU": 55.9, + "TruthfulQA": 39.79, + "Winogrande": 75.77, + "GSM8K": 12.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a12fb5937e6904977e8123b0d5ef21283b6895d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE3_3.3w-r8-gate_up_down", + "Average \u2b06\ufe0f": 53.71, + "ARC": 57.25, + "HellaSwag": 81.79, + "MMLU": 53.96, + "TruthfulQA": 39.66, + "Winogrande": 77.82, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8a75b17d4b60f820159bb0100f26f438727bb199", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kz919\/mistral-7b-sft-open-orca-flan-50k", + "Average \u2b06\ufe0f": 53.7, + "ARC": 58.79, + "HellaSwag": 81.92, + "MMLU": 55.72, + "TruthfulQA": 37.49, + "Winogrande": 77.98, + "GSM8K": 10.31, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "54129b5d7a3824af7d457e007742750029cb3904", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lajonbot\/vicuna-13b-v1.3-PL-lora_unload", + "Average \u2b06\ufe0f": 53.7, + "ARC": 54.86, + "HellaSwag": 80.41, + "MMLU": 52.2, + "TruthfulQA": 49.62, + "Winogrande": 76.09, + "GSM8K": 9.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5582369752583b02df3cba4bd2a733d12265cddb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gaodrew\/gaodrew-gorgonzola-13b", + "Average \u2b06\ufe0f": 53.7, + "ARC": 50.94, + "HellaSwag": 77.65, + "MMLU": 68.93, + "TruthfulQA": 40.63, + "Winogrande": 75.45, + "GSM8K": 8.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "a53fbe358d4cb546916847d861ccfaf7c724a103", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE5_4w-r8-q_k_v_o_gate_up_down", + "Average \u2b06\ufe0f": 53.69, + "ARC": 55.72, + "HellaSwag": 81.55, + "MMLU": 53.9, + "TruthfulQA": 41.89, + "Winogrande": 77.19, + "GSM8K": 11.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "eb934db4644738a74143b381445213979c8858ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-huangyt_FINETUNE2_3w", + "Average \u2b06\ufe0f": 53.69, + "ARC": 58.62, + "HellaSwag": 82.32, + "MMLU": 54.25, + "TruthfulQA": 38.17, + "Winogrande": 76.8, + "GSM8K": 11.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "08bc7112a775dd4223d441355f3d619694013789", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-mixtral-8x7b-v16.2-32k", + "Average \u2b06\ufe0f": 53.69, + "ARC": 34.39, + "HellaSwag": 81.72, + "MMLU": 71.33, + "TruthfulQA": 56.65, + "Winogrande": 77.82, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "eae1e422ac65e856c03a9da0a840114267d24b68", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "BramVanroy\/Llama-2-13b-chat-dutch", + "Average \u2b06\ufe0f": 53.69, + "ARC": 59.3, + "HellaSwag": 81.45, + "MMLU": 55.82, + "TruthfulQA": 38.23, + "Winogrande": 76.64, + "GSM8K": 10.69, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "428508a0cf288c0f5b7891c9b2f758ddf4d62c26", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-13b-gpt4-1.1", + "Average \u2b06\ufe0f": 53.68, + "ARC": 59.04, + "HellaSwag": 83.05, + "MMLU": 49.41, + "TruthfulQA": 46.62, + "Winogrande": 75.77, + "GSM8K": 8.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "19c7060adcb34d42e742fe51dd36b8657ac069b7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r16-q_k_v_o", + "Average \u2b06\ufe0f": 53.68, + "ARC": 56.23, + "HellaSwag": 81.98, + "MMLU": 55.87, + "TruthfulQA": 39.76, + "Winogrande": 76.72, + "GSM8K": 11.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cc3c5e5a874cf4ff4f94ea919e819f8a914c8acb", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "shareAI\/bimoGPT-llama2-13b", + "Average \u2b06\ufe0f": 53.68, + "ARC": 58.79, + "HellaSwag": 82.08, + "MMLU": 55.6, + "TruthfulQA": 37.82, + "Winogrande": 76.48, + "GSM8K": 11.3, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c29b67965ea55da3e2ac678eef7ffdf36f8ef5ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abideen\/gemma-7b-openhermes", + "Average \u2b06\ufe0f": 53.67, + "ARC": 51.28, + "HellaSwag": 71.93, + "MMLU": 53.56, + "TruthfulQA": 47.18, + "Winogrande": 68.19, + "GSM8K": 29.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "8798db2d228a8d460966f3078fe65db7616ec1dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TaylorAI\/Flash-Llama-13B", + "Average \u2b06\ufe0f": 53.67, + "ARC": 59.3, + "HellaSwag": 82.15, + "MMLU": 55.67, + "TruthfulQA": 37.39, + "Winogrande": 76.64, + "GSM8K": 10.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "81b40096471a8980e3e1a8998f358bd363033783", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "TheBloke\/Llama-2-13B-fp16", + "Average \u2b06\ufe0f": 53.67, + "ARC": 59.3, + "HellaSwag": 82.15, + "MMLU": 55.67, + "TruthfulQA": 37.39, + "Winogrande": 76.64, + "GSM8K": 10.84, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 56.0, + "Available on the hub": false, + "Model sha": "b2e65e8ad4bb35e5abaee0170ebd5fc2134a50bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NewstaR\/Starlight-13B", + "Average \u2b06\ufe0f": 53.67, + "ARC": 59.3, + "HellaSwag": 82.15, + "MMLU": 55.67, + "TruthfulQA": 37.39, + "Winogrande": 76.64, + "GSM8K": 10.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cb9fced568b1abd881133c642c427aaa488f00cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r16-gate_up_down-test1", + "Average \u2b06\ufe0f": 53.66, + "ARC": 55.8, + "HellaSwag": 82.27, + "MMLU": 55.63, + "TruthfulQA": 38.15, + "Winogrande": 77.43, + "GSM8K": 12.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "48b8ceeb62e5ca897f284bbc0923201689af7c89", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chargoddard\/llama2-22b-blocktriangular", + "Average \u2b06\ufe0f": 53.65, + "ARC": 58.28, + "HellaSwag": 82.69, + "MMLU": 54.53, + "TruthfulQA": 39.23, + "Winogrande": 75.93, + "GSM8K": 11.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 22.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "7adbaa5b8e122bb93bf510d8655ec4132d7b4a8a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-13b-gpt4", + "Average \u2b06\ufe0f": 53.64, + "ARC": 59.39, + "HellaSwag": 83.29, + "MMLU": 47.89, + "TruthfulQA": 47.65, + "Winogrande": 75.77, + "GSM8K": 7.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "c0eef6e6f63d4b11953539308717cea0079b44f9", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "chargoddard\/llama2-22b", + "Average \u2b06\ufe0f": 53.64, + "ARC": 58.53, + "HellaSwag": 82.55, + "MMLU": 54.68, + "TruthfulQA": 39.84, + "Winogrande": 76.32, + "GSM8K": 9.93, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 22.0, + "Hub \u2764\ufe0f": 44.0, + "Available on the hub": false, + "Model sha": "2bece0787009b4b584f49d0e0d1b49ecf4a52da9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/platypus2-22b-relora", + "Average \u2b06\ufe0f": 53.64, + "ARC": 57.51, + "HellaSwag": 82.36, + "MMLU": 54.94, + "TruthfulQA": 43.62, + "Winogrande": 77.11, + "GSM8K": 6.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 21.83, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "15bca3e9b25cc2f280fec21686ef3bc445217503", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NobodyExistsOnTheInternet\/PuffedLIMA13bQLORA", + "Average \u2b06\ufe0f": 53.63, + "ARC": 59.9, + "HellaSwag": 84.39, + "MMLU": 53.68, + "TruthfulQA": 39.9, + "Winogrande": 75.22, + "GSM8K": 8.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7da6d235d625e16c850ccd0b947dee40071b1f89", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/deacon-13b", + "Average \u2b06\ufe0f": 53.63, + "ARC": 57.85, + "HellaSwag": 82.63, + "MMLU": 55.25, + "TruthfulQA": 39.33, + "Winogrande": 76.32, + "GSM8K": 10.39, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6c3a002f6c9e8a481a7375d91856d603bf6dd040", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE3_3.3w-r4-q_k_v_o", + "Average \u2b06\ufe0f": 53.62, + "ARC": 59.04, + "HellaSwag": 81.15, + "MMLU": 53.0, + "TruthfulQA": 40.16, + "Winogrande": 76.48, + "GSM8K": 11.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ac40ecf48cf5f7168e8c3929632c654bc834c3d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/llama2-13b-FINETUNE3_TEST2", + "Average \u2b06\ufe0f": 53.62, + "ARC": 54.69, + "HellaSwag": 81.48, + "MMLU": 56.8, + "TruthfulQA": 39.93, + "Winogrande": 76.24, + "GSM8K": 12.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9e6431061bd13852a7435f5fe7a6eb0bbd148e14", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "llm-agents\/tora-13b-v1.0", + "Average \u2b06\ufe0f": 53.62, + "ARC": 58.96, + "HellaSwag": 82.31, + "MMLU": 54.73, + "TruthfulQA": 40.25, + "Winogrande": 75.61, + "GSM8K": 9.86, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "0636c1f582c979a5a292cc5f3dc293800b1494e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/MistralInstructLongish", + "Average \u2b06\ufe0f": 53.62, + "ARC": 60.75, + "HellaSwag": 81.86, + "MMLU": 60.49, + "TruthfulQA": 40.55, + "Winogrande": 76.56, + "GSM8K": 1.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "813c4707970cb5bf3e2a49f7f350af59e7032c24", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "chargoddard\/internlm2-base-7b-llama", + "Average \u2b06\ufe0f": 53.62, + "ARC": 54.35, + "HellaSwag": 79.47, + "MMLU": 54.05, + "TruthfulQA": 43.23, + "Winogrande": 71.43, + "GSM8K": 19.18, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "db8227e5bf55053f8efde4630f1d170c84dd1808", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NobodyExistsOnTheInternet\/PuffedConvo13bLoraE4", + "Average \u2b06\ufe0f": 53.62, + "ARC": 59.81, + "HellaSwag": 84.39, + "MMLU": 53.62, + "TruthfulQA": 39.87, + "Winogrande": 75.22, + "GSM8K": 8.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "40e4fce0c25bd23f6011b424748ee2b5374b98d5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/Llama-2-13b-FINETUNE4_TEST", + "Average \u2b06\ufe0f": 53.62, + "ARC": 54.78, + "HellaSwag": 81.52, + "MMLU": 56.03, + "TruthfulQA": 39.14, + "Winogrande": 77.03, + "GSM8K": 13.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0ed198a814192b06e60715112d2a4b6bfd630806", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/Nous-Hermes-13b-pl-lora_unload", + "Average \u2b06\ufe0f": 53.61, + "ARC": 57.08, + "HellaSwag": 81.49, + "MMLU": 49.17, + "TruthfulQA": 48.3, + "Winogrande": 76.4, + "GSM8K": 9.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d0ef3991a11c4dc2ea2f832d4082c89c3c5e810c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Python-Code-13B", + "Average \u2b06\ufe0f": 53.61, + "ARC": 58.79, + "HellaSwag": 81.66, + "MMLU": 54.78, + "TruthfulQA": 42.83, + "Winogrande": 74.03, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "981454b6a2275f787592589609df7f2bf558706d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Menouar\/phi-2-basic-maths", + "Average \u2b06\ufe0f": 53.6, + "ARC": 55.8, + "HellaSwag": 71.15, + "MMLU": 47.27, + "TruthfulQA": 41.4, + "Winogrande": 75.3, + "GSM8K": 30.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c8e856be5f951cc93588c7af07d6c6a9da058490", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BramVanroy\/llama2-13b-ft-mc4_nl_cleaned_tiny", + "Average \u2b06\ufe0f": 53.6, + "ARC": 59.3, + "HellaSwag": 82.04, + "MMLU": 54.67, + "TruthfulQA": 38.03, + "Winogrande": 77.27, + "GSM8K": 10.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "b23fe7d174653b87dc08507d9b83504a8dddbc45", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/WizardLM-1.0-Uncensored-CodeLlama-34b", + "Average \u2b06\ufe0f": 53.59, + "ARC": 56.4, + "HellaSwag": 75.45, + "MMLU": 54.51, + "TruthfulQA": 43.06, + "Winogrande": 72.45, + "GSM8K": 19.64, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 33.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3e8df2cf4a4ee1c0b2d079cb7be70024d425ea8c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r8-gate_up_down", + "Average \u2b06\ufe0f": 53.58, + "ARC": 54.35, + "HellaSwag": 82.13, + "MMLU": 55.33, + "TruthfulQA": 39.6, + "Winogrande": 77.19, + "GSM8K": 12.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1646a2b77ddeaf0f848c96ed68726556c7539729", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/tulu-13B-fp16", + "Average \u2b06\ufe0f": 53.58, + "ARC": 53.92, + "HellaSwag": 80.66, + "MMLU": 53.19, + "TruthfulQA": 43.84, + "Winogrande": 75.61, + "GSM8K": 14.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "532aeb363b0ceee155b3cf9479ef635b797cee7c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "codellama\/CodeLlama-34b-Python-hf", + "Average \u2b06\ufe0f": 53.58, + "ARC": 50.43, + "HellaSwag": 76.36, + "MMLU": 49.11, + "TruthfulQA": 41.37, + "Winogrande": 71.9, + "GSM8K": 32.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 91.0, + "Available on the hub": true, + "Model sha": "6a39a8f3839cfc8c6a966f6b4e70472ac6fb719b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/Llama-2-13b-hf-eli5-wiki-1024_r_64_alpha_16_merged", + "Average \u2b06\ufe0f": 53.57, + "ARC": 58.96, + "HellaSwag": 81.94, + "MMLU": 55.0, + "TruthfulQA": 40.26, + "Winogrande": 76.56, + "GSM8K": 8.72, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "30edbe648df2661dd779cd19ef613e6914dcc8e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "circulus\/Llama-2-7b-orca-v1", + "Average \u2b06\ufe0f": 53.56, + "ARC": 56.31, + "HellaSwag": 79.14, + "MMLU": 52.71, + "TruthfulQA": 50.19, + "Winogrande": 75.22, + "GSM8K": 7.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "e501f231277671710384ba0397da2c4486865958", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "stabilityai\/StableBeluga-7B", + "Average \u2b06\ufe0f": 53.56, + "ARC": 56.31, + "HellaSwag": 79.14, + "MMLU": 52.71, + "TruthfulQA": 50.19, + "Winogrande": 75.22, + "GSM8K": 7.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 128.0, + "Available on the hub": false, + "Model sha": "329adcfc39f48dce183eb0b155b732dbe03c6304", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ericpolewski\/TacoBeLLM", + "Average \u2b06\ufe0f": 53.56, + "ARC": 58.53, + "HellaSwag": 81.9, + "MMLU": 56.97, + "TruthfulQA": 46.06, + "Winogrande": 76.64, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "8ae631952a2421f9c7a12e048bc9d578dfc640f1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/dolphin-llama-13b", + "Average \u2b06\ufe0f": 53.56, + "ARC": 55.55, + "HellaSwag": 77.11, + "MMLU": 52.16, + "TruthfulQA": 52.23, + "Winogrande": 69.93, + "GSM8K": 14.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b6d16c3e1cffef5e914863f41fd96152dafddd6f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "google\/gemma-7b-it", + "Average \u2b06\ufe0f": 53.56, + "ARC": 51.45, + "HellaSwag": 71.96, + "MMLU": 53.52, + "TruthfulQA": 47.29, + "Winogrande": 67.96, + "GSM8K": 29.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 724.0, + "Available on the hub": true, + "Model sha": "dec4b13d574762bd36f0a1b75541439bd852b2e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/oasst-llama-13b-2-epochs", + "Average \u2b06\ufe0f": 53.55, + "ARC": 57.94, + "HellaSwag": 82.4, + "MMLU": 48.56, + "TruthfulQA": 47.27, + "Winogrande": 76.87, + "GSM8K": 8.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": false, + "Model sha": "0e3796192f7edf43968541b9454ea35da4a2b1c5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/guanaco-13B-HF", + "Average \u2b06\ufe0f": 53.54, + "ARC": 57.85, + "HellaSwag": 83.84, + "MMLU": 48.28, + "TruthfulQA": 46.73, + "Winogrande": 75.85, + "GSM8K": 8.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "bd59c700815124df616a17f5b49a0bc51590b231", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lajonbot\/tableBeluga-7B-instruct-pl-lora_unload", + "Average \u2b06\ufe0f": 53.54, + "ARC": 56.23, + "HellaSwag": 79.12, + "MMLU": 52.7, + "TruthfulQA": 50.19, + "Winogrande": 75.22, + "GSM8K": 7.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "eeb22ca9481a5ed7e131a329324494f234300a45", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Aabbhishekk\/llama2-7b-function-calling-slerp", + "Average \u2b06\ufe0f": 53.53, + "ARC": 55.46, + "HellaSwag": 79.5, + "MMLU": 50.32, + "TruthfulQA": 40.32, + "Winogrande": 75.22, + "GSM8K": 20.39, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "41e714527afd7d502e853092286c332f69b37c15", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chargoddard\/llama2-22b-blocktriangular", + "Average \u2b06\ufe0f": 53.53, + "ARC": 58.53, + "HellaSwag": 82.59, + "MMLU": 54.64, + "TruthfulQA": 39.3, + "Winogrande": 76.32, + "GSM8K": 9.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 22.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "40a51343ae776b5cb39f2b4343ae8f9b676ffd58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "s3nh\/poorx32124", + "Average \u2b06\ufe0f": 53.53, + "ARC": 53.16, + "HellaSwag": 73.58, + "MMLU": 52.88, + "TruthfulQA": 50.26, + "Winogrande": 69.38, + "GSM8K": 21.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6062703b527da6fa7ede85ba17a5fba20524c042", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-llama-13b", + "Average \u2b06\ufe0f": 53.53, + "ARC": 58.96, + "HellaSwag": 79.71, + "MMLU": 49.1, + "TruthfulQA": 49.59, + "Winogrande": 75.61, + "GSM8K": 8.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "dd326f89ce885844d714d9ab33603e0d17f56cc5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-Open_Platypus_and_ccp_2.6w", + "Average \u2b06\ufe0f": 53.52, + "ARC": 58.96, + "HellaSwag": 82.51, + "MMLU": 56.12, + "TruthfulQA": 40.07, + "Winogrande": 76.64, + "GSM8K": 6.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2929bfa1049db46df94f5710755178d18a981665", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r16-gate_up_down", + "Average \u2b06\ufe0f": 53.52, + "ARC": 55.03, + "HellaSwag": 81.97, + "MMLU": 56.64, + "TruthfulQA": 38.07, + "Winogrande": 77.19, + "GSM8K": 12.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "555486843f613276b6edb480f6d37b9203daa226", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "budecosystem\/code-millenials-34b", + "Average \u2b06\ufe0f": 53.51, + "ARC": 49.83, + "HellaSwag": 75.09, + "MMLU": 49.28, + "TruthfulQA": 45.37, + "Winogrande": 69.06, + "GSM8K": 32.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "fdb4dc33b18c884e51f9d8258f192b4ed0f93dc3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Inv\/MoECPM-Untrained-4x2b", + "Average \u2b06\ufe0f": 53.51, + "ARC": 46.76, + "HellaSwag": 72.58, + "MMLU": 53.21, + "TruthfulQA": 38.41, + "Winogrande": 65.51, + "GSM8K": 44.58, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.79, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c7d5d78d4d938d772fe22c7302a8312a40a20645", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "IGeniusDev\/llama13B-quant8-testv1-openorca-customdataset", + "Average \u2b06\ufe0f": 53.5, + "ARC": 60.49, + "HellaSwag": 82.97, + "MMLU": 54.44, + "TruthfulQA": 37.34, + "Winogrande": 75.69, + "GSM8K": 10.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f364d000bedac80e72aa103c08b77aee1b61b7da", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bofenghuang\/vigogne-13b-chat", + "Average \u2b06\ufe0f": 53.5, + "ARC": 58.62, + "HellaSwag": 80.85, + "MMLU": 47.76, + "TruthfulQA": 48.73, + "Winogrande": 76.72, + "GSM8K": 8.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "27002e974774c3599e6a4d731dd44e68b9e41f92", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-mistral-7b-v13", + "Average \u2b06\ufe0f": 53.5, + "ARC": 52.3, + "HellaSwag": 75.09, + "MMLU": 56.34, + "TruthfulQA": 50.81, + "Winogrande": 71.74, + "GSM8K": 14.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "e6c4cc00e1bb2aa2082c2b8fd93c949aa36ce300", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-llama-13b-v1.2", + "Average \u2b06\ufe0f": 53.49, + "ARC": 56.74, + "HellaSwag": 80.34, + "MMLU": 48.9, + "TruthfulQA": 51.0, + "Winogrande": 75.93, + "GSM8K": 8.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "c0a56d9f5a15bea07493191b5a6295f6797a9b2c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r4-gate_up_down", + "Average \u2b06\ufe0f": 53.48, + "ARC": 55.8, + "HellaSwag": 81.74, + "MMLU": 55.09, + "TruthfulQA": 39.12, + "Winogrande": 76.32, + "GSM8K": 12.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "aefc3a122cb054b070a212d1127600775aded4be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/orca_mini_v3_7b", + "Average \u2b06\ufe0f": 53.47, + "ARC": 56.91, + "HellaSwag": 79.64, + "MMLU": 52.37, + "TruthfulQA": 50.51, + "Winogrande": 74.27, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1583d2f02041fb37df28eeae4da644d8dff33eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "pankajmathur\/orca_mini_v3_7b", + "Average \u2b06\ufe0f": 53.47, + "ARC": 56.91, + "HellaSwag": 79.64, + "MMLU": 52.37, + "TruthfulQA": 50.51, + "Winogrande": 74.27, + "GSM8K": 7.13, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 40.0, + "Available on the hub": true, + "Model sha": "f9849ea6bf0f6ebb78dca1cea1c7a3ef8f7d715c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mncai\/Llama2-7B-guanaco-dolphin-500", + "Average \u2b06\ufe0f": 53.47, + "ARC": 56.74, + "HellaSwag": 81.62, + "MMLU": 48.68, + "TruthfulQA": 46.93, + "Winogrande": 74.11, + "GSM8K": 12.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "afe00170f084f773e401ba7d738d692533cca6b4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-llama2-13b-chat", + "Average \u2b06\ufe0f": 53.46, + "ARC": 57.51, + "HellaSwag": 77.94, + "MMLU": 52.56, + "TruthfulQA": 48.18, + "Winogrande": 74.74, + "GSM8K": 9.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "9497e3bd12e19e1300bc7b1980fbe232420134b9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE5_4w-r16-gate_up_down", + "Average \u2b06\ufe0f": 53.44, + "ARC": 55.8, + "HellaSwag": 82.1, + "MMLU": 55.33, + "TruthfulQA": 39.82, + "Winogrande": 76.24, + "GSM8K": 11.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "86f255afabc8986c73376cafd98628a068649022", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE3_3.3w-r8-q_k_v_o_gate_up_down", + "Average \u2b06\ufe0f": 53.43, + "ARC": 57.94, + "HellaSwag": 81.19, + "MMLU": 53.43, + "TruthfulQA": 40.48, + "Winogrande": 76.72, + "GSM8K": 10.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "15f1b122d60631091419cb8e668a28737b92a0e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "TigerResearch\/tigerbot-13b-base", + "Average \u2b06\ufe0f": 53.42, + "ARC": 53.84, + "HellaSwag": 77.05, + "MMLU": 53.57, + "TruthfulQA": 44.06, + "Winogrande": 74.98, + "GSM8K": 17.06, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2df5ed76be7eff0962f2d816a64eca1e78e1cbf3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/zarafusionex-1.1-l2-7b", + "Average \u2b06\ufe0f": 53.41, + "ARC": 56.14, + "HellaSwag": 79.34, + "MMLU": 52.1, + "TruthfulQA": 50.66, + "Winogrande": 74.43, + "GSM8K": 7.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "3268ff5291934a14f3f5e7013bbb408f33adb542", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "quantumaikr\/QuantumLM", + "Average \u2b06\ufe0f": 53.41, + "ARC": 55.8, + "HellaSwag": 79.74, + "MMLU": 54.17, + "TruthfulQA": 46.71, + "Winogrande": 74.19, + "GSM8K": 9.86, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9058130b416355b37f5f78777748aa56d98a4da0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/samantha-mistral-instruct-7b", + "Average \u2b06\ufe0f": 53.4, + "ARC": 53.5, + "HellaSwag": 75.14, + "MMLU": 51.72, + "TruthfulQA": 58.81, + "Winogrande": 70.4, + "GSM8K": 10.84, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3a33eea0858d411617c472c3c0ae39f17d2b3f5d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mosaicml\/mpt-30b-instruct", + "Average \u2b06\ufe0f": 53.4, + "ARC": 58.45, + "HellaSwag": 84.31, + "MMLU": 49.15, + "TruthfulQA": 38.05, + "Winogrande": 75.14, + "GSM8K": 15.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 96.0, + "Available on the hub": false, + "Model sha": "2abf1163dd8c9b11f07d805c06e6ec90a1f2037e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aeala\/GPT4-x-Alpasta-13b", + "Average \u2b06\ufe0f": 53.38, + "ARC": 58.53, + "HellaSwag": 79.92, + "MMLU": 46.03, + "TruthfulQA": 53.06, + "Winogrande": 73.95, + "GSM8K": 8.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "50af05b015446110a2dc52a1b4b341142c98e62b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE5_4w-r4-q_k_v_o_gate_up_down", + "Average \u2b06\ufe0f": 53.38, + "ARC": 55.89, + "HellaSwag": 81.38, + "MMLU": 53.77, + "TruthfulQA": 40.25, + "Winogrande": 76.72, + "GSM8K": 12.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a8b15badead658df6ec5b884b813962b9fd29cfb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "NobodyExistsOnTheInternet\/GiftedConvo13bLoraNoEcons", + "Average \u2b06\ufe0f": 53.35, + "ARC": 59.39, + "HellaSwag": 83.19, + "MMLU": 55.15, + "TruthfulQA": 40.56, + "Winogrande": 74.03, + "GSM8K": 7.81, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9d7031e7d956dd2d25c61d85f594d115ce65b172", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE3_3.3w-r4-gate_up_down", + "Average \u2b06\ufe0f": 53.35, + "ARC": 56.4, + "HellaSwag": 81.93, + "MMLU": 53.63, + "TruthfulQA": 39.23, + "Winogrande": 76.95, + "GSM8K": 11.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dd61a482fa2f71efe6f22aae6949355ca4b06ccc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-13b-2.1", + "Average \u2b06\ufe0f": 53.34, + "ARC": 59.47, + "HellaSwag": 82.47, + "MMLU": 54.83, + "TruthfulQA": 44.65, + "Winogrande": 75.06, + "GSM8K": 3.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "172e30e56e939f73d7d00a165c2d49cbd284481f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE5_4w-r4-q_k_v_o", + "Average \u2b06\ufe0f": 53.32, + "ARC": 58.36, + "HellaSwag": 81.1, + "MMLU": 54.53, + "TruthfulQA": 37.02, + "Winogrande": 76.64, + "GSM8K": 12.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5cbcd9c0a6b9a19f0d099e653cde18e11bf95303", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/vicuna-13b-v1.3.0-GPTQ", + "Average \u2b06\ufe0f": 53.29, + "ARC": 54.35, + "HellaSwag": 79.47, + "MMLU": 51.97, + "TruthfulQA": 50.88, + "Winogrande": 74.66, + "GSM8K": 8.42, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "6ef1f8d8638ea2d6681a8e3da73be57c501d847b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pillowtalks-ai\/delta13b", + "Average \u2b06\ufe0f": 53.29, + "ARC": 52.73, + "HellaSwag": 80.13, + "MMLU": 51.94, + "TruthfulQA": 52.08, + "Winogrande": 74.19, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "83fa0860990df1db35550f973ba4306449e35412", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/vicuna-13B-1.1-HF", + "Average \u2b06\ufe0f": 53.29, + "ARC": 52.73, + "HellaSwag": 80.13, + "MMLU": 51.94, + "TruthfulQA": 52.08, + "Winogrande": 74.19, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8c71dbe9221e83d2ec72e4dc08beccfc78b563c0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eachadea\/vicuna-13b-1.1", + "Average \u2b06\ufe0f": 53.29, + "ARC": 52.73, + "HellaSwag": 80.13, + "MMLU": 51.94, + "TruthfulQA": 52.08, + "Winogrande": 74.19, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 136.0, + "Available on the hub": true, + "Model sha": "bfcc6ca66694310be6c85ba0638597f4256c4143", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kevinpro\/Vicuna-13B-CoT", + "Average \u2b06\ufe0f": 53.29, + "ARC": 52.73, + "HellaSwag": 80.13, + "MMLU": 51.94, + "TruthfulQA": 52.08, + "Winogrande": 74.19, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "346e3c46959cf9f1e03feffa761afe020c0fb6a8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Vicuna-13B-CoT-fp16", + "Average \u2b06\ufe0f": 53.28, + "ARC": 52.73, + "HellaSwag": 80.14, + "MMLU": 51.9, + "TruthfulQA": 52.08, + "Winogrande": 74.19, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "fe74a0ece9089828b301bd0f067ae5f257516179", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-13b-delta-v1.1", + "Average \u2b06\ufe0f": 53.28, + "ARC": 52.73, + "HellaSwag": 80.14, + "MMLU": 51.9, + "TruthfulQA": 52.08, + "Winogrande": 74.19, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 409.0, + "Available on the hub": false, + "Model sha": "ffed4c7cf1b9814812078efbe29ec3f610ea39e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-13b-v1.1", + "Average \u2b06\ufe0f": 53.28, + "ARC": 52.73, + "HellaSwag": 80.14, + "MMLU": 51.9, + "TruthfulQA": 52.08, + "Winogrande": 74.19, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 97.0, + "Available on the hub": false, + "Model sha": "8c71dbe9221e83d2ec72e4dc08beccfc78b563c0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Llama-2-13B-GPTQ", + "Average \u2b06\ufe0f": 53.26, + "ARC": 59.13, + "HellaSwag": 81.48, + "MMLU": 54.45, + "TruthfulQA": 37.07, + "Winogrande": 76.16, + "GSM8K": 11.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 16.23, + "Hub \u2764\ufe0f": 114.0, + "Available on the hub": true, + "Model sha": "b7db471d1789802a3a8e3b93cdd66a9f046f17c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AdaptLLM\/finance-chat", + "Average \u2b06\ufe0f": 53.26, + "ARC": 53.75, + "HellaSwag": 76.6, + "MMLU": 50.16, + "TruthfulQA": 44.54, + "Winogrande": 75.69, + "GSM8K": 18.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 40.0, + "Available on the hub": true, + "Model sha": "42d449dc4f42960a52130893843136ab3fed1256", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/MiniCPM-2B-Base-v2", + "Average \u2b06\ufe0f": 53.24, + "ARC": 45.99, + "HellaSwag": 72.22, + "MMLU": 52.63, + "TruthfulQA": 40.27, + "Winogrande": 66.38, + "GSM8K": 41.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c9865131d0c5a530d04b9aa3f2d678ee6fbc8cb9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/MiniCPM-2B-Base-v3", + "Average \u2b06\ufe0f": 53.24, + "ARC": 47.01, + "HellaSwag": 73.12, + "MMLU": 52.42, + "TruthfulQA": 41.82, + "Winogrande": 66.14, + "GSM8K": 38.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "114ef55021443ac68a51fc131156a5796e72541d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r4-q_k_v_o_gate_up_down", + "Average \u2b06\ufe0f": 53.23, + "ARC": 56.31, + "HellaSwag": 81.43, + "MMLU": 55.3, + "TruthfulQA": 39.11, + "Winogrande": 76.8, + "GSM8K": 10.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0d8d502e4e5ef89592dd0d3bc7223eaf7f77f78b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/airoboros-2.1-llama-2-13B-QLoRa", + "Average \u2b06\ufe0f": 53.23, + "ARC": 59.73, + "HellaSwag": 82.91, + "MMLU": 54.77, + "TruthfulQA": 45.14, + "Winogrande": 74.03, + "GSM8K": 2.81, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ebf991c8d34314caab6ccc6b078c681d20bac39a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/Mistral-7B-loss-100000", + "Average \u2b06\ufe0f": 53.22, + "ARC": 51.79, + "HellaSwag": 77.16, + "MMLU": 53.94, + "TruthfulQA": 40.93, + "Winogrande": 76.95, + "GSM8K": 18.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b29a345c5dd34e4e198fa19814c1538da17512c5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Severus27\/BeingWell_llama2_7b", + "Average \u2b06\ufe0f": 53.22, + "ARC": 54.95, + "HellaSwag": 78.27, + "MMLU": 47.46, + "TruthfulQA": 45.93, + "Winogrande": 74.19, + "GSM8K": 18.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "d1d27f8f822d083cfb018e9550784a29d97b51a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/Medtulu-2x7b", + "Average \u2b06\ufe0f": 53.21, + "ARC": 54.61, + "HellaSwag": 75.68, + "MMLU": 49.12, + "TruthfulQA": 50.04, + "Winogrande": 72.85, + "GSM8K": 16.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 11.07, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "76a032af4d8eec7cd9b621c887cdfaa5d99b4cd9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-13b_10e5_r2_a256", + "Average \u2b06\ufe0f": 53.2, + "ARC": 58.02, + "HellaSwag": 80.99, + "MMLU": 52.71, + "TruthfulQA": 36.36, + "Winogrande": 74.74, + "GSM8K": 16.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d897ec2c64828ddf05ca0f51c4839a34060b2cef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE2_TEST_2.2w", + "Average \u2b06\ufe0f": 53.2, + "ARC": 56.23, + "HellaSwag": 82.7, + "MMLU": 55.35, + "TruthfulQA": 39.55, + "Winogrande": 76.72, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3be177b35f1b44d147751ab38ca6d8a008eb6b7f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "meta-math\/MetaMath-Llemma-7B", + "Average \u2b06\ufe0f": 53.19, + "ARC": 46.5, + "HellaSwag": 61.69, + "MMLU": 47.66, + "TruthfulQA": 39.61, + "Winogrande": 62.75, + "GSM8K": 60.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "e31ec61dccd8fa24f44f0592a518491ef76a2235", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r4-q_k_v_o", + "Average \u2b06\ufe0f": 53.18, + "ARC": 54.78, + "HellaSwag": 81.4, + "MMLU": 54.73, + "TruthfulQA": 41.02, + "Winogrande": 76.64, + "GSM8K": 10.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8702b433008a62e9f8bf15e70ba15fa7100e991c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pharaouk\/fusedyi", + "Average \u2b06\ufe0f": 53.18, + "ARC": 55.03, + "HellaSwag": 76.6, + "MMLU": 63.43, + "TruthfulQA": 49.29, + "Winogrande": 72.69, + "GSM8K": 2.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.91, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5e3fdfa75a3bebd5d18d25e3bada1da27f200fd6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/zarafusionix-l2-7b", + "Average \u2b06\ufe0f": 53.18, + "ARC": 55.55, + "HellaSwag": 79.4, + "MMLU": 51.21, + "TruthfulQA": 51.05, + "Winogrande": 74.66, + "GSM8K": 7.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "13d0e2498a4b5f53f6dc2464f20e093b07a4bd4b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/WizardLM-13B-V1-1-SuperHOT-8K-fp16", + "Average \u2b06\ufe0f": 53.16, + "ARC": 58.62, + "HellaSwag": 81.07, + "MMLU": 48.32, + "TruthfulQA": 54.19, + "Winogrande": 76.01, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "83905656ca3e63877b8d9f3a74118da0c9bc6939", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Athena-Platypus2-13B-QLora-0.80-epoch", + "Average \u2b06\ufe0f": 53.16, + "ARC": 56.66, + "HellaSwag": 80.56, + "MMLU": 55.43, + "TruthfulQA": 53.62, + "Winogrande": 72.61, + "GSM8K": 0.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f7b6c11b4df16079dfdd1e8dd8c489a8835c7cc4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Airboros2.1-Platypus2-13B-QLora-0.80-epoch", + "Average \u2b06\ufe0f": 53.15, + "ARC": 58.96, + "HellaSwag": 82.46, + "MMLU": 54.62, + "TruthfulQA": 47.71, + "Winogrande": 75.14, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "45bd1e47218ba2e075e03f6407980eb839e67eb3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Enno-Ai\/vigogne2-enno-13b-sft-lora-4bit", + "Average \u2b06\ufe0f": 53.15, + "ARC": 62.03, + "HellaSwag": 82.65, + "MMLU": 54.11, + "TruthfulQA": 42.98, + "Winogrande": 76.95, + "GSM8K": 0.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2a1b03977395eee44742abda63a4787ea5371d06", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Airoboros-L2-13B-2.1-GPTQ", + "Average \u2b06\ufe0f": 53.14, + "ARC": 58.96, + "HellaSwag": 81.72, + "MMLU": 53.16, + "TruthfulQA": 44.68, + "Winogrande": 74.35, + "GSM8K": 5.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 16.23, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "d90d96e40b9359cb5c35e6b6c8f0eb24896e827b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/Llama-2-13b-hf-ds_wiki_1024_full_r_64_alpha_16", + "Average \u2b06\ufe0f": 53.14, + "ARC": 59.04, + "HellaSwag": 82.33, + "MMLU": 55.36, + "TruthfulQA": 35.75, + "Winogrande": 76.32, + "GSM8K": 10.01, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a3ed7416156963f49bf4dc056188e006c0c214d2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/llama-13b-pretrained-sft-do2", + "Average \u2b06\ufe0f": 53.12, + "ARC": 58.96, + "HellaSwag": 80.32, + "MMLU": 47.25, + "TruthfulQA": 47.41, + "Winogrande": 75.53, + "GSM8K": 9.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "6cb016f5bfcbc24ee08312b52f08ef5e8f860871", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/MLewd-L2-13B", + "Average \u2b06\ufe0f": 53.12, + "ARC": 58.28, + "HellaSwag": 82.32, + "MMLU": 54.67, + "TruthfulQA": 48.66, + "Winogrande": 73.48, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "feb1fa71e0b24261d3ca428b4aed881dd31f166e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jjaaaww\/posi_13b", + "Average \u2b06\ufe0f": 53.12, + "ARC": 59.64, + "HellaSwag": 82.52, + "MMLU": 56.56, + "TruthfulQA": 42.14, + "Winogrande": 76.24, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ff4eeb0f876c41553c302020041a0e78a15f9aa7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/llama-13b-pretrained-sft-epoch-1", + "Average \u2b06\ufe0f": 53.11, + "ARC": 57.25, + "HellaSwag": 79.99, + "MMLU": 45.52, + "TruthfulQA": 44.45, + "Winogrande": 77.58, + "GSM8K": 13.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1f839c019153789c15bbc45ecbb512d0f5015881", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/manticore-13b-chat-pyg-GPTQ", + "Average \u2b06\ufe0f": 53.11, + "ARC": 57.85, + "HellaSwag": 81.07, + "MMLU": 47.56, + "TruthfulQA": 47.77, + "Winogrande": 75.93, + "GSM8K": 8.49, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 32.0, + "Available on the hub": true, + "Model sha": "923f27245d13058c9c1b3ab0eab6c6c93ffc162e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "genaicore3434\/MistralLite-summ-sft-e1", + "Average \u2b06\ufe0f": 53.11, + "ARC": 59.56, + "HellaSwag": 81.42, + "MMLU": 52.34, + "TruthfulQA": 41.79, + "Winogrande": 77.11, + "GSM8K": 6.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f8d5d904ff6bd07e59d6fcf484dc71986f856825", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "itsliupeng\/llama2_7b_mmlu", + "Average \u2b06\ufe0f": 53.1, + "ARC": 56.14, + "HellaSwag": 79.13, + "MMLU": 60.04, + "TruthfulQA": 40.95, + "Winogrande": 74.43, + "GSM8K": 7.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "553178f8d5d69eb1dfa5b9503d2ce0c1e481e5b1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/llama2-13b-FINETUNE3_TEST", + "Average \u2b06\ufe0f": 53.09, + "ARC": 53.67, + "HellaSwag": 79.66, + "MMLU": 54.48, + "TruthfulQA": 40.22, + "Winogrande": 75.93, + "GSM8K": 14.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "22cea7bf138eb0d6c962812df2b2235290acbee2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Cartinoe5930\/TIES-Merging", + "Average \u2b06\ufe0f": 53.08, + "ARC": 58.11, + "HellaSwag": 75.74, + "MMLU": 51.57, + "TruthfulQA": 41.25, + "Winogrande": 72.38, + "GSM8K": 19.41, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eb4d42de1ed4407e83660f2ab03139c1fd03ac02", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE3_3.3w-r4-q_k_v_o_gate_up_down", + "Average \u2b06\ufe0f": 53.06, + "ARC": 57.76, + "HellaSwag": 80.78, + "MMLU": 54.32, + "TruthfulQA": 40.8, + "Winogrande": 76.72, + "GSM8K": 7.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ebe1b75fa315a9b55f686368070a0bcd0245ee39", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/FINETUNE3_TEST4", + "Average \u2b06\ufe0f": 53.02, + "ARC": 55.63, + "HellaSwag": 81.31, + "MMLU": 52.13, + "TruthfulQA": 41.14, + "Winogrande": 76.72, + "GSM8K": 11.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5195e87bb34317c5aaf201faa476aae78ecc9f1b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Open-Orca\/LlongOrca-7B-16k", + "Average \u2b06\ufe0f": 53.02, + "ARC": 57.51, + "HellaSwag": 79.44, + "MMLU": 49.35, + "TruthfulQA": 49.84, + "Winogrande": 74.51, + "GSM8K": 7.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "1370c7c595e6c8394e6332bc535ae25e21def85b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/google-gemma-7b-it-dpo-v1", + "Average \u2b06\ufe0f": 53.02, + "ARC": 51.54, + "HellaSwag": 71.58, + "MMLU": 53.24, + "TruthfulQA": 46.85, + "Winogrande": 67.25, + "GSM8K": 27.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3d6f29fb83a38b1ec0fbfb69af1b345ac657f7cb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-13b-gpt4-1.4.1", + "Average \u2b06\ufe0f": 53.02, + "ARC": 59.13, + "HellaSwag": 82.78, + "MMLU": 55.62, + "TruthfulQA": 40.27, + "Winogrande": 73.32, + "GSM8K": 6.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "35ff51ebe5668269dfd33a9ed94412d88f1f4b65", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Walter-Mistral-7B", + "Average \u2b06\ufe0f": 53.0, + "ARC": 58.87, + "HellaSwag": 83.43, + "MMLU": 58.65, + "TruthfulQA": 39.93, + "Winogrande": 77.03, + "GSM8K": 0.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d7ccd4f0360c397765578521efaed394fe00dbf5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/llama-13b-pretrained-dropout", + "Average \u2b06\ufe0f": 52.99, + "ARC": 56.4, + "HellaSwag": 79.34, + "MMLU": 46.59, + "TruthfulQA": 48.6, + "Winogrande": 75.22, + "GSM8K": 11.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "045c84727d495bfb4b612a2482ce0d807c067b46", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AdaptLLM\/medicine-chat", + "Average \u2b06\ufe0f": 52.99, + "ARC": 53.75, + "HellaSwag": 76.11, + "MMLU": 49.98, + "TruthfulQA": 43.46, + "Winogrande": 75.69, + "GSM8K": 18.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "32824ba93e88ccfe8464f6d267a5d67024c7722b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "The-Face-Of-Goonery\/Huginn-19b-prototype", + "Average \u2b06\ufe0f": 52.99, + "ARC": 59.22, + "HellaSwag": 81.03, + "MMLU": 55.73, + "TruthfulQA": 41.15, + "Winogrande": 76.4, + "GSM8K": 4.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 19.36, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "d2c8cc15c57da217ff29ebaaae4bc4f57d6b21b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "heegyu\/LIMA2-13b-hf", + "Average \u2b06\ufe0f": 52.98, + "ARC": 60.24, + "HellaSwag": 83.69, + "MMLU": 53.17, + "TruthfulQA": 41.81, + "Winogrande": 73.24, + "GSM8K": 5.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ed3535921eb24e0737f9a6cda70b1a3fd71532cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xzuyn\/Alpacino-SuperCOT-13B", + "Average \u2b06\ufe0f": 52.97, + "ARC": 58.36, + "HellaSwag": 81.69, + "MMLU": 47.89, + "TruthfulQA": 45.42, + "Winogrande": 76.95, + "GSM8K": 7.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "3a82b04684fe99d59556421c3f96a187049a3cec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Code-290k-13B", + "Average \u2b06\ufe0f": 52.96, + "ARC": 56.06, + "HellaSwag": 81.55, + "MMLU": 51.99, + "TruthfulQA": 37.65, + "Winogrande": 72.69, + "GSM8K": 17.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "e2595df2aedc1decaf73d167ce0114e7a9cb2126", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "allenai\/digital-socrates-7b", + "Average \u2b06\ufe0f": 52.95, + "ARC": 54.44, + "HellaSwag": 75.99, + "MMLU": 51.41, + "TruthfulQA": 44.88, + "Winogrande": 73.09, + "GSM8K": 17.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "5d26db18b95778c31dc8425871052f495b267563", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/zaraxe-l2-7b", + "Average \u2b06\ufe0f": 52.95, + "ARC": 57.17, + "HellaSwag": 79.34, + "MMLU": 51.0, + "TruthfulQA": 49.11, + "Winogrande": 73.48, + "GSM8K": 7.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0875bf202aedeef7a58d7382fd6f55f5bca12968", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sethuiyer\/Dr_Samantha-7b", + "Average \u2b06\ufe0f": 52.95, + "ARC": 53.84, + "HellaSwag": 77.95, + "MMLU": 47.94, + "TruthfulQA": 45.58, + "Winogrande": 73.56, + "GSM8K": 18.8, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "b1a643e32e467d8dd722186d6c36d16ea4281003", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/Llama-2-13b-hf-ds_wiki_1024_full_r_64_alpha_16_merged", + "Average \u2b06\ufe0f": 52.94, + "ARC": 58.45, + "HellaSwag": 81.97, + "MMLU": 55.02, + "TruthfulQA": 35.85, + "Winogrande": 75.69, + "GSM8K": 10.69, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5a89844b1aea3f0573e696143ec66727df4b5d79", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "project-baize\/baize-v2-13b", + "Average \u2b06\ufe0f": 52.94, + "ARC": 56.91, + "HellaSwag": 79.29, + "MMLU": 49.72, + "TruthfulQA": 47.88, + "Winogrande": 74.9, + "GSM8K": 8.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "a3c4bbccca8b650700a49a225582c17bb49b446b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/MultiLoRA-mmlu", + "Average \u2b06\ufe0f": 52.93, + "ARC": 52.39, + "HellaSwag": 77.21, + "MMLU": 49.73, + "TruthfulQA": 50.2, + "Winogrande": 72.22, + "GSM8K": 15.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4797aeaa428a56712db1ab611bc11f02019c4a2c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-llama2-13b-v11-bf16", + "Average \u2b06\ufe0f": 52.93, + "ARC": 52.99, + "HellaSwag": 75.38, + "MMLU": 51.36, + "TruthfulQA": 47.94, + "Winogrande": 71.03, + "GSM8K": 18.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "4d4e72c553e9d60fdc208663b0a1c0364caa2f30", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Korabbit\/Llama-2-7b-chat-hf-afr-100step-flan-v2", + "Average \u2b06\ufe0f": 52.92, + "ARC": 53.24, + "HellaSwag": 78.43, + "MMLU": 48.43, + "TruthfulQA": 45.66, + "Winogrande": 72.3, + "GSM8K": 19.48, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0f1873b505a5f32ca429c164a229bab663eaf617", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NLUHOPOE\/Mistral-7B-random-100000", + "Average \u2b06\ufe0f": 52.92, + "ARC": 53.75, + "HellaSwag": 78.6, + "MMLU": 53.41, + "TruthfulQA": 43.16, + "Winogrande": 75.61, + "GSM8K": 12.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2059c4f8e796467b35a2bf28df46cf4b99f1a89f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "BioMistral\/BioMistral-7B-TIES", + "Average \u2b06\ufe0f": 52.91, + "ARC": 55.46, + "HellaSwag": 79.59, + "MMLU": 56.29, + "TruthfulQA": 52.2, + "Winogrande": 73.72, + "GSM8K": 0.23, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "143f0ab48dc2bd35cce0973826cd9d5d549c2fab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nkpz\/llama2-22b-chat-wizard-uncensored", + "Average \u2b06\ufe0f": 52.9, + "ARC": 56.23, + "HellaSwag": 80.39, + "MMLU": 53.62, + "TruthfulQA": 45.76, + "Winogrande": 70.24, + "GSM8K": 11.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 21.83, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "90cffebc8f530161505b84740ff6c8f646299d6c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "pe-nlp\/llama-2-13b-platypus-vicuna-wizard", + "Average \u2b06\ufe0f": 52.9, + "ARC": 61.26, + "HellaSwag": 82.31, + "MMLU": 55.21, + "TruthfulQA": 41.91, + "Winogrande": 75.77, + "GSM8K": 0.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "71aa919fc15fa9d9def9185791b15a3f76e7bd8d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "clibrain\/Llama-2-13b-ft-instruct-es", + "Average \u2b06\ufe0f": 52.89, + "ARC": 59.39, + "HellaSwag": 81.51, + "MMLU": 54.31, + "TruthfulQA": 37.81, + "Winogrande": 75.77, + "GSM8K": 8.57, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "772b53f64f484fa0d651d453bcefc35a0f52f251", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AdaptLLM\/law-chat", + "Average \u2b06\ufe0f": 52.88, + "ARC": 53.41, + "HellaSwag": 76.16, + "MMLU": 50.24, + "TruthfulQA": 43.53, + "Winogrande": 75.45, + "GSM8K": 18.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "0bf36fdc22bf30632cced8044667d3d46061d619", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wei123602\/llama2-13b-fintune2-4E", + "Average \u2b06\ufe0f": 52.88, + "ARC": 55.89, + "HellaSwag": 80.95, + "MMLU": 53.73, + "TruthfulQA": 42.72, + "Winogrande": 73.09, + "GSM8K": 10.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "645ede9d6ec60d8fa051bc7ad32ab5f7bfdc066d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Korabbit\/Llama-2-7b-chat-hf-afr-100step-flan", + "Average \u2b06\ufe0f": 52.88, + "ARC": 52.9, + "HellaSwag": 78.44, + "MMLU": 48.4, + "TruthfulQA": 45.67, + "Winogrande": 72.38, + "GSM8K": 19.48, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1d502ae9a15c38118baa5ae55e048a080cb05c89", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CHIH-HUNG\/llama-2-13b-FINETUNE4_3.8w-r8-q_k_v_o_gate_up_down", + "Average \u2b06\ufe0f": 52.88, + "ARC": 55.97, + "HellaSwag": 81.53, + "MMLU": 54.42, + "TruthfulQA": 40.72, + "Winogrande": 75.06, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "905fc0b26dcb9e1fc5be99e73596e0884f9b71df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ContextualAI\/archangel_sft-kto_llama13b", + "Average \u2b06\ufe0f": 52.87, + "ARC": 56.14, + "HellaSwag": 80.8, + "MMLU": 47.84, + "TruthfulQA": 39.42, + "Winogrande": 76.16, + "GSM8K": 16.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d596fb0060168006360610d673c2c35edcbbf110", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Yhyu13\/chimera-inst-chat-13b-hf", + "Average \u2b06\ufe0f": 52.86, + "ARC": 55.38, + "HellaSwag": 78.93, + "MMLU": 50.6, + "TruthfulQA": 50.12, + "Winogrande": 73.95, + "GSM8K": 8.19, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "a6943d2d30d0af904b3321559157d589e60f9e0f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Telugu-LLM-Labs\/Telugu-Llama2-7B-v0-Instruct", + "Average \u2b06\ufe0f": 52.86, + "ARC": 53.58, + "HellaSwag": 78.33, + "MMLU": 47.63, + "TruthfulQA": 43.26, + "Winogrande": 73.95, + "GSM8K": 20.39, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "b8e2895810d82fb82a811f452b2e53fef949718c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "stabilityai\/japanese-stablelm-instruct-gamma-7b", + "Average \u2b06\ufe0f": 52.82, + "ARC": 50.68, + "HellaSwag": 78.68, + "MMLU": 54.82, + "TruthfulQA": 39.77, + "Winogrande": 73.72, + "GSM8K": 19.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 41.0, + "Available on the hub": true, + "Model sha": "044918151c5b3910d12f2e489fb7c60752048e1e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "mosaicml\/mpt-30b", + "Average \u2b06\ufe0f": 52.77, + "ARC": 55.97, + "HellaSwag": 82.42, + "MMLU": 48.0, + "TruthfulQA": 38.42, + "Winogrande": 74.9, + "GSM8K": 16.91, + "Type": "pretrained", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 331.0, + "Available on the hub": false, + "Model sha": "0261af71d7177453889f868d26607dec8d5aaa2e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Llama2-13B-no_robots-alpaca-lora", + "Average \u2b06\ufe0f": 52.77, + "ARC": 58.87, + "HellaSwag": 82.43, + "MMLU": 53.11, + "TruthfulQA": 40.46, + "Winogrande": 75.3, + "GSM8K": 6.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "581aba329e607533c299746bb9eb4154a7aab139", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chargoddard\/ypotryll-22b-epoch2-qlora", + "Average \u2b06\ufe0f": 52.75, + "ARC": 59.22, + "HellaSwag": 80.66, + "MMLU": 54.52, + "TruthfulQA": 40.42, + "Winogrande": 76.32, + "GSM8K": 5.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 22.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "26fdd8fa420d72ed835c7d17086f0441db0985d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/wizard-vicuna-13B-HF", + "Average \u2b06\ufe0f": 52.75, + "ARC": 54.69, + "HellaSwag": 79.18, + "MMLU": 48.88, + "TruthfulQA": 49.62, + "Winogrande": 74.82, + "GSM8K": 9.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 48.0, + "Available on the hub": false, + "Model sha": "12dc8aacb474522ae2a83c18cb0fdf0907987f8f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/orca_mini_v2_13b", + "Average \u2b06\ufe0f": 52.75, + "ARC": 55.12, + "HellaSwag": 79.69, + "MMLU": 50.07, + "TruthfulQA": 52.56, + "Winogrande": 72.69, + "GSM8K": 6.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1058709314f7ca090937d0a2b7b37b0b3a8f12a3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Korabbit\/Llama-2-7b-chat-hf-afr-200step-flan-v2", + "Average \u2b06\ufe0f": 52.75, + "ARC": 52.65, + "HellaSwag": 78.04, + "MMLU": 48.51, + "TruthfulQA": 45.42, + "Winogrande": 72.93, + "GSM8K": 18.95, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "35e4747656b719af659625092174f188584934c1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "totally-not-an-llm\/EverythingLM-13b-V2-16k", + "Average \u2b06\ufe0f": 52.75, + "ARC": 58.7, + "HellaSwag": 80.88, + "MMLU": 49.69, + "TruthfulQA": 47.37, + "Winogrande": 73.01, + "GSM8K": 6.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": true, + "Model sha": "943f932ae1ae462389e6d2db5273158530749fff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "junelee\/wizard-vicuna-13b", + "Average \u2b06\ufe0f": 52.73, + "ARC": 54.69, + "HellaSwag": 79.18, + "MMLU": 48.88, + "TruthfulQA": 49.62, + "Winogrande": 74.82, + "GSM8K": 9.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": false, + "Model sha": "419dc5acc391de54a60d0b041e94e767d1ef2032", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elyza\/ELYZA-japanese-Llama-2-13b-fast-instruct", + "Average \u2b06\ufe0f": 52.72, + "ARC": 57.51, + "HellaSwag": 81.82, + "MMLU": 54.52, + "TruthfulQA": 43.82, + "Winogrande": 75.93, + "GSM8K": 2.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "2a0b52cd72a30d26ef0391c171b64900106a90a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openchat\/openchat_8192", + "Average \u2b06\ufe0f": 52.72, + "ARC": 59.56, + "HellaSwag": 81.44, + "MMLU": 46.26, + "TruthfulQA": 46.7, + "Winogrande": 74.98, + "GSM8K": 7.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 220.0, + "Available on the hub": false, + "Model sha": "f661da5af278fbda8a43b19ff0250e4efc103e3e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-7B-v1.2", + "Average \u2b06\ufe0f": 52.71, + "ARC": 54.35, + "HellaSwag": 79.29, + "MMLU": 49.33, + "TruthfulQA": 48.92, + "Winogrande": 73.56, + "GSM8K": 10.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "85ea4f4818478084eedd01e958ac5cc7cf64b3bb", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "PocketDoc\/Dans-PersonalityEngine-13b", + "Average \u2b06\ufe0f": 52.71, + "ARC": 58.45, + "HellaSwag": 82.3, + "MMLU": 47.58, + "TruthfulQA": 41.12, + "Winogrande": 77.51, + "GSM8K": 9.33, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "3b37c31e04419adcc91eddb57f24fd6f9ac91938", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "meta-math\/MetaMath-13B-V1.0", + "Average \u2b06\ufe0f": 52.71, + "ARC": 49.49, + "HellaSwag": 76.48, + "MMLU": 47.74, + "TruthfulQA": 41.58, + "Winogrande": 72.45, + "GSM8K": 28.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "0b448f6f64808f8bca94dc871e96a3eae7e95621", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Yehoon\/yehoon_llama2", + "Average \u2b06\ufe0f": 52.71, + "ARC": 54.78, + "HellaSwag": 78.98, + "MMLU": 51.29, + "TruthfulQA": 49.17, + "Winogrande": 74.74, + "GSM8K": 7.28, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "443cb81ce988ea6c0b1e20132c170463d559367e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/mcq-hal-vicuna-13b-v1.5", + "Average \u2b06\ufe0f": 52.7, + "ARC": 55.97, + "HellaSwag": 80.72, + "MMLU": 52.85, + "TruthfulQA": 45.03, + "Winogrande": 72.77, + "GSM8K": 8.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bb3029bce8347b09c2fd6908475b195bcabe53e3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Nous-Capybara-7B", + "Average \u2b06\ufe0f": 52.7, + "ARC": 55.29, + "HellaSwag": 80.73, + "MMLU": 48.72, + "TruthfulQA": 51.13, + "Winogrande": 73.32, + "GSM8K": 6.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "42dfc6f7d735670e2f3e30b0919708a81f9a0df9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HyperbeeAI\/Tulpar-7b-v0", + "Average \u2b06\ufe0f": 52.69, + "ARC": 56.31, + "HellaSwag": 79.01, + "MMLU": 52.55, + "TruthfulQA": 51.68, + "Winogrande": 73.88, + "GSM8K": 2.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "d7c2bc52a3ae13571357f51273ae948caf84400e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Capybara-7B", + "Average \u2b06\ufe0f": 52.69, + "ARC": 55.2, + "HellaSwag": 80.76, + "MMLU": 48.8, + "TruthfulQA": 51.07, + "Winogrande": 73.4, + "GSM8K": 6.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "42dfc6f7d735670e2f3e30b0919708a81f9a0df9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/CodeEngine", + "Average \u2b06\ufe0f": 52.68, + "ARC": 58.36, + "HellaSwag": 82.27, + "MMLU": 54.18, + "TruthfulQA": 45.18, + "Winogrande": 74.59, + "GSM8K": 1.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f57879831c39f2dcb656cb2c9e9ce5878e92bb44", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/mcq-vicuna-13b-v1.5", + "Average \u2b06\ufe0f": 52.68, + "ARC": 56.66, + "HellaSwag": 81.09, + "MMLU": 53.3, + "TruthfulQA": 43.99, + "Winogrande": 73.01, + "GSM8K": 8.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f769a92cfeffe8ee07beee8814ce7eca7cd62805", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-mixtral-8x7b-v16.1-32k", + "Average \u2b06\ufe0f": 52.68, + "ARC": 29.1, + "HellaSwag": 82.27, + "MMLU": 71.37, + "TruthfulQA": 55.97, + "Winogrande": 77.35, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "51086693792910d6bc89398200c5eca8b6930f6f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "teknium\/Mistral-Trismegistus-7B", + "Average \u2b06\ufe0f": 52.66, + "ARC": 54.1, + "HellaSwag": 77.91, + "MMLU": 54.49, + "TruthfulQA": 49.36, + "Winogrande": 70.17, + "GSM8K": 9.93, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 166.0, + "Available on the hub": true, + "Model sha": "0a5752d096ebab21759dbe203f6b7c7f6092faf2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-13b-gpt4-m2.0", + "Average \u2b06\ufe0f": 52.66, + "ARC": 59.22, + "HellaSwag": 81.02, + "MMLU": 53.73, + "TruthfulQA": 39.7, + "Winogrande": 73.64, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "a852b77f7d0777092c76898bc83f8e657ca2af3e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LeoLM\/leo-hessianai-13b", + "Average \u2b06\ufe0f": 52.65, + "ARC": 57.25, + "HellaSwag": 81.94, + "MMLU": 53.65, + "TruthfulQA": 38.03, + "Winogrande": 76.09, + "GSM8K": 8.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": false, + "Model sha": "a947965cb07ca12a38ff981fe65b618d7dea28d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Korabbit\/Llama-2-7b-chat-hf-afr-200step-flan", + "Average \u2b06\ufe0f": 52.62, + "ARC": 52.47, + "HellaSwag": 78.02, + "MMLU": 48.42, + "TruthfulQA": 45.47, + "Winogrande": 72.69, + "GSM8K": 18.65, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "03550d05aac147dde6d70b7b63f4a1661ecf5cb3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-mistral-7b-v13.1", + "Average \u2b06\ufe0f": 52.62, + "ARC": 52.56, + "HellaSwag": 75.73, + "MMLU": 56.68, + "TruthfulQA": 50.44, + "Winogrande": 71.59, + "GSM8K": 8.72, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "b64386bde3d7850a01df763f5c777c74888d34fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "heegyu\/LIMA-13b-hf", + "Average \u2b06\ufe0f": 52.61, + "ARC": 57.42, + "HellaSwag": 81.68, + "MMLU": 48.72, + "TruthfulQA": 41.76, + "Winogrande": 77.19, + "GSM8K": 8.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "98faa74a9b41cbd9033904cd58420705936849eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LinkSoul\/Chinese-Llama-2-7b", + "Average \u2b06\ufe0f": 52.59, + "ARC": 52.99, + "HellaSwag": 75.64, + "MMLU": 50.74, + "TruthfulQA": 48.94, + "Winogrande": 72.77, + "GSM8K": 14.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 297.0, + "Available on the hub": true, + "Model sha": "72efd71d7f89d9c46008b7a574faf90300ed9ba8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "stabilityai\/japanese-stablelm-base-gamma-7b", + "Average \u2b06\ufe0f": 52.59, + "ARC": 50.34, + "HellaSwag": 77.47, + "MMLU": 54.75, + "TruthfulQA": 41.2, + "Winogrande": 73.95, + "GSM8K": 17.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "e1c3840c716485077b688296fefa8e5641249843", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Locutusque\/Mistral-7B-SFT", + "Average \u2b06\ufe0f": 52.58, + "ARC": 46.5, + "HellaSwag": 75.69, + "MMLU": 51.04, + "TruthfulQA": 52.02, + "Winogrande": 72.77, + "GSM8K": 17.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "db1c291a7cbab162ebfb9512f9d27a95b42c6548", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "gmonsoon\/MiniCPM-2B-Base", + "Average \u2b06\ufe0f": 52.56, + "ARC": 46.08, + "HellaSwag": 70.52, + "MMLU": 52.61, + "TruthfulQA": 41.39, + "Winogrande": 65.9, + "GSM8K": 38.89, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cecd6b3d629a72aec5a21858ca043fa1e737522d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "indischepartij\/MiniCPM-3B-Bacchus", + "Average \u2b06\ufe0f": 52.55, + "ARC": 43.52, + "HellaSwag": 70.45, + "MMLU": 50.49, + "TruthfulQA": 43.52, + "Winogrande": 66.85, + "GSM8K": 40.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a950abcd65c24f7b3de09298c38ca8890e8fa269", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "frank098\/Wizard-Vicuna-13B-juniper", + "Average \u2b06\ufe0f": 52.55, + "ARC": 55.89, + "HellaSwag": 79.75, + "MMLU": 44.99, + "TruthfulQA": 54.72, + "Winogrande": 72.69, + "GSM8K": 7.28, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "24f58beb9ed4cf635fc962853ed71d0f4b1909ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wahaha1987\/llama_13b_sharegpt94k_fastchat", + "Average \u2b06\ufe0f": 52.55, + "ARC": 53.75, + "HellaSwag": 79.47, + "MMLU": 51.5, + "TruthfulQA": 49.54, + "Winogrande": 72.61, + "GSM8K": 8.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "388bc2f82a1ee8b963c7f94f9c7b6743f7214306", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/mcq-vicuna-13b-v1.5", + "Average \u2b06\ufe0f": 52.55, + "ARC": 56.23, + "HellaSwag": 81.15, + "MMLU": 53.38, + "TruthfulQA": 44.08, + "Winogrande": 72.93, + "GSM8K": 7.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f769a92cfeffe8ee07beee8814ce7eca7cd62805", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-codellama-dolphin-orca-platypus-34b", + "Average \u2b06\ufe0f": 52.53, + "ARC": 52.47, + "HellaSwag": 74.13, + "MMLU": 53.47, + "TruthfulQA": 47.14, + "Winogrande": 73.24, + "GSM8K": 14.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "57e18e617b4fd7ab61bd7da8ee9516513ad76842", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "speechlessai\/speechless-codellama-34b-v1.0", + "Average \u2b06\ufe0f": 52.53, + "ARC": 52.47, + "HellaSwag": 74.13, + "MMLU": 53.47, + "TruthfulQA": 47.14, + "Winogrande": 73.24, + "GSM8K": 14.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1d64d871cd56da3031e19bc267ef8bd0b85b9936", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Llama-2-7b-chat-hf-10-attention-sparsity", + "Average \u2b06\ufe0f": 52.52, + "ARC": 52.9, + "HellaSwag": 78.18, + "MMLU": 48.1, + "TruthfulQA": 45.4, + "Winogrande": 71.43, + "GSM8K": 19.11, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "175ab7c54ff9031936cbcd23edfb82420e438252", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "indischepartij\/MiniCPM-3B-Hercules-v2.0", + "Average \u2b06\ufe0f": 52.52, + "ARC": 43.26, + "HellaSwag": 71.11, + "MMLU": 51.82, + "TruthfulQA": 40.37, + "Winogrande": 66.46, + "GSM8K": 42.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 3.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7564c055f9aaca4094e955b62f68975ec305d675", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-codellama-34b-v2.0", + "Average \u2b06\ufe0f": 52.51, + "ARC": 54.35, + "HellaSwag": 75.65, + "MMLU": 54.67, + "TruthfulQA": 45.21, + "Winogrande": 73.56, + "GSM8K": 11.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "cb81174d72dbe06f8db1c406ef97981532de6f09", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lvkaokao\/llama2-7b-hf-chat-lora-v2", + "Average \u2b06\ufe0f": 52.5, + "ARC": 55.03, + "HellaSwag": 78.81, + "MMLU": 51.35, + "TruthfulQA": 44.05, + "Winogrande": 74.9, + "GSM8K": 10.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0b8e61d3325cddbad207cbf885c2b5db6a83a059", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-13b-gpt4-2.0", + "Average \u2b06\ufe0f": 52.49, + "ARC": 59.04, + "HellaSwag": 82.82, + "MMLU": 54.71, + "TruthfulQA": 36.47, + "Winogrande": 74.19, + "GSM8K": 7.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "ec556571acc6783fea4414e4ca72d291c563b6dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "liuda1\/Mistral-7B-golden", + "Average \u2b06\ufe0f": 52.49, + "ARC": 60.75, + "HellaSwag": 44.42, + "MMLU": 59.29, + "TruthfulQA": 53.51, + "Winogrande": 76.64, + "GSM8K": 20.32, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bc4624485fef5a2e3fcde465eaf2191cb1df1877", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yukang\/Llama-2-13b-longlora-32k-ft", + "Average \u2b06\ufe0f": 52.49, + "ARC": 59.47, + "HellaSwag": 82.61, + "MMLU": 52.13, + "TruthfulQA": 37.44, + "Winogrande": 75.53, + "GSM8K": 7.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "6d17c854025b0bd54ce572ac803f1bb052875dbf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "genaicore3434\/MistralLite-summ-sft-e1", + "Average \u2b06\ufe0f": 52.48, + "ARC": 57.59, + "HellaSwag": 80.66, + "MMLU": 52.28, + "TruthfulQA": 40.85, + "Winogrande": 76.16, + "GSM8K": 7.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f8d5d904ff6bd07e59d6fcf484dc71986f856825", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lvkaokao\/llama2-7b-hf-chat-lora-v3", + "Average \u2b06\ufe0f": 52.48, + "ARC": 57.25, + "HellaSwag": 78.62, + "MMLU": 50.57, + "TruthfulQA": 50.62, + "Winogrande": 76.32, + "GSM8K": 1.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "79047f667253c878ad3143b016e3dcb3df707572", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Llama-2-7b-chat-hf-10-sparsity", + "Average \u2b06\ufe0f": 52.48, + "ARC": 53.16, + "HellaSwag": 78.26, + "MMLU": 48.18, + "TruthfulQA": 45.29, + "Winogrande": 71.59, + "GSM8K": 18.42, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9dda6f163ab399b0ae0fd19d6fe8ec37d9ff97be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beaugogh\/Llama2-7b-openorca-mc-v2", + "Average \u2b06\ufe0f": 52.47, + "ARC": 55.55, + "HellaSwag": 81.26, + "MMLU": 48.3, + "TruthfulQA": 51.49, + "Winogrande": 72.85, + "GSM8K": 5.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1e74a9cca843cdeb8591d4e4f4320dc1870adf1b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lizhuang144\/llama_mirror_13b_v1.0", + "Average \u2b06\ufe0f": 52.46, + "ARC": 57.59, + "HellaSwag": 80.53, + "MMLU": 48.0, + "TruthfulQA": 44.54, + "Winogrande": 76.64, + "GSM8K": 7.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "379cb8f080110f3418155029f534f67a79e25db4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bofenghuang\/vigogne-2-7b-chat", + "Average \u2b06\ufe0f": 52.45, + "ARC": 55.63, + "HellaSwag": 78.71, + "MMLU": 50.98, + "TruthfulQA": 47.21, + "Winogrande": 74.43, + "GSM8K": 7.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "7a1b76feabe3e0ed007ea83ee93f7644156d3b23", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ausboss\/llama-13b-supercot", + "Average \u2b06\ufe0f": 52.44, + "ARC": 56.06, + "HellaSwag": 81.71, + "MMLU": 45.36, + "TruthfulQA": 48.55, + "Winogrande": 75.77, + "GSM8K": 7.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "f6953fa162b487a3d4c6bdc7b7951e09576c2ae5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "camel-ai\/CAMEL-13B-Combined-Data", + "Average \u2b06\ufe0f": 52.44, + "ARC": 55.63, + "HellaSwag": 79.25, + "MMLU": 49.74, + "TruthfulQA": 47.42, + "Winogrande": 75.45, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "6d98f2801f13d89de7978ee9f348a52ea46a24ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PocketDoc\/Dans-PileOfSets-Mk1-llama-13b-merged", + "Average \u2b06\ufe0f": 52.43, + "ARC": 58.79, + "HellaSwag": 81.79, + "MMLU": 48.12, + "TruthfulQA": 41.24, + "Winogrande": 76.16, + "GSM8K": 8.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a7e5484df8aceae7800ae9301a3954cf74b527e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Korabbit\/Llama-2-7b-chat-hf-afr-300step-flan-v2", + "Average \u2b06\ufe0f": 52.41, + "ARC": 52.56, + "HellaSwag": 77.76, + "MMLU": 48.51, + "TruthfulQA": 45.14, + "Winogrande": 72.53, + "GSM8K": 17.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a2191bd90b04396016b7420dd14675916056f44a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/PuddleJumper-Platypus2-13B-QLoRA-0.80-epoch", + "Average \u2b06\ufe0f": 52.41, + "ARC": 54.52, + "HellaSwag": 79.36, + "MMLU": 55.15, + "TruthfulQA": 54.32, + "Winogrande": 71.11, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4b5aabc51907e4cba49f373c6dc09a2634f2fb8a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/zararp-l2-7b", + "Average \u2b06\ufe0f": 52.39, + "ARC": 56.31, + "HellaSwag": 79.19, + "MMLU": 51.36, + "TruthfulQA": 51.26, + "Winogrande": 74.51, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6032c5106970f98d59925959fbd330ae4b1d1a7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Unbabel\/TowerInstruct-7B-v0.1", + "Average \u2b06\ufe0f": 52.39, + "ARC": 55.46, + "HellaSwag": 79.0, + "MMLU": 46.88, + "TruthfulQA": 42.59, + "Winogrande": 73.95, + "GSM8K": 16.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 52.0, + "Available on the hub": true, + "Model sha": "d97a456da8a218425b5171a906a7d9a0c5cd7b2f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Alpacino13b", + "Average \u2b06\ufe0f": 52.39, + "ARC": 58.53, + "HellaSwag": 81.31, + "MMLU": 47.92, + "TruthfulQA": 41.66, + "Winogrande": 76.95, + "GSM8K": 7.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 29.0, + "Available on the hub": true, + "Model sha": "7092a5c8dec649694dd66ff8cfe5452ce52e6a40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "The-Face-Of-Goonery\/Huginn-22b-Prototype", + "Average \u2b06\ufe0f": 52.36, + "ARC": 57.68, + "HellaSwag": 80.69, + "MMLU": 49.81, + "TruthfulQA": 52.11, + "Winogrande": 71.59, + "GSM8K": 2.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 21.83, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "29222b05794abb862ad0aaaf3020696c9f599810", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Deita-2b", + "Average \u2b06\ufe0f": 52.35, + "ARC": 44.71, + "HellaSwag": 70.39, + "MMLU": 52.79, + "TruthfulQA": 39.61, + "Winogrande": 65.27, + "GSM8K": 41.32, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 3.01, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "11267fbddbe8652cff32c1f6c7e3e8ca2f48f28c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "totally-not-an-llm\/EverythingLM-13b-16k", + "Average \u2b06\ufe0f": 52.33, + "ARC": 56.57, + "HellaSwag": 80.58, + "MMLU": 50.18, + "TruthfulQA": 47.46, + "Winogrande": 72.77, + "GSM8K": 6.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 33.0, + "Available on the hub": true, + "Model sha": "8456a856a8b115b05e76a7d0d945853b10ac71e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BioMistral\/BioMistral-7B", + "Average \u2b06\ufe0f": 52.33, + "ARC": 54.27, + "HellaSwag": 79.09, + "MMLU": 55.56, + "TruthfulQA": 51.61, + "Winogrande": 73.48, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 271.0, + "Available on the hub": true, + "Model sha": "e7298b35e5460a37b83fb0dc69eae03f46b49275", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "beaugogh\/Llama2-7b-openorca-mc-v2-dpo", + "Average \u2b06\ufe0f": 52.32, + "ARC": 54.78, + "HellaSwag": 81.48, + "MMLU": 47.2, + "TruthfulQA": 53.13, + "Winogrande": 72.85, + "GSM8K": 4.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "734a6f0c69e1e53b988c107926bc17cb0536f851", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-atom-13b-v9-bf16", + "Average \u2b06\ufe0f": 52.31, + "ARC": 51.19, + "HellaSwag": 75.99, + "MMLU": 49.33, + "TruthfulQA": 48.66, + "Winogrande": 73.32, + "GSM8K": 15.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "35bb2c73953f6ea40be6f0c8c6b2dfa7ecbaa0df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-13b-gpt4-1.2", + "Average \u2b06\ufe0f": 52.31, + "ARC": 58.36, + "HellaSwag": 81.61, + "MMLU": 48.84, + "TruthfulQA": 47.54, + "Winogrande": 73.64, + "GSM8K": 3.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "482bd38b65e73fde13f5d03fed2bee7acda8fadd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eachadea\/vicuna-13b", + "Average \u2b06\ufe0f": 52.3, + "ARC": 51.71, + "HellaSwag": 79.94, + "MMLU": 50.84, + "TruthfulQA": 52.68, + "Winogrande": 71.03, + "GSM8K": 7.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ac4218770a58baaaaf25201076fe082abb6ffd13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "prithivida\/Asimov-7B-v2", + "Average \u2b06\ufe0f": 52.29, + "ARC": 54.27, + "HellaSwag": 78.72, + "MMLU": 52.59, + "TruthfulQA": 45.44, + "Winogrande": 71.82, + "GSM8K": 10.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0aeea2284ac78cac081bee88e5a98a19bb987227", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-mmlu-merged", + "Average \u2b06\ufe0f": 52.29, + "ARC": 51.11, + "HellaSwag": 76.75, + "MMLU": 49.39, + "TruthfulQA": 48.49, + "Winogrande": 71.98, + "GSM8K": 16.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "189304f388007b3be70818d8f9842b4512faf310", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ericpolewski\/Palworld-SME-13b", + "Average \u2b06\ufe0f": 52.28, + "ARC": 55.55, + "HellaSwag": 80.81, + "MMLU": 53.64, + "TruthfulQA": 46.67, + "Winogrande": 74.82, + "GSM8K": 2.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-3.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4b3b88c21071c77cffb23ddb5508c86f735fe229", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mncai\/Llama2-7B-guanaco-1k", + "Average \u2b06\ufe0f": 52.28, + "ARC": 55.12, + "HellaSwag": 80.53, + "MMLU": 47.93, + "TruthfulQA": 47.69, + "Winogrande": 74.82, + "GSM8K": 7.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5f3194b779897bbc4c4218a9dddc44a9b5faea15", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Korabbit\/Llama-2-7b-chat-hf-afr-441step-flan-v2", + "Average \u2b06\ufe0f": 52.28, + "ARC": 52.13, + "HellaSwag": 77.63, + "MMLU": 48.52, + "TruthfulQA": 45.02, + "Winogrande": 72.53, + "GSM8K": 17.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "daede60607179be05b5d6e90b4c6777806b10fb8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "nnethercott\/llava-v1.5-7b-hf-vicuna", + "Average \u2b06\ufe0f": 52.28, + "ARC": 52.65, + "HellaSwag": 76.09, + "MMLU": 51.68, + "TruthfulQA": 45.86, + "Winogrande": 72.06, + "GSM8K": 15.31, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "62343e8b8383aed371cb04aa01aff8a143b82ff9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TFLai\/Platypus2-13B-QLoRA-0.80-epoch", + "Average \u2b06\ufe0f": 52.27, + "ARC": 57.76, + "HellaSwag": 81.63, + "MMLU": 55.63, + "TruthfulQA": 39.7, + "Winogrande": 75.93, + "GSM8K": 2.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "114eb8efd2de1c9eae85d92de490b95c854dfae9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "oh-yeontaek\/llama-2-7B-LoRA-assemble", + "Average \u2b06\ufe0f": 52.26, + "ARC": 57.34, + "HellaSwag": 78.81, + "MMLU": 50.75, + "TruthfulQA": 53.18, + "Winogrande": 73.48, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "72e866a96a2e9afc6527c8d757c69088c3a069c8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-temporal-sharegpt", + "Average \u2b06\ufe0f": 52.26, + "ARC": 53.5, + "HellaSwag": 75.82, + "MMLU": 50.79, + "TruthfulQA": 44.75, + "Winogrande": 72.69, + "GSM8K": 16.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dffa41945e5bdac60bd7541ef775642a02189d15", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Korabbit\/Llama-2-7b-chat-hf-afr-200step-merged", + "Average \u2b06\ufe0f": 52.26, + "ARC": 52.05, + "HellaSwag": 77.38, + "MMLU": 48.65, + "TruthfulQA": 44.6, + "Winogrande": 71.9, + "GSM8K": 18.95, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "858de1c14854e55d5141b8d1b3954b335044669e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "beaugogh\/Llama2-7b-openorca-mc-v1", + "Average \u2b06\ufe0f": 52.24, + "ARC": 55.63, + "HellaSwag": 80.17, + "MMLU": 48.44, + "TruthfulQA": 51.62, + "Winogrande": 73.48, + "GSM8K": 4.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2c4096fa2129665fb127f1c2a1302f30565a5265", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/zararp-1.1-l2-7b", + "Average \u2b06\ufe0f": 52.22, + "ARC": 56.48, + "HellaSwag": 78.85, + "MMLU": 51.49, + "TruthfulQA": 51.99, + "Winogrande": 73.4, + "GSM8K": 1.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "31fa6527a3285d5fd320219d7c2dadde07b83718", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "LTC-AI-Labs\/L2-7b-Hermes-Synthia", + "Average \u2b06\ufe0f": 52.21, + "ARC": 51.02, + "HellaSwag": 79.12, + "MMLU": 47.88, + "TruthfulQA": 46.77, + "Winogrande": 74.51, + "GSM8K": 13.95, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "6f9bd33be62c4b5dbbb8d76ad30d61c3ceb01641", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Llama-2-7b-chat-hf-20-attention-sparsity", + "Average \u2b06\ufe0f": 52.19, + "ARC": 53.41, + "HellaSwag": 77.91, + "MMLU": 47.49, + "TruthfulQA": 45.84, + "Winogrande": 70.72, + "GSM8K": 17.74, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d095cb8c872249e6b324ec25c7e388aa9203e5b4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Nous-Hermes-13B-SuperHOT-8K-fp16", + "Average \u2b06\ufe0f": 52.18, + "ARC": 55.29, + "HellaSwag": 81.87, + "MMLU": 48.23, + "TruthfulQA": 51.19, + "Winogrande": 75.3, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "b407c1ece029ad5693d38e6e0931e9482962ed15", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/oasst-llama-13b-1000-steps", + "Average \u2b06\ufe0f": 52.18, + "ARC": 58.11, + "HellaSwag": 81.52, + "MMLU": 48.65, + "TruthfulQA": 35.99, + "Winogrande": 77.51, + "GSM8K": 11.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d2cd599cc40db3370009f45d6caa7e486cb6d31f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HyperbeeAI\/Tulpar-7b-v1", + "Average \u2b06\ufe0f": 52.16, + "ARC": 57.0, + "HellaSwag": 79.69, + "MMLU": 51.33, + "TruthfulQA": 51.83, + "Winogrande": 72.45, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "719d8e1eb4a820f01e0a92ef6220d041964bb472", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/WizardLM-13B-V1-1-SuperHOT-8K-GPTQ", + "Average \u2b06\ufe0f": 52.15, + "ARC": 57.0, + "HellaSwag": 80.32, + "MMLU": 47.08, + "TruthfulQA": 53.46, + "Winogrande": 74.35, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 46.0, + "Available on the hub": true, + "Model sha": "085eb5cd394f30d72bf5efcf83a580e87264b3e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Stheno-1.3-L2-13B", + "Average \u2b06\ufe0f": 52.15, + "ARC": 56.83, + "HellaSwag": 81.7, + "MMLU": 52.79, + "TruthfulQA": 50.23, + "Winogrande": 71.11, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "45ba2f603769aa6b97639962f522b8d7398c2393", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "xxyyy123\/mc_data_30k_from_platpus_orca_7b_10k_v1_lora_qkvo_rank14_v2", + "Average \u2b06\ufe0f": 52.13, + "ARC": 57.17, + "HellaSwag": 79.57, + "MMLU": 50.24, + "TruthfulQA": 52.51, + "Winogrande": 72.93, + "GSM8K": 0.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9c4a7444d6fb12931e50f111053e016531fe60b7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "StudentLLM\/Alpagasus-2-13B-QLoRA-pipeline", + "Average \u2b06\ufe0f": 52.13, + "ARC": 58.28, + "HellaSwag": 80.98, + "MMLU": 54.14, + "TruthfulQA": 34.21, + "Winogrande": 75.93, + "GSM8K": 9.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "86329885e029c1f4fb6ff6b6f3409007158499e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-mixtral-7bx8-v16.3-32k", + "Average \u2b06\ufe0f": 52.13, + "ARC": 26.45, + "HellaSwag": 80.83, + "MMLU": 71.99, + "TruthfulQA": 56.39, + "Winogrande": 77.11, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "133279baf54f2b8fe414203318272e7d3619ace4", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Biomimicry-AI\/ANIMA-Nectar-v2", + "Average \u2b06\ufe0f": 52.13, + "ARC": 53.24, + "HellaSwag": 76.63, + "MMLU": 54.21, + "TruthfulQA": 49.04, + "Winogrande": 74.11, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "304e41b614d1ac9debccfa266887640b508c9823", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xwin-LM\/Xwin-LM-7B-V0.1", + "Average \u2b06\ufe0f": 52.08, + "ARC": 56.57, + "HellaSwag": 79.4, + "MMLU": 49.98, + "TruthfulQA": 47.89, + "Winogrande": 73.32, + "GSM8K": 5.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 75.0, + "Available on the hub": true, + "Model sha": "470e680120a7249d6e8a875345015ddba1711100", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-7b-v1.5", + "Average \u2b06\ufe0f": 52.06, + "ARC": 53.24, + "HellaSwag": 77.39, + "MMLU": 51.04, + "TruthfulQA": 50.34, + "Winogrande": 72.14, + "GSM8K": 8.19, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 174.0, + "Available on the hub": true, + "Model sha": "de56c35b1763eaae20f4d60efd64af0a9091ebe5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "l3utterfly\/llama2-7b-layla", + "Average \u2b06\ufe0f": 52.05, + "ARC": 54.18, + "HellaSwag": 79.34, + "MMLU": 49.7, + "TruthfulQA": 46.5, + "Winogrande": 74.11, + "GSM8K": 8.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "733016abcd2abee63eb45ed63d2bba14b91da217", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LTC-AI-Labs\/L2-7b-Beluga-WVG-Test", + "Average \u2b06\ufe0f": 52.04, + "ARC": 53.75, + "HellaSwag": 78.38, + "MMLU": 51.57, + "TruthfulQA": 45.76, + "Winogrande": 74.9, + "GSM8K": 7.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b90c207e248c0ad541274c2eb5ef76da1181802f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lvkaokao\/llama2-7b-hf-chat-lora", + "Average \u2b06\ufe0f": 52.03, + "ARC": 55.72, + "HellaSwag": 78.75, + "MMLU": 47.99, + "TruthfulQA": 43.11, + "Winogrande": 75.85, + "GSM8K": 10.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e92a1439ac8d2edb5e311b8a42e13ed7c5e70db5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bofenghuang\/vigogne-2-7b-instruct", + "Average \u2b06\ufe0f": 52.02, + "ARC": 56.23, + "HellaSwag": 79.97, + "MMLU": 47.17, + "TruthfulQA": 49.51, + "Winogrande": 75.45, + "GSM8K": 3.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": false, + "Model sha": "8f4dd9c870f748322989168af5c109e16b01c63d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Llama-2-7b-chat-hf-20-sparsity", + "Average \u2b06\ufe0f": 52.01, + "ARC": 52.47, + "HellaSwag": 77.91, + "MMLU": 47.27, + "TruthfulQA": 45.88, + "Winogrande": 70.72, + "GSM8K": 17.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7b44f4902cde1b21b48c87c0379c7aab819436ef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "haonan-li\/bactrian-x-llama-13b-merged", + "Average \u2b06\ufe0f": 52.0, + "ARC": 56.4, + "HellaSwag": 79.33, + "MMLU": 48.4, + "TruthfulQA": 48.38, + "Winogrande": 73.95, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cc5ee2231066c147423f89e9df40f7364c3275a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-7b-v1.5", + "Average \u2b06\ufe0f": 51.99, + "ARC": 53.24, + "HellaSwag": 77.39, + "MMLU": 50.82, + "TruthfulQA": 50.33, + "Winogrande": 72.06, + "GSM8K": 8.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 174.0, + "Available on the hub": true, + "Model sha": "de56c35b1763eaae20f4d60efd64af0a9091ebe5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JosephusCheung\/Qwen-LLaMAfied-7B-Chat", + "Average \u2b06\ufe0f": 51.99, + "ARC": 50.94, + "HellaSwag": 83.47, + "MMLU": 53.52, + "TruthfulQA": 46.09, + "Winogrande": 73.16, + "GSM8K": 4.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 100.0, + "Available on the hub": true, + "Model sha": "4d70cf0047a7a5cd2c864bc2606e81f0830e4405", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-mistral-7b-v13-base", + "Average \u2b06\ufe0f": 51.99, + "ARC": 52.9, + "HellaSwag": 76.12, + "MMLU": 57.54, + "TruthfulQA": 52.82, + "Winogrande": 71.35, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "8ff18d61b1c8295ecd73153b8e0b63934187a50e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "davzoku\/frankencria-llama2-11b-v1.3-m.1", + "Average \u2b06\ufe0f": 51.96, + "ARC": 52.82, + "HellaSwag": 77.5, + "MMLU": 48.0, + "TruthfulQA": 46.87, + "Winogrande": 71.59, + "GSM8K": 15.01, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 9.98, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b528d28472ee973165ca216337e66207a0d7c6e3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/spicyboros-7b-2.2", + "Average \u2b06\ufe0f": 51.95, + "ARC": 56.57, + "HellaSwag": 80.09, + "MMLU": 48.47, + "TruthfulQA": 47.22, + "Winogrande": 74.51, + "GSM8K": 4.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "fdf075081555f3ed84c037e8dd3fe85c3b3609d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xxyyy123\/10k_v1_lora_qkvo_rank28_v2", + "Average \u2b06\ufe0f": 51.95, + "ARC": 55.38, + "HellaSwag": 79.21, + "MMLU": 50.5, + "TruthfulQA": 52.75, + "Winogrande": 73.24, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "70e38a7424544193f0ad6a93ae26a5bfd15e4e90", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "pe-nlp\/llama-2-13b-vicuna-wizard", + "Average \u2b06\ufe0f": 51.94, + "ARC": 57.76, + "HellaSwag": 82.16, + "MMLU": 54.68, + "TruthfulQA": 41.11, + "Winogrande": 74.98, + "GSM8K": 0.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b51bf8c4e132308751cc8b9d9c1131539f79f07f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chinoll\/Yi-6b-200k-dpo", + "Average \u2b06\ufe0f": 51.93, + "ARC": 43.09, + "HellaSwag": 74.53, + "MMLU": 64.0, + "TruthfulQA": 45.51, + "Winogrande": 73.09, + "GSM8K": 11.37, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "925c5fbaeccb321ba8edbde79c3d994adc460a41", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "chinoll\/Yi-7b-dpo", + "Average \u2b06\ufe0f": 51.93, + "ARC": 43.09, + "HellaSwag": 74.53, + "MMLU": 64.0, + "TruthfulQA": 45.51, + "Winogrande": 73.09, + "GSM8K": 11.37, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "925c5fbaeccb321ba8edbde79c3d994adc460a41", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "indischepartij\/MiniCPM-3B-OpenHermes-2.5-v2", + "Average \u2b06\ufe0f": 51.91, + "ARC": 47.44, + "HellaSwag": 72.0, + "MMLU": 53.06, + "TruthfulQA": 42.28, + "Winogrande": 65.43, + "GSM8K": 31.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.01, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "e192b35bd2b59f3fe7f6987b4459eaa59b69fc9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/Nous-Hermes-llama-2-7b", + "Average \u2b06\ufe0f": 51.87, + "ARC": 55.12, + "HellaSwag": 78.94, + "MMLU": 48.34, + "TruthfulQA": 49.01, + "Winogrande": 74.03, + "GSM8K": 5.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": [ + "mit" + ], + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 61.0, + "Available on the hub": true, + "Model sha": "60e58acecdc1552e1b1752a38d1d91d942d1c3f0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-zephyr-7b-v14.1", + "Average \u2b06\ufe0f": 51.86, + "ARC": 52.13, + "HellaSwag": 75.02, + "MMLU": 56.21, + "TruthfulQA": 49.84, + "Winogrande": 73.24, + "GSM8K": 4.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 49.0, + "Available on the hub": true, + "Model sha": "208b6fb841239a36fb0ea675179a231e0ad9d287", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ashercn97\/manatee-7b", + "Average \u2b06\ufe0f": 51.84, + "ARC": 54.52, + "HellaSwag": 78.95, + "MMLU": 49.26, + "TruthfulQA": 46.77, + "Winogrande": 74.51, + "GSM8K": 7.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "e66094c43ffe6c5b3f4164cd4ba048d3bc422fd0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "migtissera\/Synthia-7B", + "Average \u2b06\ufe0f": 51.83, + "ARC": 56.14, + "HellaSwag": 78.6, + "MMLU": 50.35, + "TruthfulQA": 45.03, + "Winogrande": 74.27, + "GSM8K": 6.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "4f9e95665d95b4c692910190ff77257216e476f1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Medusa-1.1-L2-7B", + "Average \u2b06\ufe0f": 51.8, + "ARC": 56.48, + "HellaSwag": 78.57, + "MMLU": 51.56, + "TruthfulQA": 47.7, + "Winogrande": 75.06, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "df23c3d22bc546dbce0267415e94bdb482446c06", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Llama-2-7b-chat-hf-30-attention-sparsity", + "Average \u2b06\ufe0f": 51.8, + "ARC": 53.41, + "HellaSwag": 76.87, + "MMLU": 47.04, + "TruthfulQA": 45.02, + "Winogrande": 71.03, + "GSM8K": 17.44, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06031965747c6a43923b2a84555ceba5f6d2aecc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elliotthwang\/Elliott-Chinese-LLaMa-GPTQ", + "Average \u2b06\ufe0f": 51.79, + "ARC": 51.02, + "HellaSwag": 75.23, + "MMLU": 49.58, + "TruthfulQA": 45.09, + "Winogrande": 72.61, + "GSM8K": 17.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 53.9, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bbbca62bb340b4ae0a19ba93dae38fc9f9787c16", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sao10K\/Stheno-Mix-L2-20B", + "Average \u2b06\ufe0f": 51.79, + "ARC": 57.76, + "HellaSwag": 79.63, + "MMLU": 52.51, + "TruthfulQA": 51.8, + "Winogrande": 68.98, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 20.63, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6f9dcdaae6ef9071effe63d2107abe8b9712345b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "umd-zhou-lab\/recycled-wizardlm-7b-v2.0", + "Average \u2b06\ufe0f": 51.79, + "ARC": 54.95, + "HellaSwag": 77.85, + "MMLU": 45.79, + "TruthfulQA": 48.29, + "Winogrande": 71.51, + "GSM8K": 12.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4a770caf3509b3fdda5ed54735dc40a8f0442c61", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-13b-gpt4-1.3", + "Average \u2b06\ufe0f": 51.76, + "ARC": 58.53, + "HellaSwag": 81.6, + "MMLU": 46.96, + "TruthfulQA": 45.29, + "Winogrande": 75.85, + "GSM8K": 2.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "32a474742c2a235ca12c96afaea57dcb6b46ef56", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decruz07\/llama-2-7b-miniguanaco", + "Average \u2b06\ufe0f": 51.74, + "ARC": 50.0, + "HellaSwag": 76.96, + "MMLU": 48.05, + "TruthfulQA": 42.84, + "Winogrande": 73.48, + "GSM8K": 19.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ef3fa61b50387f5a982aa2578933dfc20afb7237", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lazycuber\/L2-7b-Orca-WVG-Test", + "Average \u2b06\ufe0f": 51.72, + "ARC": 54.86, + "HellaSwag": 78.25, + "MMLU": 51.13, + "TruthfulQA": 43.68, + "Winogrande": 74.35, + "GSM8K": 8.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6073a87872eb36149404bfb7d60e0108074ee1c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Azure99\/blossom-v2-llama2-7b", + "Average \u2b06\ufe0f": 51.71, + "ARC": 54.1, + "HellaSwag": 78.57, + "MMLU": 51.66, + "TruthfulQA": 46.84, + "Winogrande": 74.35, + "GSM8K": 4.78, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "8c71cdb481ce6bbda3b2042e5526a232ab23825c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jphme\/em_german_leo_mistral", + "Average \u2b06\ufe0f": 51.69, + "ARC": 52.82, + "HellaSwag": 78.03, + "MMLU": 50.03, + "TruthfulQA": 50.19, + "Winogrande": 73.48, + "GSM8K": 5.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 56.0, + "Available on the hub": true, + "Model sha": "aa63a32154923034fb89b1408d3d7ffa994d3327", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "haoranxu\/ALMA-13B-Pretrain", + "Average \u2b06\ufe0f": 51.68, + "ARC": 56.91, + "HellaSwag": 80.15, + "MMLU": 50.31, + "TruthfulQA": 37.44, + "Winogrande": 76.4, + "GSM8K": 8.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "69e9e12d8bab66dffdcb15fa534fc3f0dc34acec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-ziya-13b", + "Average \u2b06\ufe0f": 51.67, + "ARC": 55.38, + "HellaSwag": 78.47, + "MMLU": 45.18, + "TruthfulQA": 49.29, + "Winogrande": 74.82, + "GSM8K": 6.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "9a21051ae490d2f8ab8b1181c1b45e0412d71a90", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TencentARC\/LLaMA-Pro-8B", + "Average \u2b06\ufe0f": 51.67, + "ARC": 53.75, + "HellaSwag": 77.91, + "MMLU": 47.49, + "TruthfulQA": 38.86, + "Winogrande": 74.19, + "GSM8K": 17.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 8.36, + "Hub \u2764\ufe0f": 162.0, + "Available on the hub": true, + "Model sha": "7a2b46875f68ca276562a44ea99b713d86ddb9f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/llama_ppo_1e6_new_tokenizerstep_8000", + "Average \u2b06\ufe0f": 51.67, + "ARC": 54.78, + "HellaSwag": 78.64, + "MMLU": 46.63, + "TruthfulQA": 41.06, + "Winogrande": 74.03, + "GSM8K": 14.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "04de12f4c9f1fdf9fd4cd0d71dac8bc169813c63", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LTC-AI-Labs\/L2-7b-Base-test-WVG", + "Average \u2b06\ufe0f": 51.66, + "ARC": 54.27, + "HellaSwag": 77.81, + "MMLU": 51.07, + "TruthfulQA": 46.28, + "Winogrande": 73.56, + "GSM8K": 6.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2491546f1219c3e9bb1a8cf37fbecf0b299c2177", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rombodawg\/LosslessMegaCoder-llama2-7b-mini", + "Average \u2b06\ufe0f": 51.66, + "ARC": 53.5, + "HellaSwag": 77.38, + "MMLU": 49.72, + "TruthfulQA": 45.77, + "Winogrande": 74.03, + "GSM8K": 9.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "186b105d61054611d0b921a55c220d41c6aefe43", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/llama_sft_longer", + "Average \u2b06\ufe0f": 51.64, + "ARC": 54.78, + "HellaSwag": 78.58, + "MMLU": 46.87, + "TruthfulQA": 40.82, + "Winogrande": 73.88, + "GSM8K": 14.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cf2d1d1b306395ad3ae92484dc951ade09fb698c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "augmxnt\/shisa-base-7b-v1", + "Average \u2b06\ufe0f": 51.64, + "ARC": 52.3, + "HellaSwag": 77.63, + "MMLU": 23.12, + "TruthfulQA": 42.4, + "Winogrande": 78.53, + "GSM8K": 35.86, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.96, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "5aa465caca707816a4bb36b4980aef5d102d76fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elliotthwang\/Elliott-Chinese-LLaMa-GPTQ-V1.0", + "Average \u2b06\ufe0f": 51.64, + "ARC": 50.68, + "HellaSwag": 75.36, + "MMLU": 49.33, + "TruthfulQA": 44.7, + "Winogrande": 72.38, + "GSM8K": 17.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 53.9, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "01305dc473ba231519fe71e7f4b2d1e3f6aa9bc8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TheBloke\/stable-vicuna-13B-HF", + "Average \u2b06\ufe0f": 51.64, + "ARC": 53.33, + "HellaSwag": 78.5, + "MMLU": 50.29, + "TruthfulQA": 48.38, + "Winogrande": 75.22, + "GSM8K": 4.09, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 95.0, + "Available on the hub": true, + "Model sha": "2b099b2be0dafb2606ae9808c0f6183fe4bff7bc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/Platypus2xOpenOrca-13B-LoRa-v2", + "Average \u2b06\ufe0f": 51.61, + "ARC": 58.62, + "HellaSwag": 81.17, + "MMLU": 50.23, + "TruthfulQA": 43.43, + "Winogrande": 76.16, + "GSM8K": 0.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "568ac6a5f1a9f5eb6bc09efb2188740d771ed0e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/llama_ppo_1e6step_4000", + "Average \u2b06\ufe0f": 51.61, + "ARC": 54.44, + "HellaSwag": 78.66, + "MMLU": 46.74, + "TruthfulQA": 41.24, + "Winogrande": 74.19, + "GSM8K": 14.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4fa307bac86077a73c3b1a19be4dd12c4d709fae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rufjdk5480\/llama-7b-ludwig-alpaca", + "Average \u2b06\ufe0f": 51.6, + "ARC": 54.01, + "HellaSwag": 78.73, + "MMLU": 45.8, + "TruthfulQA": 41.91, + "Winogrande": 74.27, + "GSM8K": 14.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7928584c0329c3ed88915a823033908be90ba657", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abhinand\/tamil-llama-13b-instruct-v0.1", + "Average \u2b06\ufe0f": 51.59, + "ARC": 54.52, + "HellaSwag": 79.35, + "MMLU": 50.37, + "TruthfulQA": 41.22, + "Winogrande": 76.56, + "GSM8K": 7.51, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7d6d6f23f69d1d8806ac21eec7ef8feba63c0e67", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-7b-v1.5-16k", + "Average \u2b06\ufe0f": 51.58, + "ARC": 54.69, + "HellaSwag": 77.32, + "MMLU": 49.51, + "TruthfulQA": 50.41, + "Winogrande": 71.11, + "GSM8K": 6.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 82.0, + "Available on the hub": true, + "Model sha": "9a93d7d11fac7f3f9074510b80092b53bc1a5bec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Envoid\/Yousei-22B", + "Average \u2b06\ufe0f": 51.56, + "ARC": 55.89, + "HellaSwag": 78.55, + "MMLU": 52.31, + "TruthfulQA": 50.68, + "Winogrande": 71.51, + "GSM8K": 0.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 21.83, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "ae8f93963266d31000433f1a52d43435e1473e2b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PocketDoc\/Dans-MysteryModel-13b", + "Average \u2b06\ufe0f": 51.54, + "ARC": 57.0, + "HellaSwag": 80.35, + "MMLU": 52.06, + "TruthfulQA": 45.0, + "Winogrande": 74.82, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c38a9df20162455b53eb35d38a9b67fb824559e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lvkaokao\/llama2-7b-hf-instruction-lora", + "Average \u2b06\ufe0f": 51.54, + "ARC": 55.38, + "HellaSwag": 78.57, + "MMLU": 49.39, + "TruthfulQA": 41.83, + "Winogrande": 74.19, + "GSM8K": 9.86, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f660a40323b29040e78097acca320517ed242512", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/airoboros-c34b-2.1", + "Average \u2b06\ufe0f": 51.52, + "ARC": 54.69, + "HellaSwag": 76.45, + "MMLU": 55.08, + "TruthfulQA": 46.15, + "Winogrande": 68.43, + "GSM8K": 8.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "2caa8ce3aab012bf34c7c531827f6befc7cc1c98", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GeneZC\/MiniChat-2-3B", + "Average \u2b06\ufe0f": 51.49, + "ARC": 44.88, + "HellaSwag": 67.69, + "MMLU": 47.59, + "TruthfulQA": 49.64, + "Winogrande": 66.46, + "GSM8K": 32.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "f9c59fdc14c42d1a84539e4195335da0a10af955", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-deepseek-10b-v17.1-4k", + "Average \u2b06\ufe0f": 51.48, + "ARC": 54.35, + "HellaSwag": 76.93, + "MMLU": 53.17, + "TruthfulQA": 45.96, + "Winogrande": 74.03, + "GSM8K": 4.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 10.55, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3d1f7c5136dbf13607d591c66e21e268a6c0c29e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elliotthwang\/Elliott-Chinese-LLaMa-GPTQ-V2.0", + "Average \u2b06\ufe0f": 51.47, + "ARC": 50.77, + "HellaSwag": 75.36, + "MMLU": 49.41, + "TruthfulQA": 44.7, + "Winogrande": 72.61, + "GSM8K": 16.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ebffe57ba6cc70b60ff5295889abc62d91eeb4dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lajonbot\/vicuna-7b-v1.5-PL-lora_unload", + "Average \u2b06\ufe0f": 51.46, + "ARC": 53.5, + "HellaSwag": 76.74, + "MMLU": 49.69, + "TruthfulQA": 49.68, + "Winogrande": 71.98, + "GSM8K": 7.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "92bf763ce7ae0bfe155bfd60190eed64582e5080", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-class-tutor-7b-ep3", + "Average \u2b06\ufe0f": 51.45, + "ARC": 52.13, + "HellaSwag": 78.07, + "MMLU": 51.32, + "TruthfulQA": 52.3, + "Winogrande": 71.19, + "GSM8K": 3.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "724cf8becd6dbb0b67070c34711ef6d60ad5f216", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JosephusCheung\/Pwen-VL-Chat-20_30", + "Average \u2b06\ufe0f": 51.45, + "ARC": 50.17, + "HellaSwag": 72.21, + "MMLU": 56.34, + "TruthfulQA": 42.52, + "Winogrande": 68.35, + "GSM8K": 19.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "64a9b89fb18140fc1af1f11471dc9fe34ebc7446", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "amazon\/MistralLite", + "Average \u2b06\ufe0f": 51.45, + "ARC": 59.56, + "HellaSwag": 81.84, + "MMLU": 50.93, + "TruthfulQA": 37.87, + "Winogrande": 77.43, + "GSM8K": 1.06, + "Type": "", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 412.0, + "Available on the hub": true, + "Model sha": "23486089ab7ba741b34adc69ab7555885f8abe71", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "frank098\/WizardLM_13B_juniper", + "Average \u2b06\ufe0f": 51.45, + "ARC": 55.38, + "HellaSwag": 77.2, + "MMLU": 45.46, + "TruthfulQA": 51.5, + "Winogrande": 71.11, + "GSM8K": 8.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2204970fc0d96b071e2b1b003fbc5c87cfc46840", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "itsliupeng\/llama2_7b_zh", + "Average \u2b06\ufe0f": 51.44, + "ARC": 52.05, + "HellaSwag": 74.88, + "MMLU": 60.69, + "TruthfulQA": 42.86, + "Winogrande": 71.74, + "GSM8K": 6.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "410711781d2e24226c0d62959e4990d1de851c3c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tlphams\/zoyllm-7b-slimorca", + "Average \u2b06\ufe0f": 51.44, + "ARC": 50.6, + "HellaSwag": 72.12, + "MMLU": 48.78, + "TruthfulQA": 49.13, + "Winogrande": 67.32, + "GSM8K": 20.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4b49caa2c42b3e8757f986624b047dab485ee26f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "camel-ai\/CAMEL-13B-Role-Playing-Data", + "Average \u2b06\ufe0f": 51.42, + "ARC": 54.95, + "HellaSwag": 79.25, + "MMLU": 46.61, + "TruthfulQA": 46.35, + "Winogrande": 74.03, + "GSM8K": 7.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": false, + "Model sha": "762ecb0d85572c8f8bcbca06d27f7f64a4d74615", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-7b-v1.5-16k", + "Average \u2b06\ufe0f": 51.42, + "ARC": 54.18, + "HellaSwag": 77.31, + "MMLU": 49.3, + "TruthfulQA": 50.35, + "Winogrande": 71.03, + "GSM8K": 6.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 82.0, + "Available on the hub": true, + "Model sha": "9a93d7d11fac7f3f9074510b80092b53bc1a5bec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hiyouga\/Baichuan2-7B-Chat-LLaMAfied", + "Average \u2b06\ufe0f": 51.42, + "ARC": 52.47, + "HellaSwag": 74.04, + "MMLU": 53.88, + "TruthfulQA": 48.04, + "Winogrande": 69.14, + "GSM8K": 10.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "da2cd76e2d61bf0247bd67a4f2835319c54a7d62", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nkpz\/llama2-22b-daydreamer-v3", + "Average \u2b06\ufe0f": 51.39, + "ARC": 56.06, + "HellaSwag": 80.07, + "MMLU": 52.49, + "TruthfulQA": 42.43, + "Winogrande": 73.48, + "GSM8K": 3.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 22.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "e6c74222958328e50712aa00294dc818c24075b2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hpcai-tech\/Colossal-LLaMA-2-7b-base", + "Average \u2b06\ufe0f": 51.39, + "ARC": 53.5, + "HellaSwag": 70.5, + "MMLU": 54.4, + "TruthfulQA": 50.19, + "Winogrande": 70.01, + "GSM8K": 9.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": true, + "Model sha": "1f30e4f2037e1e30122667639b8ef37138e85057", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Open-Orca\/OpenOrca-Preview1-13B", + "Average \u2b06\ufe0f": 51.38, + "ARC": 54.95, + "HellaSwag": 78.19, + "MMLU": 50.12, + "TruthfulQA": 49.05, + "Winogrande": 71.03, + "GSM8K": 4.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 147.0, + "Available on the hub": true, + "Model sha": "d120381b03051b60a7c77ec3fb1be6c3c1546466", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/kuchiki-1.1-l2-7b", + "Average \u2b06\ufe0f": 51.36, + "ARC": 54.18, + "HellaSwag": 78.0, + "MMLU": 48.14, + "TruthfulQA": 49.96, + "Winogrande": 73.16, + "GSM8K": 4.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "10fe70fec0df5c4dcbdfd2e9ec74830c41b3cfd2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "huggingface\/llama-13b", + "Average \u2b06\ufe0f": 51.36, + "ARC": 56.23, + "HellaSwag": 80.93, + "MMLU": 47.67, + "TruthfulQA": 39.48, + "Winogrande": 76.24, + "GSM8K": 7.58, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4022c52fcc7473ce7364bb5ac166195903ea1efb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LTC-AI-Labs\/L2-7b-Hermes-WVG-Test", + "Average \u2b06\ufe0f": 51.35, + "ARC": 54.95, + "HellaSwag": 78.48, + "MMLU": 48.36, + "TruthfulQA": 45.72, + "Winogrande": 74.74, + "GSM8K": 5.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "eb5b1d65fdf916ca71f89a46eb91175c1c630a57", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "huggyllama\/llama-13b", + "Average \u2b06\ufe0f": 51.33, + "ARC": 56.14, + "HellaSwag": 80.92, + "MMLU": 47.61, + "TruthfulQA": 39.48, + "Winogrande": 76.24, + "GSM8K": 7.58, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 127.0, + "Available on the hub": true, + "Model sha": "bf57045473f207bb1de1ed035ace226f4d9f9bba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/kuchiki-l2-7b", + "Average \u2b06\ufe0f": 51.33, + "ARC": 54.35, + "HellaSwag": 78.44, + "MMLU": 47.74, + "TruthfulQA": 49.88, + "Winogrande": 73.09, + "GSM8K": 4.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "745c34e70aa92056e8cd79c1d16e8fcfe1797645", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jordiclive\/gpt4all-alpaca-oa-codealpaca-lora-13b", + "Average \u2b06\ufe0f": 51.33, + "ARC": 56.14, + "HellaSwag": 80.93, + "MMLU": 47.66, + "TruthfulQA": 39.48, + "Winogrande": 76.16, + "GSM8K": 7.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "13443d633eaa5b7e1a90ac9cdb4a4d51b1c8d0d1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Tap-M\/Luna-AI-Llama2-Uncensored", + "Average \u2b06\ufe0f": 51.29, + "ARC": 54.35, + "HellaSwag": 78.6, + "MMLU": 46.7, + "TruthfulQA": 45.5, + "Winogrande": 72.77, + "GSM8K": 9.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 121.0, + "Available on the hub": true, + "Model sha": "6b5e1067e412cc5750aec7415a065671df3618be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/zarablend-l2-7b", + "Average \u2b06\ufe0f": 51.29, + "ARC": 54.44, + "HellaSwag": 78.62, + "MMLU": 47.61, + "TruthfulQA": 49.38, + "Winogrande": 73.32, + "GSM8K": 4.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "8b14e71ae3f52c409a25e1ac98dd05e0bb91eaff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abdulrahman-nuzha\/finetuned-llama2-chat-5000-v2.0", + "Average \u2b06\ufe0f": 51.28, + "ARC": 52.05, + "HellaSwag": 76.13, + "MMLU": 46.33, + "TruthfulQA": 45.18, + "Winogrande": 72.3, + "GSM8K": 15.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3e740254650b5f41e77d04c66806e6a0d3145195", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Locutusque\/Rhino-Mistral-7B", + "Average \u2b06\ufe0f": 51.27, + "ARC": 48.12, + "HellaSwag": 71.42, + "MMLU": 48.95, + "TruthfulQA": 45.9, + "Winogrande": 71.11, + "GSM8K": 22.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "9d23ebfc46951058a44d99c3ee45abf0c55d08ef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hyunseoki\/ko-en-llama2-13b", + "Average \u2b06\ufe0f": 51.27, + "ARC": 58.19, + "HellaSwag": 81.89, + "MMLU": 52.02, + "TruthfulQA": 39.96, + "Winogrande": 74.82, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": false, + "Model sha": "2768cf6f955b65868ccbb20658e2cc444b2f3be9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "teknium\/OpenHermes-7B", + "Average \u2b06\ufe0f": 51.26, + "ARC": 56.14, + "HellaSwag": 78.32, + "MMLU": 48.62, + "TruthfulQA": 45.0, + "Winogrande": 74.51, + "GSM8K": 5.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "74edb1ad58d3d517ef46c4e2a31081084ecbc473", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Norquinal\/llama-2-7b-claude-chat-rp", + "Average \u2b06\ufe0f": 51.25, + "ARC": 54.95, + "HellaSwag": 80.05, + "MMLU": 47.03, + "TruthfulQA": 43.47, + "Winogrande": 74.74, + "GSM8K": 7.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "4309eedebe8ba5709e0cc7cf186cb783f3bc8060", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/zarablend-1.1-l2-7b", + "Average \u2b06\ufe0f": 51.25, + "ARC": 54.86, + "HellaSwag": 78.58, + "MMLU": 47.89, + "TruthfulQA": 49.0, + "Winogrande": 72.61, + "GSM8K": 4.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e46bfa43829cbea7608192a6d07bcc147387fdb7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LTC-AI-Labs\/L2-7b-Synthia-WVG-Test", + "Average \u2b06\ufe0f": 51.25, + "ARC": 55.97, + "HellaSwag": 77.89, + "MMLU": 49.48, + "TruthfulQA": 44.11, + "Winogrande": 74.11, + "GSM8K": 5.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "23ae02efba01c37abe3cff0fedc7d2d9644fe98e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/airoboros-l2-7b-2.2.1", + "Average \u2b06\ufe0f": 51.22, + "ARC": 55.03, + "HellaSwag": 80.06, + "MMLU": 47.64, + "TruthfulQA": 44.65, + "Winogrande": 73.8, + "GSM8K": 6.14, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "eafbba6fec094a17ca7bce6d9605cac97b90a483", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Harshvir\/Llama-2-7B-physics", + "Average \u2b06\ufe0f": 51.22, + "ARC": 52.9, + "HellaSwag": 77.71, + "MMLU": 48.83, + "TruthfulQA": 48.93, + "Winogrande": 71.9, + "GSM8K": 7.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5e66b59c145586266b2351a63f0cf1b4f62f5454", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ncsgobubble\/Llama-7B-rollercoaster_v2", + "Average \u2b06\ufe0f": 51.2, + "ARC": 52.82, + "HellaSwag": 78.22, + "MMLU": 49.8, + "TruthfulQA": 43.62, + "Winogrande": 73.16, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b099c0725af7e984a8dd9d4ba2af2230613aa367", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "klyang\/MentaLLaMA-chat-7B", + "Average \u2b06\ufe0f": 51.17, + "ARC": 52.82, + "HellaSwag": 76.1, + "MMLU": 47.51, + "TruthfulQA": 44.02, + "Winogrande": 70.4, + "GSM8K": 16.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "eb0b119279aada6404042c69763aaadb5be5000d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/koala-13B-HF", + "Average \u2b06\ufe0f": 51.16, + "ARC": 52.99, + "HellaSwag": 77.59, + "MMLU": 45.32, + "TruthfulQA": 50.23, + "Winogrande": 74.03, + "GSM8K": 6.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 41.0, + "Available on the hub": true, + "Model sha": "b20f96a0171ce4c0fa27d6048215ebe710521587", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "64bits\/LexPodLM-13B", + "Average \u2b06\ufe0f": 51.14, + "ARC": 57.76, + "HellaSwag": 81.04, + "MMLU": 48.38, + "TruthfulQA": 43.48, + "Winogrande": 76.16, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 64.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "3553d84037addc97678f99a3464be4c866a0c268", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FlagAlpha\/Llama2-Chinese-7b-Chat", + "Average \u2b06\ufe0f": 51.13, + "ARC": 52.39, + "HellaSwag": 77.52, + "MMLU": 47.72, + "TruthfulQA": 46.87, + "Winogrande": 74.27, + "GSM8K": 8.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 173.0, + "Available on the hub": true, + "Model sha": "4c3bc725f71898c6a1acd4ea98a2f8d74d1b1b6b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BelalTab\/finetuned-llama2-2048-v3.0", + "Average \u2b06\ufe0f": 51.13, + "ARC": 49.83, + "HellaSwag": 77.09, + "MMLU": 46.69, + "TruthfulQA": 46.21, + "Winogrande": 72.06, + "GSM8K": 14.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "474902c7d83bd67edbb732502e0fe4cf93ed1fc8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/vicuna-7b-v1.3-attention-sparsity-10", + "Average \u2b06\ufe0f": 51.13, + "ARC": 52.22, + "HellaSwag": 77.05, + "MMLU": 47.93, + "TruthfulQA": 46.87, + "Winogrande": 69.53, + "GSM8K": 13.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4f7d536f7c880d75aba888699771281b704485e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "chargoddard\/llama-2-26b-trenchcoat-stack", + "Average \u2b06\ufe0f": 51.13, + "ARC": 55.03, + "HellaSwag": 79.9, + "MMLU": 53.73, + "TruthfulQA": 40.48, + "Winogrande": 74.74, + "GSM8K": 2.88, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 25.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "075d67c3223f4b379ab7f997c3787cd0630d80f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vikash06\/doctorLLM", + "Average \u2b06\ufe0f": 51.12, + "ARC": 52.9, + "HellaSwag": 79.76, + "MMLU": 46.47, + "TruthfulQA": 42.52, + "Winogrande": 71.59, + "GSM8K": 13.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0c13f4e15ee967c85643bf6c72d673798ea0b7a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "totally-not-an-llm\/EverythingLM-13b-V3-16k", + "Average \u2b06\ufe0f": 51.11, + "ARC": 58.19, + "HellaSwag": 80.12, + "MMLU": 50.48, + "TruthfulQA": 45.18, + "Winogrande": 70.72, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "1de9244bfadb947f80872727f76790cbc76e7142", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PygmalionAI\/pygmalion-2-7b", + "Average \u2b06\ufe0f": 51.11, + "ARC": 54.01, + "HellaSwag": 78.23, + "MMLU": 49.11, + "TruthfulQA": 43.78, + "Winogrande": 75.14, + "GSM8K": 6.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 48.0, + "Available on the hub": true, + "Model sha": "983f8ad5c156f4a0e4d2b7b5f1146981ad2e8a8b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abdulrahman-nuzha\/finetuned-llama2-chat-5000-v1.0-squad", + "Average \u2b06\ufe0f": 51.09, + "ARC": 50.94, + "HellaSwag": 76.61, + "MMLU": 46.43, + "TruthfulQA": 44.45, + "Winogrande": 71.98, + "GSM8K": 16.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "67c1301cb8a9ea7eb6e2b2c1829719ef746465d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "umd-zhou-lab\/recycled-alpaca-7b-v2.0", + "Average \u2b06\ufe0f": 51.09, + "ARC": 54.18, + "HellaSwag": 77.98, + "MMLU": 46.79, + "TruthfulQA": 45.4, + "Winogrande": 71.35, + "GSM8K": 10.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "12ab9aed495d8129856fdc469ce3ec672c94e6a3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishek\/llama2guanacotest", + "Average \u2b06\ufe0f": 51.08, + "ARC": 51.62, + "HellaSwag": 77.55, + "MMLU": 48.49, + "TruthfulQA": 43.88, + "Winogrande": 73.16, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "679d17809939a0bf9b79bbb027898cbea64045b2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/Samantha-1.11-7b", + "Average \u2b06\ufe0f": 51.07, + "ARC": 55.03, + "HellaSwag": 79.12, + "MMLU": 40.51, + "TruthfulQA": 50.37, + "Winogrande": 74.19, + "GSM8K": 7.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "730cbd8f3077f3d24001aab714def991f1e4e7e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Wanfq\/FuseLLM-7B", + "Average \u2b06\ufe0f": 51.07, + "ARC": 53.24, + "HellaSwag": 78.72, + "MMLU": 47.93, + "TruthfulQA": 38.17, + "Winogrande": 74.03, + "GSM8K": 14.33, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "503725445dc3bd0377948b3042bda80fc957f85e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "deepseek-ai\/deepseek-moe-16b-base", + "Average \u2b06\ufe0f": 51.07, + "ARC": 53.24, + "HellaSwag": 79.77, + "MMLU": 46.31, + "TruthfulQA": 36.08, + "Winogrande": 73.72, + "GSM8K": 17.29, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 16.38, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "521d2bc4fb69a3f3ae565310fcc3b65f97af2580", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "beaugogh\/Llama2-7b-sharegpt4", + "Average \u2b06\ufe0f": 51.05, + "ARC": 55.72, + "HellaSwag": 80.94, + "MMLU": 47.47, + "TruthfulQA": 48.34, + "Winogrande": 71.19, + "GSM8K": 2.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "922d1d963ad1b042c30b774a818d9f6180c28075", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HWERI\/Llama2-7b-sharegpt4", + "Average \u2b06\ufe0f": 51.05, + "ARC": 55.72, + "HellaSwag": 80.94, + "MMLU": 47.47, + "TruthfulQA": 48.34, + "Winogrande": 71.19, + "GSM8K": 2.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "8ecaba5dd0e9929f5858cfe9f5f8cd8ba285c9e5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "heegyu\/WizardVicuna2-13b-hf", + "Average \u2b06\ufe0f": 51.05, + "ARC": 55.38, + "HellaSwag": 79.14, + "MMLU": 48.46, + "TruthfulQA": 42.43, + "Winogrande": 73.48, + "GSM8K": 7.43, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6cfd95e2dcdb6996afa9eb5c63273a1a3524c6c6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "minghaowu\/phi-2-OpenHermes-2.5", + "Average \u2b06\ufe0f": 51.05, + "ARC": 56.48, + "HellaSwag": 73.88, + "MMLU": 54.8, + "TruthfulQA": 48.1, + "Winogrande": 73.01, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "37ea7cc2653b7f5a6c53e95dca49f968a13a6d21", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mikael110\/llama-2-7b-guanaco-fp16", + "Average \u2b06\ufe0f": 51.04, + "ARC": 54.86, + "HellaSwag": 79.65, + "MMLU": 46.38, + "TruthfulQA": 43.83, + "Winogrande": 75.22, + "GSM8K": 6.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": false, + "Model sha": "f769fed10874af73ad12115efd044cb4a64506b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ziqingyang\/chinese-llama-2-13b", + "Average \u2b06\ufe0f": 51.04, + "ARC": 55.8, + "HellaSwag": 79.53, + "MMLU": 53.01, + "TruthfulQA": 38.24, + "Winogrande": 75.69, + "GSM8K": 3.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.97, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "484c8a18b02f95eb2b6f6302105cf9a329e76ec8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wang7776\/vicuna-7b-v1.3-sparsity-10", + "Average \u2b06\ufe0f": 51.02, + "ARC": 51.45, + "HellaSwag": 76.98, + "MMLU": 47.95, + "TruthfulQA": 46.88, + "Winogrande": 69.77, + "GSM8K": 13.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "134ecba330ed973ff11f87aefaa3b2e19af024b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Llama-2-7b-chat-hf-30-sparsity", + "Average \u2b06\ufe0f": 51.02, + "ARC": 52.47, + "HellaSwag": 76.58, + "MMLU": 45.57, + "TruthfulQA": 44.82, + "Winogrande": 69.61, + "GSM8K": 17.06, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c3d07c4f8b6a509334d0f63e5057e9447f01b318", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lorinma\/yi6B_Vicuna", + "Average \u2b06\ufe0f": 51.02, + "ARC": 46.16, + "HellaSwag": 69.3, + "MMLU": 58.43, + "TruthfulQA": 48.11, + "Winogrande": 65.67, + "GSM8K": 18.42, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4ba7237cc904a14240f426154dc5233ef47db9e4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Delcos\/Mistral-Pygmalion-7b", + "Average \u2b06\ufe0f": 51.02, + "ARC": 54.44, + "HellaSwag": 78.48, + "MMLU": 49.23, + "TruthfulQA": 41.82, + "Winogrande": 75.3, + "GSM8K": 6.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "4e5fa9ae7f572b4841b02c3f96d8a3c7a7e59521", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Norquinal\/llama-2-7b-claude-chat", + "Average \u2b06\ufe0f": 50.98, + "ARC": 54.44, + "HellaSwag": 80.66, + "MMLU": 46.74, + "TruthfulQA": 41.39, + "Winogrande": 74.9, + "GSM8K": 7.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "e65d34ed31cdcd2637f6284aa0605f30ef5a9381", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AlekseyKorshuk\/vic15-exp-syn-fight-cp3838", + "Average \u2b06\ufe0f": 50.97, + "ARC": 51.79, + "HellaSwag": 75.79, + "MMLU": 50.23, + "TruthfulQA": 49.61, + "Winogrande": 71.82, + "GSM8K": 6.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "91ce25dbdb67793ad1fcfdfd59f7603c2be65aea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "meta-llama\/Llama-2-7b-hf", + "Average \u2b06\ufe0f": 50.97, + "ARC": 53.07, + "HellaSwag": 78.59, + "MMLU": 46.87, + "TruthfulQA": 38.76, + "Winogrande": 74.03, + "GSM8K": 14.48, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1134.0, + "Available on the hub": false, + "Model sha": "e8f058fa738b6b308540024e9aa12e274e291f75", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "formulae\/Dorflan", + "Average \u2b06\ufe0f": 50.96, + "ARC": 54.44, + "HellaSwag": 75.78, + "MMLU": 51.36, + "TruthfulQA": 51.17, + "Winogrande": 72.61, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5d8e7e5764ace89e6ccd1deece33b0e8a4b4587b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/base_7b", + "Average \u2b06\ufe0f": 50.95, + "ARC": 53.16, + "HellaSwag": 78.59, + "MMLU": 46.78, + "TruthfulQA": 38.74, + "Winogrande": 73.88, + "GSM8K": 14.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7971b900b2e0b2b3657bc70f7cc2e1251b7ac155", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dfurman\/llama-2-7b-instruct-peft", + "Average \u2b06\ufe0f": 50.94, + "ARC": 51.19, + "HellaSwag": 78.92, + "MMLU": 46.63, + "TruthfulQA": 48.5, + "Winogrande": 74.43, + "GSM8K": 5.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0fc43413117187e0723cdac133068ab527c80fe2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PeanutJar\/LLaMa-2-PeanutButter_v18_B-7B", + "Average \u2b06\ufe0f": 50.94, + "ARC": 54.61, + "HellaSwag": 81.0, + "MMLU": 47.07, + "TruthfulQA": 41.93, + "Winogrande": 74.51, + "GSM8K": 6.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bc8c239cacf1e3211f05e27be67a74d84c12aea9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "davzoku\/cria-llama2-7b-v1.3", + "Average \u2b06\ufe0f": 50.93, + "ARC": 52.73, + "HellaSwag": 78.58, + "MMLU": 48.3, + "TruthfulQA": 45.58, + "Winogrande": 71.9, + "GSM8K": 8.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "163a5bec7b6f5aaa4667aa6a95746deff50ceab1", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Korabbit\/Llama-2-7b-chat-hf-afr-100step-v2", + "Average \u2b06\ufe0f": 50.89, + "ARC": 52.65, + "HellaSwag": 78.25, + "MMLU": 48.47, + "TruthfulQA": 45.18, + "Winogrande": 72.3, + "GSM8K": 8.49, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4ee3182f614473f9ea3b6e429b01872bc90e89f1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "deepseek-ai\/deepseek-coder-7b-instruct-v1.5", + "Average \u2b06\ufe0f": 50.89, + "ARC": 48.55, + "HellaSwag": 72.35, + "MMLU": 50.45, + "TruthfulQA": 46.73, + "Winogrande": 66.85, + "GSM8K": 20.39, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.91, + "Hub \u2764\ufe0f": 50.0, + "Available on the hub": true, + "Model sha": "2a050a4c59d687a85324d32e147517992117ed30", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Danielbrdz\/Barcenas-7b", + "Average \u2b06\ufe0f": 50.87, + "ARC": 55.12, + "HellaSwag": 77.4, + "MMLU": 49.27, + "TruthfulQA": 43.64, + "Winogrande": 73.64, + "GSM8K": 6.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "770fa73981a599e935c21a95b1817a553c726694", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-13b-2.1", + "Average \u2b06\ufe0f": 50.84, + "ARC": 55.12, + "HellaSwag": 80.24, + "MMLU": 50.89, + "TruthfulQA": 44.62, + "Winogrande": 71.9, + "GSM8K": 2.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "172e30e56e939f73d7d00a165c2d49cbd284481f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LTC-AI-Labs\/Guanaco-Vicuna-7B-L2", + "Average \u2b06\ufe0f": 50.83, + "ARC": 53.24, + "HellaSwag": 78.89, + "MMLU": 46.77, + "TruthfulQA": 42.75, + "Winogrande": 75.37, + "GSM8K": 7.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ba8e755feab0bbf90675dcb9f8875a42f92112a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Rijgersberg\/GEITje-7B-chat-v2", + "Average \u2b06\ufe0f": 50.79, + "ARC": 50.34, + "HellaSwag": 74.13, + "MMLU": 49.0, + "TruthfulQA": 43.55, + "Winogrande": 71.51, + "GSM8K": 16.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "7e45fc97dcf957b845a98605a08fa13506023d15", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tyson0420\/stack_llama_fil_ai", + "Average \u2b06\ufe0f": 50.79, + "ARC": 53.5, + "HellaSwag": 78.63, + "MMLU": 46.23, + "TruthfulQA": 38.72, + "Winogrande": 74.82, + "GSM8K": 12.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06deb8bab434bb45083a39aed732165bdec0fb0b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-llama2-13b-pretrain", + "Average \u2b06\ufe0f": 50.77, + "ARC": 53.92, + "HellaSwag": 79.1, + "MMLU": 51.25, + "TruthfulQA": 36.24, + "Winogrande": 75.53, + "GSM8K": 8.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.97, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f87d66f9c4541c575a6fad3c19a31b11568e0dfb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PeanutJar\/LLaMa-2-PeanutButter_v10-7B", + "Average \u2b06\ufe0f": 50.75, + "ARC": 55.29, + "HellaSwag": 81.69, + "MMLU": 46.97, + "TruthfulQA": 43.78, + "Winogrande": 70.88, + "GSM8K": 5.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f98bb987216448aa3aa89e575a7494fae8b68066", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "meta-llama\/Llama-2-7b-chat-hf", + "Average \u2b06\ufe0f": 50.74, + "ARC": 52.9, + "HellaSwag": 78.55, + "MMLU": 48.32, + "TruthfulQA": 45.57, + "Winogrande": 71.74, + "GSM8K": 7.35, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 2867.0, + "Available on the hub": false, + "Model sha": "b7701a9e825e79a5ab18b5801be113c2160cc627", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-timedial-unit-080082", + "Average \u2b06\ufe0f": 50.74, + "ARC": 52.82, + "HellaSwag": 76.07, + "MMLU": 50.47, + "TruthfulQA": 43.54, + "Winogrande": 73.72, + "GSM8K": 7.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "372c90543ebb2a317fb9b51ff3890cc270e5ce3a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tyson0420\/stack_llama_fil_ai", + "Average \u2b06\ufe0f": 50.74, + "ARC": 53.75, + "HellaSwag": 78.59, + "MMLU": 46.5, + "TruthfulQA": 38.7, + "Winogrande": 74.74, + "GSM8K": 12.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06deb8bab434bb45083a39aed732165bdec0fb0b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "declare-lab\/starling-7B", + "Average \u2b06\ufe0f": 50.73, + "ARC": 51.02, + "HellaSwag": 76.77, + "MMLU": 47.75, + "TruthfulQA": 48.18, + "Winogrande": 70.56, + "GSM8K": 10.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "837b74bb8904dd025a2b5b2df8916800380d7c12", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "davzoku\/frankencria-llama2-12.5b-v1.3-m.2", + "Average \u2b06\ufe0f": 50.72, + "ARC": 55.03, + "HellaSwag": 79.17, + "MMLU": 46.16, + "TruthfulQA": 50.31, + "Winogrande": 70.24, + "GSM8K": 3.41, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 12.4, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b51db8ade612c1fe6979f4075310077b777e787c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-timedial-unit-080091", + "Average \u2b06\ufe0f": 50.71, + "ARC": 52.82, + "HellaSwag": 76.1, + "MMLU": 50.58, + "TruthfulQA": 43.4, + "Winogrande": 73.72, + "GSM8K": 7.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ae7e0fb58f4201bb14fd4e641d0d6dcc22674e0e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vikash06\/doctorLLM10k", + "Average \u2b06\ufe0f": 50.7, + "ARC": 54.95, + "HellaSwag": 79.94, + "MMLU": 44.4, + "TruthfulQA": 44.76, + "Winogrande": 70.01, + "GSM8K": 10.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "587b0f8bac27e0f316c41649186d93771d043472", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Mistral-7B-Instruct-v0.2-sparsity-20", + "Average \u2b06\ufe0f": 50.7, + "ARC": 52.65, + "HellaSwag": 76.71, + "MMLU": 47.27, + "TruthfulQA": 47.22, + "Winogrande": 69.06, + "GSM8K": 11.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "afbc5381ebc40d33832702045c8b6cd567f6f1f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tyson0420\/stack_llama-clang", + "Average \u2b06\ufe0f": 50.69, + "ARC": 54.1, + "HellaSwag": 78.93, + "MMLU": 45.97, + "TruthfulQA": 38.65, + "Winogrande": 74.11, + "GSM8K": 12.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "94d0bb2e81c094c2b0fc48d6c897827fd5650002", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "revolutionarybukhari\/Llama-2-7b-chat-finetune-AUTOMATE", + "Average \u2b06\ufe0f": 50.68, + "ARC": 53.07, + "HellaSwag": 75.59, + "MMLU": 48.8, + "TruthfulQA": 44.73, + "Winogrande": 73.24, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "55862462a23ab43fb73d4c784f1518ab4645764c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tyson0420\/stack_llama_full", + "Average \u2b06\ufe0f": 50.68, + "ARC": 54.27, + "HellaSwag": 78.76, + "MMLU": 45.55, + "TruthfulQA": 40.26, + "Winogrande": 73.48, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9a9a38b4d1c9b4d3f30f6407558470e74b1e56fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "psyche\/kollama2-7b-v2", + "Average \u2b06\ufe0f": 50.66, + "ARC": 53.33, + "HellaSwag": 78.5, + "MMLU": 43.61, + "TruthfulQA": 46.37, + "Winogrande": 75.61, + "GSM8K": 6.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "d5b6e9d5b882d4f6ba322396e027925ed915f848", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vonjack\/Qwen-LLaMAfied-HFTok-7B-Chat", + "Average \u2b06\ufe0f": 50.64, + "ARC": 50.51, + "HellaSwag": 83.65, + "MMLU": 51.53, + "TruthfulQA": 44.23, + "Winogrande": 71.43, + "GSM8K": 2.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": false, + "Model sha": "b8d5c09c83b1ef23668cb9209dbc43c0df2de8ae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-7b_10e4", + "Average \u2b06\ufe0f": 50.63, + "ARC": 53.84, + "HellaSwag": 78.46, + "MMLU": 46.76, + "TruthfulQA": 38.29, + "Winogrande": 73.48, + "GSM8K": 12.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "770088da097d9fe992d0847071d92e3af1923d90", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/vicuna-7b-v1.3-attention-sparsity-20", + "Average \u2b06\ufe0f": 50.63, + "ARC": 52.3, + "HellaSwag": 77.05, + "MMLU": 47.39, + "TruthfulQA": 46.62, + "Winogrande": 69.22, + "GSM8K": 11.22, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9ffb1e27f2672d68db2b5b2fb08d38e401e7c18d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LTC-AI-Labs\/L2-7b-Base-WVG-Uncensored", + "Average \u2b06\ufe0f": 50.63, + "ARC": 53.24, + "HellaSwag": 79.13, + "MMLU": 46.65, + "TruthfulQA": 42.59, + "Winogrande": 75.14, + "GSM8K": 7.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "67ede9be6ceffdf574294351cca937d88d7d448d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DopeorNope\/LaOT", + "Average \u2b06\ufe0f": 50.62, + "ARC": 55.63, + "HellaSwag": 78.96, + "MMLU": 50.3, + "TruthfulQA": 44.72, + "Winogrande": 74.11, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "df3a2c77a63a370405c7711b323e7ffa550cdd9e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zarakiquemparte\/zaraxls-l2-7b", + "Average \u2b06\ufe0f": 50.61, + "ARC": 54.44, + "HellaSwag": 78.94, + "MMLU": 50.39, + "TruthfulQA": 46.51, + "Winogrande": 73.16, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cc1dad50689b3ebcc1c9c67f275da6b4bb63e2ce", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "vikash06\/doctorLLM5k", + "Average \u2b06\ufe0f": 50.6, + "ARC": 52.47, + "HellaSwag": 79.66, + "MMLU": 44.68, + "TruthfulQA": 43.14, + "Winogrande": 69.53, + "GSM8K": 14.1, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e7b7ac695d46be0832e404a932f6e9a60159333a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Severian\/ANIMA-Nectar-v3", + "Average \u2b06\ufe0f": 50.58, + "ARC": 49.49, + "HellaSwag": 75.99, + "MMLU": 53.34, + "TruthfulQA": 46.16, + "Winogrande": 73.72, + "GSM8K": 4.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8ff9dd66d8cb8fba5c745e5bdb9928c4fc9889e4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Voicelab\/trurl-2-7b", + "Average \u2b06\ufe0f": 50.58, + "ARC": 53.41, + "HellaSwag": 75.29, + "MMLU": 50.0, + "TruthfulQA": 45.42, + "Winogrande": 72.22, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "e26ca5f157c60fc527170cc04db7fc0ea04ad26f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "guardrail\/llama-2-7b-guanaco-instruct-sharded", + "Average \u2b06\ufe0f": 50.58, + "ARC": 53.75, + "HellaSwag": 78.69, + "MMLU": 46.65, + "TruthfulQA": 43.93, + "Winogrande": 72.61, + "GSM8K": 7.81, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "fc7a3abbc3b9a9b3e163ef3c4844307ac270fca7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "maximuslee07\/llama-2-7b-rockwell-final", + "Average \u2b06\ufe0f": 50.55, + "ARC": 52.73, + "HellaSwag": 79.1, + "MMLU": 47.88, + "TruthfulQA": 47.21, + "Winogrande": 68.43, + "GSM8K": 7.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "de4cfe99e9e3db62733b40f48b2b11faf9abe4bf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "decruz07\/llama-2-7b-miniguanaco", + "Average \u2b06\ufe0f": 50.55, + "ARC": 49.06, + "HellaSwag": 75.59, + "MMLU": 46.14, + "TruthfulQA": 43.73, + "Winogrande": 72.61, + "GSM8K": 16.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ef3fa61b50387f5a982aa2578933dfc20afb7237", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-mmlu-val-mcq-7b-ep2", + "Average \u2b06\ufe0f": 50.55, + "ARC": 53.33, + "HellaSwag": 77.73, + "MMLU": 46.85, + "TruthfulQA": 43.87, + "Winogrande": 71.27, + "GSM8K": 10.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a6e6639ddaed9b2a8a549424f8c8a2d2bca241d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lazycuber\/L2-7b-Guanaco-Uncensored", + "Average \u2b06\ufe0f": 50.55, + "ARC": 50.6, + "HellaSwag": 76.99, + "MMLU": 48.93, + "TruthfulQA": 43.42, + "Winogrande": 75.37, + "GSM8K": 7.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9d49378c69c00113cf7f6e66d1ddb9d9b003dddc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Rijgersberg\/GEITje-7B", + "Average \u2b06\ufe0f": 50.53, + "ARC": 44.8, + "HellaSwag": 75.31, + "MMLU": 50.1, + "TruthfulQA": 40.45, + "Winogrande": 72.38, + "GSM8K": 20.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "80064d11c557eb1e0ddb52ed060d0e152c764c7c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/trurl-2-7b-pl-instruct_unload", + "Average \u2b06\ufe0f": 50.52, + "ARC": 53.16, + "HellaSwag": 74.64, + "MMLU": 49.89, + "TruthfulQA": 45.74, + "Winogrande": 72.3, + "GSM8K": 7.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "768d800e4dbe3fc95334f30ca7cd02113d3e3fd3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Technoculture\/mtor-2x7b", + "Average \u2b06\ufe0f": 50.5, + "ARC": 55.2, + "HellaSwag": 73.6, + "MMLU": 51.83, + "TruthfulQA": 48.06, + "Winogrande": 70.64, + "GSM8K": 3.64, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 11.07, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fbc4cdb251bf62307529a45f5ad267eb259761cc", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "922-CA\/monika-ddlc-7b-v1", + "Average \u2b06\ufe0f": 50.49, + "ARC": 54.95, + "HellaSwag": 76.78, + "MMLU": 45.61, + "TruthfulQA": 43.94, + "Winogrande": 72.85, + "GSM8K": 8.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4157d696bb0015da3ba26a58c1d24925515e4125", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jilp00\/OpenHermes-Symbolic-Mistral-7B", + "Average \u2b06\ufe0f": 50.46, + "ARC": 54.86, + "HellaSwag": 72.55, + "MMLU": 61.8, + "TruthfulQA": 45.35, + "Winogrande": 66.22, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d231c07fea44298a7fa33f84a0179fb1d683a94d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "WizardLM\/WizardCoder-Python-34B-V1.0", + "Average \u2b06\ufe0f": 50.46, + "ARC": 52.13, + "HellaSwag": 74.78, + "MMLU": 49.15, + "TruthfulQA": 48.85, + "Winogrande": 68.35, + "GSM8K": 9.48, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 726.0, + "Available on the hub": true, + "Model sha": "5cdc34e4a81d202f1d4a3b5d60e028aab895dfeb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jilp00\/OpenHermes-Symbolic-Mistral-7B", + "Average \u2b06\ufe0f": 50.45, + "ARC": 54.78, + "HellaSwag": 72.56, + "MMLU": 61.96, + "TruthfulQA": 45.28, + "Winogrande": 66.22, + "GSM8K": 1.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d231c07fea44298a7fa33f84a0179fb1d683a94d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lazycuber\/L2-7b-Base-Guanaco-Uncensored", + "Average \u2b06\ufe0f": 50.45, + "ARC": 52.22, + "HellaSwag": 79.08, + "MMLU": 46.63, + "TruthfulQA": 42.97, + "Winogrande": 74.51, + "GSM8K": 7.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dd51a3b26ad378e2953c947a1e4c2f8febe0cb52", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openthaigpt\/openthaigpt-1.0.0-beta-13b-chat-hf", + "Average \u2b06\ufe0f": 50.45, + "ARC": 53.58, + "HellaSwag": 79.09, + "MMLU": 51.13, + "TruthfulQA": 44.16, + "Winogrande": 73.88, + "GSM8K": 0.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "e800c7aec39678c5c0f30b0af16cb43800a0d379", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NurtureAI\/MistralLite-11B", + "Average \u2b06\ufe0f": 50.43, + "ARC": 57.68, + "HellaSwag": 79.54, + "MMLU": 50.09, + "TruthfulQA": 38.27, + "Winogrande": 76.64, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1a327551e7b2b4fdfbe27fcdb03d1cf5cbffdab4", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "chavinlo\/gpt4-x-alpaca", + "Average \u2b06\ufe0f": 50.41, + "ARC": 52.82, + "HellaSwag": 79.59, + "MMLU": 48.19, + "TruthfulQA": 48.88, + "Winogrande": 70.17, + "GSM8K": 2.81, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 477.0, + "Available on the hub": false, + "Model sha": "6a571f458cab9a23d14324ec63e0abd1744c8353", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/Llama-2-7b-hf-eli5-cleaned-1024_qlora_merged", + "Average \u2b06\ufe0f": 50.4, + "ARC": 53.67, + "HellaSwag": 78.21, + "MMLU": 45.9, + "TruthfulQA": 46.13, + "Winogrande": 73.8, + "GSM8K": 4.7, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1295069e9fef63aed87d36fe108d6c934cb34ded", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheTravellingEngineer\/llama2-7b-chat-hf-dpo", + "Average \u2b06\ufe0f": 50.38, + "ARC": 53.67, + "HellaSwag": 78.79, + "MMLU": 46.78, + "TruthfulQA": 43.97, + "Winogrande": 71.74, + "GSM8K": 7.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ec98429034fc84a4555dd4e3db4d6af534a03832", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ConvexAI\/Pelican-9b-v0.1", + "Average \u2b06\ufe0f": 50.38, + "ARC": 47.95, + "HellaSwag": 66.22, + "MMLU": 62.85, + "TruthfulQA": 50.61, + "Winogrande": 74.66, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 9.86, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "35f2317f2c1b892daf81011b4b46332f59430f70", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NewstaR\/Koss-7B-chat", + "Average \u2b06\ufe0f": 50.37, + "ARC": 53.67, + "HellaSwag": 78.79, + "MMLU": 46.72, + "TruthfulQA": 43.97, + "Winogrande": 71.74, + "GSM8K": 7.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b1ab836d9ebf7029fafa07949b51d3838501d537", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-7b-delta-v1.1", + "Average \u2b06\ufe0f": 50.37, + "ARC": 53.67, + "HellaSwag": 77.5, + "MMLU": 45.61, + "TruthfulQA": 48.95, + "Winogrande": 70.96, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 201.0, + "Available on the hub": false, + "Model sha": "24fb8e1e9cc78e0aa7ef154b026c4a83296e3fc4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Ejafa\/vicuna_7B_vanilla_1.1", + "Average \u2b06\ufe0f": 50.37, + "ARC": 53.67, + "HellaSwag": 77.46, + "MMLU": 45.63, + "TruthfulQA": 48.94, + "Winogrande": 70.96, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "d971d788db19648ad16bf77ec3f1de35ebf9a8e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eachadea\/vicuna-7b-1.1", + "Average \u2b06\ufe0f": 50.37, + "ARC": 53.67, + "HellaSwag": 77.46, + "MMLU": 45.63, + "TruthfulQA": 48.94, + "Winogrande": 70.96, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 109.0, + "Available on the hub": true, + "Model sha": "9d8eea215e00b388a22e8f050768ea8911d41f1d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "joehuangx\/spatial-vicuna-7b-v1.5-LoRA", + "Average \u2b06\ufe0f": 50.36, + "ARC": 50.77, + "HellaSwag": 74.63, + "MMLU": 48.13, + "TruthfulQA": 49.36, + "Winogrande": 72.38, + "GSM8K": 6.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dc71924cfb214b91461d35178e6ea6fef7946f13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-timedial", + "Average \u2b06\ufe0f": 50.35, + "ARC": 52.9, + "HellaSwag": 76.29, + "MMLU": 50.47, + "TruthfulQA": 41.6, + "Winogrande": 73.56, + "GSM8K": 7.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1e1709818cca48af4cd31c07c493f996854aa10f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ValiantLabs\/Fireplace-13b", + "Average \u2b06\ufe0f": 50.34, + "ARC": 47.7, + "HellaSwag": 69.61, + "MMLU": 43.56, + "TruthfulQA": 48.24, + "Winogrande": 67.17, + "GSM8K": 25.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1c37006534c4352f19c0b7ee857ed00601644068", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/vicuna-7b-v1.3-attention-sparsity-30", + "Average \u2b06\ufe0f": 50.33, + "ARC": 51.02, + "HellaSwag": 76.41, + "MMLU": 46.83, + "TruthfulQA": 46.06, + "Winogrande": 69.3, + "GSM8K": 12.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "df0a01a17930aed8715cc6ab508dffdbb15ee240", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "willnguyen\/lacda-2-7B-chat-v0.1", + "Average \u2b06\ufe0f": 50.29, + "ARC": 53.07, + "HellaSwag": 77.57, + "MMLU": 46.03, + "TruthfulQA": 44.57, + "Winogrande": 74.19, + "GSM8K": 6.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "afca346816726b83e331bb4d93246ed5146e1675", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beomi\/Yi-Ko-6B", + "Average \u2b06\ufe0f": 50.27, + "ARC": 48.89, + "HellaSwag": 74.48, + "MMLU": 55.72, + "TruthfulQA": 37.09, + "Winogrande": 72.93, + "GSM8K": 12.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.18, + "Hub \u2764\ufe0f": 30.0, + "Available on the hub": true, + "Model sha": "8f2f500574cd3c2972f05b7ae6e2807819cce051", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rishiraj\/smol-3b", + "Average \u2b06\ufe0f": 50.27, + "ARC": 46.33, + "HellaSwag": 68.23, + "MMLU": 46.33, + "TruthfulQA": 50.73, + "Winogrande": 65.35, + "GSM8K": 24.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 3.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "21c18e02cbd8becf5cb48eaff485379b6d62a2cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "starmpcc\/Asclepius-Llama2-13B", + "Average \u2b06\ufe0f": 50.25, + "ARC": 55.89, + "HellaSwag": 79.66, + "MMLU": 52.38, + "TruthfulQA": 40.76, + "Winogrande": 72.69, + "GSM8K": 0.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "579271bebb894d89369205060d151120a217ce81", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/tulu-7B-fp16", + "Average \u2b06\ufe0f": 50.24, + "ARC": 50.17, + "HellaSwag": 77.04, + "MMLU": 47.63, + "TruthfulQA": 41.61, + "Winogrande": 73.8, + "GSM8K": 11.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "8a026683f79119643f4007da4e9155c7849792cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/Llama-2-7b-hf-instruct-pl-lora_unload", + "Average \u2b06\ufe0f": 50.23, + "ARC": 53.75, + "HellaSwag": 78.34, + "MMLU": 46.8, + "TruthfulQA": 42.34, + "Winogrande": 73.95, + "GSM8K": 6.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3dfef350be9c8ce92c2d314dbe96a002bd6ca97d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GeneZC\/MiniChat-1.5-3B", + "Average \u2b06\ufe0f": 50.23, + "ARC": 46.5, + "HellaSwag": 68.28, + "MMLU": 46.67, + "TruthfulQA": 50.71, + "Winogrande": 65.04, + "GSM8K": 24.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": true, + "Model sha": "886af9601d57d8675c09bab02144b68366cd4437", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "vishesht27\/22-Neuro_Model", + "Average \u2b06\ufe0f": 50.23, + "ARC": 49.15, + "HellaSwag": 62.31, + "MMLU": 62.01, + "TruthfulQA": 60.23, + "Winogrande": 66.54, + "GSM8K": 1.14, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "807caffa6064420c088fadb9f2d34012da6b3236", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "conceptofmind\/LLongMA-2-13b-16k", + "Average \u2b06\ufe0f": 50.22, + "ARC": 54.27, + "HellaSwag": 79.63, + "MMLU": 50.97, + "TruthfulQA": 37.71, + "Winogrande": 72.77, + "GSM8K": 5.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c2defe28e2f3f10460baf8f778b00986a53aa7a2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kashif\/stack-llama-2", + "Average \u2b06\ufe0f": 50.21, + "ARC": 53.07, + "HellaSwag": 78.57, + "MMLU": 46.8, + "TruthfulQA": 38.75, + "Winogrande": 74.03, + "GSM8K": 10.01, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "28a206689c0097738177840a40e455a308db2d7d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Korabbit\/Llama-2-7b-chat-hf-afr-200step-v2", + "Average \u2b06\ufe0f": 50.21, + "ARC": 51.79, + "HellaSwag": 77.41, + "MMLU": 48.55, + "TruthfulQA": 43.69, + "Winogrande": 71.9, + "GSM8K": 7.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a3575a542e1dc3db4a7794b8f36b104c93b39875", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elliotthwang\/elliott_Llama-2-7b-hf", + "Average \u2b06\ufe0f": 50.2, + "ARC": 53.16, + "HellaSwag": 78.33, + "MMLU": 47.09, + "TruthfulQA": 42.11, + "Winogrande": 73.64, + "GSM8K": 6.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ac5d22e14c2c7a400519da5d12d88e4fe683ccfa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "RatanRohith\/SRBOSGPT-7B-slerp", + "Average \u2b06\ufe0f": 50.19, + "ARC": 49.15, + "HellaSwag": 62.28, + "MMLU": 61.95, + "TruthfulQA": 60.23, + "Winogrande": 66.54, + "GSM8K": 0.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "037f68c68da7ff3f981534f6deec3c85e86a9a86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "edor\/Platypus2-mini-7B", + "Average \u2b06\ufe0f": 50.18, + "ARC": 53.33, + "HellaSwag": 78.81, + "MMLU": 45.58, + "TruthfulQA": 42.0, + "Winogrande": 75.14, + "GSM8K": 6.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "4ede4a6f8a8d6cc3bfff8b98837116c74c280f63", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-7b_10e5", + "Average \u2b06\ufe0f": 50.17, + "ARC": 53.84, + "HellaSwag": 78.32, + "MMLU": 46.16, + "TruthfulQA": 38.97, + "Winogrande": 73.16, + "GSM8K": 10.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "43d9d3339870dfcce7a8775a2b4284c25dbeba66", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "haoranxu\/ALMA-13B", + "Average \u2b06\ufe0f": 50.16, + "ARC": 56.83, + "HellaSwag": 80.29, + "MMLU": 49.92, + "TruthfulQA": 37.57, + "Winogrande": 76.32, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "6798d9501a71b203be0610e640ec92fc08ea8dc6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "quantumaikr\/llama-2-7b-hf-guanaco-1k", + "Average \u2b06\ufe0f": 50.13, + "ARC": 51.62, + "HellaSwag": 76.73, + "MMLU": 47.45, + "TruthfulQA": 44.79, + "Winogrande": 72.77, + "GSM8K": 7.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "bdb57c5c992872ced47f48cb2177a5fa159f926a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheTravellingEngineer\/llama2-7b-hf-guanaco", + "Average \u2b06\ufe0f": 50.12, + "ARC": 52.47, + "HellaSwag": 78.75, + "MMLU": 45.33, + "TruthfulQA": 43.9, + "Winogrande": 74.19, + "GSM8K": 6.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "6c1fc95e67b11f1011a3b2fc1aa05c7b83251e40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TinyPixel\/elm-test", + "Average \u2b06\ufe0f": 50.09, + "ARC": 53.16, + "HellaSwag": 78.98, + "MMLU": 47.04, + "TruthfulQA": 39.51, + "Winogrande": 74.35, + "GSM8K": 7.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "aa8f81624d897aa493474bcd96dc3feae9f7a535", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "conceptofmind\/LLongMA-2-13b-16k", + "Average \u2b06\ufe0f": 50.09, + "ARC": 54.27, + "HellaSwag": 79.66, + "MMLU": 50.86, + "TruthfulQA": 37.68, + "Winogrande": 72.61, + "GSM8K": 5.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c2defe28e2f3f10460baf8f778b00986a53aa7a2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/Llama-2-7B-32K-Instruct", + "Average \u2b06\ufe0f": 50.02, + "ARC": 51.11, + "HellaSwag": 78.51, + "MMLU": 46.11, + "TruthfulQA": 44.86, + "Winogrande": 73.88, + "GSM8K": 5.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 157.0, + "Available on the hub": true, + "Model sha": "35696b9a7ab330dcbe240ff76fb44ab1eccf45bf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheTravellingEngineer\/llama2-7b-chat-hf-guanaco", + "Average \u2b06\ufe0f": 50.02, + "ARC": 50.51, + "HellaSwag": 76.72, + "MMLU": 48.03, + "TruthfulQA": 43.36, + "Winogrande": 72.93, + "GSM8K": 8.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5d33696ee324899d52fc43794b46009fea08a9af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dhmeltzer\/llama-7b-SFT_eli5_wiki65k_1024_r_64_alpha_16_merged", + "Average \u2b06\ufe0f": 50.0, + "ARC": 53.75, + "HellaSwag": 78.76, + "MMLU": 46.02, + "TruthfulQA": 43.31, + "Winogrande": 73.48, + "GSM8K": 4.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6ba5416f618ed3e11b409326e84c36fa542f0951", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/llama-7b-SFT-qlora-eli5-wiki_DPO_ds_RM_top_2_1024_r_64_alpha_16", + "Average \u2b06\ufe0f": 49.98, + "ARC": 54.1, + "HellaSwag": 78.74, + "MMLU": 45.44, + "TruthfulQA": 43.4, + "Winogrande": 73.64, + "GSM8K": 4.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f1f3b9fdb1e2d8d8fa913d57a8fe15d7bdf72c20", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/Buttocks-7B-v1.1", + "Average \u2b06\ufe0f": 49.97, + "ARC": 54.61, + "HellaSwag": 75.61, + "MMLU": 50.22, + "TruthfulQA": 44.72, + "Winogrande": 68.9, + "GSM8K": 5.76, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "828ccce85f9dd3744a9438f140ffb8c06187d165", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TeeZee\/Buttocks-7B-v1.0", + "Average \u2b06\ufe0f": 49.97, + "ARC": 54.61, + "HellaSwag": 75.61, + "MMLU": 50.22, + "TruthfulQA": 44.72, + "Winogrande": 68.9, + "GSM8K": 5.76, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "42c97d578b5daab95a71c7c4b007e882fd91e774", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "garage-bAInd\/Platypus2-7B", + "Average \u2b06\ufe0f": 49.97, + "ARC": 55.2, + "HellaSwag": 78.84, + "MMLU": 49.83, + "TruthfulQA": 40.64, + "Winogrande": 73.48, + "GSM8K": 1.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "f784afa7887b0738d92ea470797582756f02e630", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "RoversX\/llama-2-7b-hf-small-shards-Samantha-V1-SFT", + "Average \u2b06\ufe0f": 49.96, + "ARC": 53.16, + "HellaSwag": 77.71, + "MMLU": 43.47, + "TruthfulQA": 45.28, + "Winogrande": 73.8, + "GSM8K": 6.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "c39cee3821269e7fdffa690c2d0836c74dfebd25", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abdulrahman-nuzha\/belal-finetuned-llama2-1024-v2.2", + "Average \u2b06\ufe0f": 49.96, + "ARC": 52.65, + "HellaSwag": 77.81, + "MMLU": 44.65, + "TruthfulQA": 40.02, + "Winogrande": 74.11, + "GSM8K": 10.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9981b2c54d1cbf0d7d11b0855e27dada1e99434c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CobraMamba\/mamba-gpt-7b", + "Average \u2b06\ufe0f": 49.96, + "ARC": 51.19, + "HellaSwag": 75.4, + "MMLU": 47.47, + "TruthfulQA": 42.06, + "Winogrande": 71.67, + "GSM8K": 11.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cb0b04b1bff7921614efbd87d5b87bac04c58d13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TinyPixel\/lima-test", + "Average \u2b06\ufe0f": 49.96, + "ARC": 53.07, + "HellaSwag": 78.88, + "MMLU": 46.42, + "TruthfulQA": 39.4, + "Winogrande": 74.03, + "GSM8K": 7.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4d6a006c6341f29b11c02f19bf9535f51b4da1b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Uncensored-Jordan-7B", + "Average \u2b06\ufe0f": 49.95, + "ARC": 51.28, + "HellaSwag": 77.37, + "MMLU": 45.69, + "TruthfulQA": 47.5, + "Winogrande": 71.11, + "GSM8K": 6.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "96a9fbe5aaef8410a8d0dad25f3cc97b408c4efb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mrm8488\/llama-2-coder-7b", + "Average \u2b06\ufe0f": 49.95, + "ARC": 54.01, + "HellaSwag": 78.35, + "MMLU": 46.25, + "TruthfulQA": 38.49, + "Winogrande": 75.45, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 48.0, + "Available on the hub": true, + "Model sha": "f21c0d5e3f9f8c5addf093358e6885afa9602296", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_llama2-7b_10e6", + "Average \u2b06\ufe0f": 49.92, + "ARC": 53.41, + "HellaSwag": 78.03, + "MMLU": 46.07, + "TruthfulQA": 38.78, + "Winogrande": 73.01, + "GSM8K": 10.24, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d355af2ca568135fe1a7fc403ac334345949f0d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "llm-agents\/tora-code-34b-v1.0", + "Average \u2b06\ufe0f": 49.92, + "ARC": 50.26, + "HellaSwag": 75.48, + "MMLU": 46.65, + "TruthfulQA": 39.62, + "Winogrande": 67.72, + "GSM8K": 19.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "cbb33eea774cc03d4363c424d81e8c9d58332274", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-deepseekcoder-33b-v16.1-32k", + "Average \u2b06\ufe0f": 49.91, + "ARC": 45.05, + "HellaSwag": 60.79, + "MMLU": 43.24, + "TruthfulQA": 44.49, + "Winogrande": 62.19, + "GSM8K": 43.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 33.4, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "afab8e521c80d127a2795539a48de4d93bd02e88", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aloobun\/Reyna-CoT-4B-v0.1", + "Average \u2b06\ufe0f": 49.91, + "ARC": 44.71, + "HellaSwag": 71.12, + "MMLU": 55.9, + "TruthfulQA": 43.09, + "Winogrande": 67.72, + "GSM8K": 16.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "39785f4cca88485960fb2eefe9845fa17a614d6d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lodrick-the-lafted\/Winged-Lagomorph-2x13B", + "Average \u2b06\ufe0f": 49.9, + "ARC": 47.95, + "HellaSwag": 69.39, + "MMLU": 44.5, + "TruthfulQA": 44.54, + "Winogrande": 67.4, + "GSM8K": 25.63, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 21.51, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "f3959f69559f531fb9202798baf641b4af90c1bb", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "PeanutJar\/LLaMa-2-PeanutButter_v18_A-7B", + "Average \u2b06\ufe0f": 49.88, + "ARC": 53.16, + "HellaSwag": 78.11, + "MMLU": 45.54, + "TruthfulQA": 40.37, + "Winogrande": 74.9, + "GSM8K": 7.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "15b2fa81418792841014f589e61d1d9e30457040", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wenge-research\/yayi-7b-llama2", + "Average \u2b06\ufe0f": 49.88, + "ARC": 54.78, + "HellaSwag": 77.94, + "MMLU": 41.35, + "TruthfulQA": 44.02, + "Winogrande": 74.51, + "GSM8K": 6.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": false, + "Model sha": "18a4ed38285c732efc583a4bd883b3a681f8d005", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TinyPixel\/testmodel2", + "Average \u2b06\ufe0f": 49.88, + "ARC": 53.24, + "HellaSwag": 78.78, + "MMLU": 46.61, + "TruthfulQA": 39.17, + "Winogrande": 73.8, + "GSM8K": 7.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cb1111653997cee2818ffcf13a1c37237ea2934d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lajonbot\/Llama-2-7b-chat-hf-instruct-pl-lora_unload", + "Average \u2b06\ufe0f": 49.86, + "ARC": 52.99, + "HellaSwag": 77.49, + "MMLU": 47.12, + "TruthfulQA": 42.61, + "Winogrande": 72.06, + "GSM8K": 6.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f838fda8d2b97effae1e8af4dbb6217eab14fb7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/MultiLoRA-llama2-mmlu", + "Average \u2b06\ufe0f": 49.82, + "ARC": 52.22, + "HellaSwag": 77.59, + "MMLU": 42.61, + "TruthfulQA": 40.93, + "Winogrande": 73.8, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5cd015af30f8676b65320c8e597f12389aa4c576", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psyche\/kollama2-7b", + "Average \u2b06\ufe0f": 49.81, + "ARC": 53.24, + "HellaSwag": 78.78, + "MMLU": 42.31, + "TruthfulQA": 44.56, + "Winogrande": 73.95, + "GSM8K": 5.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "48fca4ba1e2d31ff4fbe6856b9b93ad2d97da8b7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kodonho\/Solar-M-SakuraSolar-Mixed", + "Average \u2b06\ufe0f": 49.81, + "ARC": 45.9, + "HellaSwag": 58.56, + "MMLU": 64.51, + "TruthfulQA": 59.62, + "Winogrande": 70.24, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9d67378e58c9b6ec96d1712f5313a49b33028629", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TinyPixel\/testmodel-3", + "Average \u2b06\ufe0f": 49.79, + "ARC": 53.24, + "HellaSwag": 78.72, + "MMLU": 46.57, + "TruthfulQA": 38.75, + "Winogrande": 73.88, + "GSM8K": 7.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a1fbc4d8a2c1a3d211325bdff9e7f0539fa7a2b1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WizardLM\/WizardMath-7B-V1.0", + "Average \u2b06\ufe0f": 49.78, + "ARC": 54.1, + "HellaSwag": 79.55, + "MMLU": 45.97, + "TruthfulQA": 43.65, + "Winogrande": 72.69, + "GSM8K": 2.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 44.0, + "Available on the hub": true, + "Model sha": "06dbd3e0da08255c575e585cb82e0554c1d2707a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "elyza\/ELYZA-japanese-Llama-2-7b-instruct", + "Average \u2b06\ufe0f": 49.78, + "ARC": 53.16, + "HellaSwag": 78.25, + "MMLU": 47.07, + "TruthfulQA": 39.08, + "Winogrande": 73.24, + "GSM8K": 7.88, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 48.0, + "Available on the hub": true, + "Model sha": "48fa08b3098a23d3671e09565499a4cfbaff1923", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/vicuna-7b-v1.3", + "Average \u2b06\ufe0f": 49.78, + "ARC": 50.43, + "HellaSwag": 76.92, + "MMLU": 48.14, + "TruthfulQA": 47.01, + "Winogrande": 70.48, + "GSM8K": 5.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 119.0, + "Available on the hub": false, + "Model sha": "ac066c83424c4a7221aa10c0ebe074b24d3bcdb6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "undi95\/llama2-to-mistral-diff", + "Average \u2b06\ufe0f": 49.78, + "ARC": 53.41, + "HellaSwag": 78.56, + "MMLU": 46.43, + "TruthfulQA": 38.71, + "Winogrande": 74.03, + "GSM8K": 7.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "16c279c5e7d12b8a6ff7771881808ef253a406b9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheTravellingEngineer\/llama2-7b-chat-hf-v4", + "Average \u2b06\ufe0f": 49.78, + "ARC": 53.41, + "HellaSwag": 78.56, + "MMLU": 46.43, + "TruthfulQA": 38.71, + "Winogrande": 74.03, + "GSM8K": 7.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "405c54ec7aea0735996ef5ff6ede6c35ab930381", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-mixed-datasets-time-unit", + "Average \u2b06\ufe0f": 49.77, + "ARC": 51.79, + "HellaSwag": 76.41, + "MMLU": 49.58, + "TruthfulQA": 40.33, + "Winogrande": 73.4, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "26626ea669172be6bc8e6b2b0bc5f14aef8061aa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wenge-research\/yayi-7b-llama2", + "Average \u2b06\ufe0f": 49.75, + "ARC": 55.03, + "HellaSwag": 77.84, + "MMLU": 40.92, + "TruthfulQA": 44.02, + "Winogrande": 73.72, + "GSM8K": 6.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": false, + "Model sha": "f1a9e8d91e5b636cde3ea7fcf752a9f0234bd92a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/LongQLoRA-Llama2-7b-8k", + "Average \u2b06\ufe0f": 49.75, + "ARC": 52.47, + "HellaSwag": 78.11, + "MMLU": 45.37, + "TruthfulQA": 38.94, + "Winogrande": 72.06, + "GSM8K": 11.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d29069d302700fcbd9322c4b4189a0eac4bccaa7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "wang7776\/Mistral-7B-Instruct-v0.2-sparsity-30", + "Average \u2b06\ufe0f": 49.74, + "ARC": 51.11, + "HellaSwag": 75.72, + "MMLU": 46.54, + "TruthfulQA": 45.53, + "Winogrande": 68.98, + "GSM8K": 10.54, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8454c7220f153f57b84d789225a141e3cdc3ba00", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/llama-2-7b-hf_open-platypus", + "Average \u2b06\ufe0f": 49.73, + "ARC": 51.45, + "HellaSwag": 78.63, + "MMLU": 43.6, + "TruthfulQA": 43.71, + "Winogrande": 74.43, + "GSM8K": 6.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c7e776f3f3afc0fa22cb7aff0d00522e571e9b29", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yeen214\/test_llama2_7b", + "Average \u2b06\ufe0f": 49.73, + "ARC": 53.07, + "HellaSwag": 78.57, + "MMLU": 46.86, + "TruthfulQA": 38.75, + "Winogrande": 74.03, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "69a4886f51ed752216cdd7f41a584d14240126f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bongchoi\/test-llama2-7b", + "Average \u2b06\ufe0f": 49.73, + "ARC": 53.07, + "HellaSwag": 78.57, + "MMLU": 46.86, + "TruthfulQA": 38.75, + "Winogrande": 74.03, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ebe2e68699cb7ab6bb22688f265c89be2ac0fa6d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheTravellingEngineer\/llama2-7b-chat-hf-v2", + "Average \u2b06\ufe0f": 49.73, + "ARC": 53.07, + "HellaSwag": 78.57, + "MMLU": 46.8, + "TruthfulQA": 38.75, + "Winogrande": 74.03, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1c97650d4b919e2c6a2829778caa3a109935a58c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibranze\/araproje-llama2-7b-hf", + "Average \u2b06\ufe0f": 49.73, + "ARC": 53.07, + "HellaSwag": 78.57, + "MMLU": 46.8, + "TruthfulQA": 38.75, + "Winogrande": 74.03, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7fe54f507e762b0f62265813aef908765b1298c0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TaylorAI\/Flash-Llama-7B", + "Average \u2b06\ufe0f": 49.73, + "ARC": 53.07, + "HellaSwag": 78.57, + "MMLU": 46.8, + "TruthfulQA": 38.75, + "Winogrande": 74.03, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "27c84ef23d850582453e1cc2dcea13de48da090f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheTravellingEngineer\/llama2-7b-chat-hf-v4", + "Average \u2b06\ufe0f": 49.73, + "ARC": 53.07, + "HellaSwag": 78.57, + "MMLU": 46.8, + "TruthfulQA": 38.75, + "Winogrande": 74.03, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "405c54ec7aea0735996ef5ff6ede6c35ab930381", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NewstaR\/Starlight-7B", + "Average \u2b06\ufe0f": 49.73, + "ARC": 53.07, + "HellaSwag": 78.57, + "MMLU": 46.8, + "TruthfulQA": 38.75, + "Winogrande": 74.03, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1f7436c458ebc3d8d31b91091c1a7a48e942cd3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "davzoku\/cria-llama2-7b-v1.3_peft", + "Average \u2b06\ufe0f": 49.72, + "ARC": 51.45, + "HellaSwag": 77.35, + "MMLU": 46.47, + "TruthfulQA": 45.52, + "Winogrande": 70.8, + "GSM8K": 6.75, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6864fa8ee43fa4d6b4f3ae055bbf464a5dcca570", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ToolBench\/ToolLLaMA-7b-LoRA", + "Average \u2b06\ufe0f": 49.72, + "ARC": 52.99, + "HellaSwag": 78.62, + "MMLU": 46.87, + "TruthfulQA": 38.67, + "Winogrande": 74.35, + "GSM8K": 6.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "67f2e8af850049a86fb9ee8ef581deb0f51e58e6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/Llama-2-7b-hf-eli5-cleaned-wiki65k-1024_qlora_merged", + "Average \u2b06\ufe0f": 49.71, + "ARC": 53.67, + "HellaSwag": 78.09, + "MMLU": 45.63, + "TruthfulQA": 41.72, + "Winogrande": 73.56, + "GSM8K": 5.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2af3d3acb0466fef466512bc17b9bf57024629e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-class-shishya-ac-hal-13b-ep3", + "Average \u2b06\ufe0f": 49.7, + "ARC": 48.46, + "HellaSwag": 80.78, + "MMLU": 56.17, + "TruthfulQA": 39.32, + "Winogrande": 73.48, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5a8ccf2bf67a7ee21c3d3accc8a1c5b318677c25", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abdulrahman-nuzha\/belal-finetuned-llama2-v1.0", + "Average \u2b06\ufe0f": 49.7, + "ARC": 52.82, + "HellaSwag": 77.75, + "MMLU": 43.51, + "TruthfulQA": 39.09, + "Winogrande": 74.35, + "GSM8K": 10.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9280900648e021d222ebba3689e663d31227d9a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-mixed-datasets", + "Average \u2b06\ufe0f": 49.7, + "ARC": 51.71, + "HellaSwag": 76.44, + "MMLU": 50.13, + "TruthfulQA": 39.57, + "Winogrande": 73.24, + "GSM8K": 7.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9c74b9396ff6b33e7a7622e59aa1f46103d993fe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abdulrahman-nuzha\/finetuned-llama-v2.0", + "Average \u2b06\ufe0f": 49.67, + "ARC": 53.16, + "HellaSwag": 77.75, + "MMLU": 43.69, + "TruthfulQA": 39.08, + "Winogrande": 74.43, + "GSM8K": 9.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9ffa847a1a0b229ea9c218e865bcf20f78556a8e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "georgesung\/llama2_7b_chat_uncensored", + "Average \u2b06\ufe0f": 49.67, + "ARC": 53.58, + "HellaSwag": 78.66, + "MMLU": 44.49, + "TruthfulQA": 41.34, + "Winogrande": 74.11, + "GSM8K": 5.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 192.0, + "Available on the hub": true, + "Model sha": "e9a972b12c6b59bfbcf30fe3779c2c933ce755bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shibing624\/chinese-alpaca-plus-13b-hf", + "Average \u2b06\ufe0f": 49.66, + "ARC": 53.16, + "HellaSwag": 73.51, + "MMLU": 48.81, + "TruthfulQA": 45.32, + "Winogrande": 75.06, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 34.0, + "Available on the hub": true, + "Model sha": "a118d2c35573b9a70c6f5b56fba4b657f74ce00c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HuggingFaceH4\/starchat-beta", + "Average \u2b06\ufe0f": 49.66, + "ARC": 52.47, + "HellaSwag": 80.59, + "MMLU": 42.85, + "TruthfulQA": 47.22, + "Winogrande": 69.69, + "GSM8K": 5.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 15.52, + "Hub \u2764\ufe0f": 250.0, + "Available on the hub": true, + "Model sha": "b1bcda690655777373f57ea6614eb095ec2c886f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "togethercomputer\/Llama-2-7B-32K-Instruct", + "Average \u2b06\ufe0f": 49.65, + "ARC": 51.37, + "HellaSwag": 78.47, + "MMLU": 45.53, + "TruthfulQA": 45.01, + "Winogrande": 72.85, + "GSM8K": 4.7, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 157.0, + "Available on the hub": true, + "Model sha": "b050a6f17d46e32c4b90a30492f14746589f74b7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TaylorAI\/FLAN-Llama-7B-2_Llama2-7B-Flash_868_full_model", + "Average \u2b06\ufe0f": 49.64, + "ARC": 52.47, + "HellaSwag": 79.08, + "MMLU": 47.58, + "TruthfulQA": 37.14, + "Winogrande": 74.74, + "GSM8K": 6.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "819f3f384e37f8906a62a8048556c9e58e495c02", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-7b-2.1", + "Average \u2b06\ufe0f": 49.64, + "ARC": 54.44, + "HellaSwag": 78.68, + "MMLU": 44.45, + "TruthfulQA": 43.95, + "Winogrande": 74.11, + "GSM8K": 2.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "699491e2e73cc2936205db143f59c1a686b88f14", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/longchat-13b-16k", + "Average \u2b06\ufe0f": 49.64, + "ARC": 53.58, + "HellaSwag": 77.67, + "MMLU": 45.24, + "TruthfulQA": 47.07, + "Winogrande": 70.09, + "GSM8K": 4.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 131.0, + "Available on the hub": false, + "Model sha": "70e2e38b82f1e25d8b90b50fbfc2361123bef45f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "clibrain\/Llama-2-7b-ft-instruct-es", + "Average \u2b06\ufe0f": 49.63, + "ARC": 53.67, + "HellaSwag": 77.83, + "MMLU": 46.58, + "TruthfulQA": 38.82, + "Winogrande": 75.22, + "GSM8K": 5.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "b62f431c88b232204ea7046f9d906ae1daa68437", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jondurbin\/airocoder-34b-2.1", + "Average \u2b06\ufe0f": 49.61, + "ARC": 54.18, + "HellaSwag": 73.84, + "MMLU": 50.67, + "TruthfulQA": 40.7, + "Winogrande": 69.93, + "GSM8K": 8.34, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "f66e783ac783837b3f59f274ecf55f18a9221cd0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "malhajar\/meditron-7b-chat", + "Average \u2b06\ufe0f": 49.59, + "ARC": 50.77, + "HellaSwag": 75.37, + "MMLU": 40.49, + "TruthfulQA": 48.56, + "Winogrande": 73.16, + "GSM8K": 9.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "b2e32b581d1484c831654fb2c03d2d29e7f520d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "gywy\/llama2-13b-chinese-v2", + "Average \u2b06\ufe0f": 49.58, + "ARC": 53.92, + "HellaSwag": 74.64, + "MMLU": 49.74, + "TruthfulQA": 45.43, + "Winogrande": 71.59, + "GSM8K": 2.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "8f6b11ca4344ac230d6b55defa4e04e60a39f9b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sia-ai\/llama-2-7b-1-percent-open-orca-1000-steps-v0", + "Average \u2b06\ufe0f": 49.56, + "ARC": 51.28, + "HellaSwag": 78.75, + "MMLU": 44.68, + "TruthfulQA": 45.83, + "Winogrande": 74.11, + "GSM8K": 2.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a893ebef4b818de1968dd9e932da2f513d16386a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dotvignesh\/perry-7b", + "Average \u2b06\ufe0f": 49.55, + "ARC": 51.79, + "HellaSwag": 76.43, + "MMLU": 46.18, + "TruthfulQA": 40.08, + "Winogrande": 72.53, + "GSM8K": 10.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f35ae37b436637cd3e14d086324ccdaccfd69045", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CalderaAI\/13B-Ouroboros", + "Average \u2b06\ufe0f": 49.54, + "ARC": 57.42, + "HellaSwag": 82.11, + "MMLU": 51.43, + "TruthfulQA": 47.99, + "Winogrande": 57.85, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": false, + "Model sha": "97981254d4b0ac0d1472376f602c004670070fdd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-7b-gpt4-1.4.1", + "Average \u2b06\ufe0f": 49.54, + "ARC": 55.12, + "HellaSwag": 79.6, + "MMLU": 45.17, + "TruthfulQA": 40.29, + "Winogrande": 74.27, + "GSM8K": 2.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "77bdd1f049f27876c38b68782fc240518208f391", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jb723\/llama2-ko-7B-model", + "Average \u2b06\ufe0f": 49.52, + "ARC": 56.31, + "HellaSwag": 79.51, + "MMLU": 45.71, + "TruthfulQA": 40.98, + "Winogrande": 72.06, + "GSM8K": 2.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.67, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "03d23910fa0f9b0542ce7634cbcd36983321f55a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "llama-anon\/instruct-13b", + "Average \u2b06\ufe0f": 49.52, + "ARC": 56.14, + "HellaSwag": 80.27, + "MMLU": 47.89, + "TruthfulQA": 36.97, + "Winogrande": 73.56, + "GSM8K": 2.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "142e198df473fd0cd4370b0d50be5f57e1da399b", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "quantumaikr\/QuantumLM-7B", + "Average \u2b06\ufe0f": 49.51, + "ARC": 50.26, + "HellaSwag": 76.1, + "MMLU": 45.27, + "TruthfulQA": 46.25, + "Winogrande": 71.51, + "GSM8K": 7.66, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f44998432fb90d88094ddf42e57ec458877a197f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhinand\/tamil-llama-13b-base-v0.1", + "Average \u2b06\ufe0f": 49.5, + "ARC": 52.82, + "HellaSwag": 79.95, + "MMLU": 52.05, + "TruthfulQA": 36.56, + "Winogrande": 75.61, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6cbdb6b6088910459cd104b1752177ab52e7f892", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/zephyr-7b-beta-lora-mmlu-merged", + "Average \u2b06\ufe0f": 49.49, + "ARC": 52.82, + "HellaSwag": 76.12, + "MMLU": 37.82, + "TruthfulQA": 44.6, + "Winogrande": 71.35, + "GSM8K": 14.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9e73428dfba192ac2db8d9ec550254858af03ba6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rombodawg\/Everyone-Coder-33b-Base", + "Average \u2b06\ufe0f": 49.48, + "ARC": 45.99, + "HellaSwag": 61.71, + "MMLU": 44.05, + "TruthfulQA": 42.26, + "Winogrande": 63.06, + "GSM8K": 39.8, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 33.34, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "5f595eabc02a322d232e9d06e424e72606e9b0f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FreedomIntelligence\/AceGPT-7B", + "Average \u2b06\ufe0f": 49.47, + "ARC": 53.58, + "HellaSwag": 77.54, + "MMLU": 43.0, + "TruthfulQA": 38.75, + "Winogrande": 72.77, + "GSM8K": 11.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c907e27abebb1237ff62450b0e84cab7ad4dfb5f", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/Manticore-13B-Chat-Pyg-Guanaco-SuperHOT-8K-GPTQ", + "Average \u2b06\ufe0f": 49.47, + "ARC": 52.82, + "HellaSwag": 79.63, + "MMLU": 39.83, + "TruthfulQA": 52.55, + "Winogrande": 71.82, + "GSM8K": 0.15, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "bd3c66e626c81de4977f197e1534bd3dfa2f569d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "adamo1139\/LWM-7B-1M-1000000ctx-AEZAKMI-3_1-1702", + "Average \u2b06\ufe0f": 49.42, + "ARC": 51.19, + "HellaSwag": 77.08, + "MMLU": 43.12, + "TruthfulQA": 44.19, + "Winogrande": 72.06, + "GSM8K": 8.87, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fdb6787960ddbe5c867ad1b6e61793c9a76da740", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Fredithefish\/Guanaco-7B-Uncensored", + "Average \u2b06\ufe0f": 49.35, + "ARC": 52.13, + "HellaSwag": 78.77, + "MMLU": 43.42, + "TruthfulQA": 44.45, + "Winogrande": 73.09, + "GSM8K": 4.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "db068e363e66e5d4b131e1d7a42a3a849e406a9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-temporal-without-mctaco-1", + "Average \u2b06\ufe0f": 49.35, + "ARC": 49.49, + "HellaSwag": 75.93, + "MMLU": 47.47, + "TruthfulQA": 39.95, + "Winogrande": 71.35, + "GSM8K": 11.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f023eda0d38152e826136ecb988e8d2bdcc6f46c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rameshm\/llama-2-13b-mathgpt-v4", + "Average \u2b06\ufe0f": 49.35, + "ARC": 50.94, + "HellaSwag": 75.56, + "MMLU": 43.78, + "TruthfulQA": 41.96, + "Winogrande": 69.14, + "GSM8K": 14.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c5072a762070c6b3756385c63805348c155004b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ceadar-ie\/FinanceConnect-13B", + "Average \u2b06\ufe0f": 49.34, + "ARC": 55.12, + "HellaSwag": 77.73, + "MMLU": 52.08, + "TruthfulQA": 37.68, + "Winogrande": 71.82, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "9ed6c7154cd14d1a5cdbec603a3ae8c8ce05cb29", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "haoranxu\/ALMA-13B-R", + "Average \u2b06\ufe0f": 49.32, + "ARC": 55.55, + "HellaSwag": 79.45, + "MMLU": 49.52, + "TruthfulQA": 36.09, + "Winogrande": 75.3, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 59.0, + "Available on the hub": true, + "Model sha": "f0a3613c5da62cbe85fb90ea348932ddfc022b22", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-openllama-13b-v7-fp16", + "Average \u2b06\ufe0f": 49.31, + "ARC": 47.61, + "HellaSwag": 72.24, + "MMLU": 47.74, + "TruthfulQA": 48.73, + "Winogrande": 69.69, + "GSM8K": 9.86, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "8690c065bccd3e897ccbf3d8aa24b0216a6f5dba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "qualis2006\/llama-2-7b-int4-python-code-18k", + "Average \u2b06\ufe0f": 49.3, + "ARC": 52.13, + "HellaSwag": 78.55, + "MMLU": 46.25, + "TruthfulQA": 37.69, + "Winogrande": 74.98, + "GSM8K": 6.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "aed968a4b3f3b716064eb8b50c5ae24b38007627", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OdiaGenAI\/odia_llama2_7B_base", + "Average \u2b06\ufe0f": 49.3, + "ARC": 50.77, + "HellaSwag": 75.94, + "MMLU": 46.1, + "TruthfulQA": 37.27, + "Winogrande": 70.8, + "GSM8K": 14.94, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "d3782ee2a527fd90dcd86359ab19417936089538", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "namirocks\/mistral-tutor-model-7b-ep3", + "Average \u2b06\ufe0f": 49.29, + "ARC": 49.32, + "HellaSwag": 76.93, + "MMLU": 49.07, + "TruthfulQA": 47.73, + "Winogrande": 72.69, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "17fd803a0b6a2d94e0467882728b4df35c294abb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "LeoLM\/leo-hessianai-7b-chat", + "Average \u2b06\ufe0f": 49.29, + "ARC": 52.56, + "HellaSwag": 77.61, + "MMLU": 45.58, + "TruthfulQA": 44.89, + "Winogrande": 69.93, + "GSM8K": 5.16, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": false, + "Model sha": "7c343a501f5cd3b768d2f78d9941b760fd66815d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bofenghuang\/vigogne-7b-chat", + "Average \u2b06\ufe0f": 49.27, + "ARC": 52.47, + "HellaSwag": 78.35, + "MMLU": 39.51, + "TruthfulQA": 44.52, + "Winogrande": 73.16, + "GSM8K": 7.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "9af636df9c8693ea857b62442bd1c6c73d657dc6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "heegyu\/LIMA2-7b-hf", + "Average \u2b06\ufe0f": 49.27, + "ARC": 53.24, + "HellaSwag": 80.6, + "MMLU": 43.22, + "TruthfulQA": 44.74, + "Winogrande": 69.93, + "GSM8K": 3.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "6a1aa59cb7624f059728840ce68b20b1070ebdcb", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TehVenom\/Pygmalion-Vicuna-1.1-7b", + "Average \u2b06\ufe0f": 49.25, + "ARC": 52.82, + "HellaSwag": 78.66, + "MMLU": 43.61, + "TruthfulQA": 42.21, + "Winogrande": 71.98, + "GSM8K": 6.22, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": false, + "Model sha": "bdac596568769d1ba4af8df9a611eee9723adf29", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dhmeltzer\/llama-7b-SFT_ds_eli5_1024_r_64_alpha_16_merged", + "Average \u2b06\ufe0f": 49.22, + "ARC": 53.41, + "HellaSwag": 77.9, + "MMLU": 43.56, + "TruthfulQA": 40.81, + "Winogrande": 74.59, + "GSM8K": 5.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6ca41503b383c654aee8d5496e70fbdfaa33db10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KnutJaegersberg\/YaYi-30b-EverythingLM", + "Average \u2b06\ufe0f": 49.19, + "ARC": 37.97, + "HellaSwag": 61.05, + "MMLU": 69.63, + "TruthfulQA": 49.74, + "Winogrande": 62.83, + "GSM8K": 13.95, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.4, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5e1c06e0d4c54df59355b6d2fb4e868bf8922346", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "venkycs\/llama-v2-7b-32kC-Security", + "Average \u2b06\ufe0f": 49.19, + "ARC": 49.83, + "HellaSwag": 77.33, + "MMLU": 44.41, + "TruthfulQA": 47.96, + "Winogrande": 71.74, + "GSM8K": 3.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0ae2abdc539a79ad84b141f894d614adf3754882", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wahaha1987\/llama_7b_sharegpt94k_fastchat", + "Average \u2b06\ufe0f": 49.19, + "ARC": 53.24, + "HellaSwag": 76.94, + "MMLU": 44.64, + "TruthfulQA": 45.34, + "Winogrande": 70.64, + "GSM8K": 4.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "2d82abff150b7a5ae484f9cd7c64c72fd4eaf7f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PocketDoc\/Dans-RetroRodeo-13b", + "Average \u2b06\ufe0f": 49.15, + "ARC": 53.84, + "HellaSwag": 79.63, + "MMLU": 48.93, + "TruthfulQA": 38.73, + "Winogrande": 73.8, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "102f9fdad903f5eaffe1ed8173ae56081072e429", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/vicuna-7B-physics", + "Average \u2b06\ufe0f": 49.15, + "ARC": 49.49, + "HellaSwag": 75.88, + "MMLU": 46.58, + "TruthfulQA": 49.31, + "Winogrande": 69.38, + "GSM8K": 4.25, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2147983e9493347c3424c07403f65e7a81c0b19f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elyza\/ELYZA-japanese-Llama-2-7b-fast-instruct", + "Average \u2b06\ufe0f": 49.15, + "ARC": 53.75, + "HellaSwag": 77.55, + "MMLU": 46.85, + "TruthfulQA": 38.84, + "Winogrande": 71.59, + "GSM8K": 6.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 64.0, + "Available on the hub": true, + "Model sha": "89de33d1ad568855853196802aeaecd799c6586f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Unbabel\/TowerBase-7B-v0.1", + "Average \u2b06\ufe0f": 49.11, + "ARC": 51.02, + "HellaSwag": 77.68, + "MMLU": 43.48, + "TruthfulQA": 37.29, + "Winogrande": 72.06, + "GSM8K": 13.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 43.0, + "Available on the hub": true, + "Model sha": "227253877d67620f45c7b45ff22ead1dc6e03e4f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "whiterabbitneo\/WhiteRabbitNeo-13B", + "Average \u2b06\ufe0f": 49.11, + "ARC": 48.55, + "HellaSwag": 68.7, + "MMLU": 43.04, + "TruthfulQA": 44.58, + "Winogrande": 67.4, + "GSM8K": 22.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "594b9222df90074334697d0ed36ffeb3b478e9ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WhiteRabbitNeo\/WhiteRabbitNeo-13B-v1", + "Average \u2b06\ufe0f": 49.11, + "ARC": 48.55, + "HellaSwag": 68.7, + "MMLU": 43.04, + "TruthfulQA": 44.58, + "Winogrande": 67.4, + "GSM8K": 22.37, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 306.0, + "Available on the hub": true, + "Model sha": "594b9222df90074334697d0ed36ffeb3b478e9ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/scarlett-7b", + "Average \u2b06\ufe0f": 49.09, + "ARC": 57.17, + "HellaSwag": 80.27, + "MMLU": 36.11, + "TruthfulQA": 48.52, + "Winogrande": 72.14, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "0715b738e750830ba7213f26fe32fa1cc1bb15b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "itsliupeng\/llama2_7b_code", + "Average \u2b06\ufe0f": 49.05, + "ARC": 52.13, + "HellaSwag": 75.71, + "MMLU": 48.05, + "TruthfulQA": 38.76, + "Winogrande": 71.51, + "GSM8K": 8.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "0e6d1edd87c8753b55d280179c8fb0e65ebf5fa2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hiyouga\/Baichuan2-7B-Base-LLaMAfied", + "Average \u2b06\ufe0f": 48.99, + "ARC": 49.57, + "HellaSwag": 73.45, + "MMLU": 54.86, + "TruthfulQA": 37.54, + "Winogrande": 70.72, + "GSM8K": 7.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "dc5bda435771212fc73a8c6556fbdf4fcd87f96d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-mmlu-val-only-correct-mcq-7b-ep2", + "Average \u2b06\ufe0f": 48.96, + "ARC": 52.99, + "HellaSwag": 77.67, + "MMLU": 47.92, + "TruthfulQA": 43.17, + "Winogrande": 71.9, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f0606bca9bea0afdd1dd8c26f0664b65f4dc5967", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "llm-agents\/tora-code-34b-v1.0", + "Average \u2b06\ufe0f": 48.95, + "ARC": 50.43, + "HellaSwag": 75.54, + "MMLU": 46.78, + "TruthfulQA": 39.66, + "Winogrande": 68.19, + "GSM8K": 13.12, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "cbb33eea774cc03d4363c424d81e8c9d58332274", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "martyn\/mistral-megamerge-dare-7b", + "Average \u2b06\ufe0f": 48.93, + "ARC": 55.29, + "HellaSwag": 70.48, + "MMLU": 43.05, + "TruthfulQA": 51.08, + "Winogrande": 67.09, + "GSM8K": 6.6, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f116230ee12e55d1716b89e1b114dd2ee3d397bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PotatoOff\/HamSter-0.2", + "Average \u2b06\ufe0f": 48.91, + "ARC": 50.09, + "HellaSwag": 73.65, + "MMLU": 50.39, + "TruthfulQA": 49.63, + "Winogrande": 69.69, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "85cd65a8a1ac1fc2814a06e11640da72db25935a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xzuyn\/MedicWizard-7B", + "Average \u2b06\ufe0f": 48.88, + "ARC": 53.5, + "HellaSwag": 78.39, + "MMLU": 44.61, + "TruthfulQA": 41.32, + "Winogrande": 70.56, + "GSM8K": 4.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0b3ef975fb5e8ac1eae775160ab54c98221889df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ziqingyang\/chinese-alpaca-2-7b", + "Average \u2b06\ufe0f": 48.85, + "ARC": 49.57, + "HellaSwag": 72.62, + "MMLU": 46.5, + "TruthfulQA": 48.63, + "Winogrande": 70.01, + "GSM8K": 5.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ab2476bffedeed752daedd77e71900578e136e7c", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "openchat\/opencoderplus", + "Average \u2b06\ufe0f": 48.84, + "ARC": 50.6, + "HellaSwag": 78.22, + "MMLU": 42.73, + "TruthfulQA": 50.72, + "Winogrande": 66.14, + "GSM8K": 4.62, + "Type": "", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 104.0, + "Available on the hub": false, + "Model sha": "845e9e4452dd4440760b3d5f680400fc014e91b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dhmeltzer\/llama-7b-SFT_ds_wiki65k_1024_r_64_alpha_16_merged", + "Average \u2b06\ufe0f": 48.82, + "ARC": 54.35, + "HellaSwag": 78.06, + "MMLU": 45.35, + "TruthfulQA": 37.11, + "Winogrande": 73.4, + "GSM8K": 4.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "684c4f4612fadae47c2c7db9fe9e9be4aaafc7e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheTravellingEngineer\/llama2-7b-chat-hf-v3", + "Average \u2b06\ufe0f": 48.81, + "ARC": 52.22, + "HellaSwag": 76.78, + "MMLU": 45.89, + "TruthfulQA": 38.38, + "Winogrande": 73.4, + "GSM8K": 6.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a5269bc93a7f98e192e34553cec1302877ca4327", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-class-shishya-all-hal-7b-ep3", + "Average \u2b06\ufe0f": 48.75, + "ARC": 45.48, + "HellaSwag": 77.21, + "MMLU": 51.54, + "TruthfulQA": 44.83, + "Winogrande": 71.03, + "GSM8K": 2.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5a1424eb777c8a3ce94ab31486510da8f617d17e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "EleutherAI\/llemma_7b", + "Average \u2b06\ufe0f": 48.75, + "ARC": 46.16, + "HellaSwag": 62.98, + "MMLU": 47.87, + "TruthfulQA": 38.88, + "Winogrande": 63.3, + "GSM8K": 33.28, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 69.0, + "Available on the hub": true, + "Model sha": "acc26c54609e9f18bf31fc5d58b5b533239e0430", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/vicuna-7b-v1.3-instruct-pl-lora_unload", + "Average \u2b06\ufe0f": 48.74, + "ARC": 48.04, + "HellaSwag": 76.28, + "MMLU": 47.42, + "TruthfulQA": 44.4, + "Winogrande": 70.09, + "GSM8K": 6.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e4b19d9d6168b32402da4ab2b5ec7ff27cf40d9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "LeoLM\/leo-hessianai-7b-chat-bilingual", + "Average \u2b06\ufe0f": 48.72, + "ARC": 51.02, + "HellaSwag": 76.03, + "MMLU": 44.68, + "TruthfulQA": 47.16, + "Winogrande": 70.72, + "GSM8K": 2.73, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "5ee98fd03b310e3081f0c9986c5153b27ec5dce6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GOAT-AI\/GOAT-7B-Community", + "Average \u2b06\ufe0f": 48.71, + "ARC": 48.81, + "HellaSwag": 74.63, + "MMLU": 49.58, + "TruthfulQA": 42.48, + "Winogrande": 72.3, + "GSM8K": 4.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 36.0, + "Available on the hub": true, + "Model sha": "a7073a0f5142ce04aaa1603b0812b358f62a8de8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elyza\/ELYZA-japanese-Llama-2-7b", + "Average \u2b06\ufe0f": 48.7, + "ARC": 52.22, + "HellaSwag": 76.42, + "MMLU": 44.6, + "TruthfulQA": 37.92, + "Winogrande": 72.69, + "GSM8K": 8.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 65.0, + "Available on the hub": true, + "Model sha": "976887c5891284db204320860bb84b71d598063e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheTravellingEngineer\/llama2-7b-chat-hf-v3", + "Average \u2b06\ufe0f": 48.65, + "ARC": 51.96, + "HellaSwag": 76.7, + "MMLU": 45.36, + "TruthfulQA": 38.31, + "Winogrande": 73.56, + "GSM8K": 5.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a5269bc93a7f98e192e34553cec1302877ca4327", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fblgit\/una-llama-7b", + "Average \u2b06\ufe0f": 48.64, + "ARC": 53.67, + "HellaSwag": 80.07, + "MMLU": 37.37, + "TruthfulQA": 38.01, + "Winogrande": 72.93, + "GSM8K": 9.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6321d1b950c6a3997a424b20273d66cb2b9395a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dominguesm\/canarim-7b", + "Average \u2b06\ufe0f": 48.63, + "ARC": 51.96, + "HellaSwag": 77.52, + "MMLU": 40.92, + "TruthfulQA": 40.03, + "Winogrande": 71.43, + "GSM8K": 9.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "18d34bd9ad2d9674675b2e0d88dee9324b52f2b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PocketDoc\/Dans-CreepingSenseOfDoom", + "Average \u2b06\ufe0f": 48.58, + "ARC": 53.33, + "HellaSwag": 78.9, + "MMLU": 48.09, + "TruthfulQA": 37.84, + "Winogrande": 73.32, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "efc7cbc5d0461c137e8ea0c83e54bc5357188783", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-7b-gpt4-1.1", + "Average \u2b06\ufe0f": 48.57, + "ARC": 54.61, + "HellaSwag": 80.15, + "MMLU": 39.25, + "TruthfulQA": 41.22, + "Winogrande": 73.09, + "GSM8K": 3.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "5a45a16bac51ed9529a6dc2eab7355cc61eefb5b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/GML-Mistral-merged-v1", + "Average \u2b06\ufe0f": 48.54, + "ARC": 43.77, + "HellaSwag": 57.89, + "MMLU": 64.13, + "TruthfulQA": 51.58, + "Winogrande": 73.88, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3ec981e2e8c018f9e34a7553df2a2ed0d032dd37", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-class-shishya-13b-ep3", + "Average \u2b06\ufe0f": 48.52, + "ARC": 46.5, + "HellaSwag": 80.36, + "MMLU": 57.06, + "TruthfulQA": 35.0, + "Winogrande": 72.22, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "870fe04090a6a6cfe27d0bf4b06cc9f18dd4c67d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "namirocks\/student-model-13b-ep3", + "Average \u2b06\ufe0f": 48.52, + "ARC": 46.5, + "HellaSwag": 80.36, + "MMLU": 57.06, + "TruthfulQA": 35.0, + "Winogrande": 72.22, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1f21e9d0506e908a10d5e611d5f1c022fdee6585", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rinna\/youri-7b-chat", + "Average \u2b06\ufe0f": 48.51, + "ARC": 51.19, + "HellaSwag": 76.09, + "MMLU": 46.06, + "TruthfulQA": 41.17, + "Winogrande": 75.06, + "GSM8K": 1.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "96d1690c4a1fa192ab26c4be8f9c79e1faed8346", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "llm-agents\/tora-7b-v1.0", + "Average \u2b06\ufe0f": 48.5, + "ARC": 52.47, + "HellaSwag": 78.68, + "MMLU": 45.9, + "TruthfulQA": 37.9, + "Winogrande": 73.56, + "GSM8K": 2.5, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "717edbee98945192b1a396fc9c337c5b32d6c79c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yash21\/Mistral-Quantum-dpo", + "Average \u2b06\ufe0f": 48.5, + "ARC": 43.43, + "HellaSwag": 57.76, + "MMLU": 64.29, + "TruthfulQA": 51.49, + "Winogrande": 74.03, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8aba300293cd8abbf71517e7d7c80fe26bf07baa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/Pygmalion-13b-Merged", + "Average \u2b06\ufe0f": 48.49, + "ARC": 56.48, + "HellaSwag": 80.02, + "MMLU": 42.93, + "TruthfulQA": 35.86, + "Winogrande": 75.53, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": false, + "Model sha": "f96308083033c84db47b6c093da3817c085c87c7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "TheBloke\/Llama-2-7B-GPTQ", + "Average \u2b06\ufe0f": 48.48, + "ARC": 52.05, + "HellaSwag": 77.59, + "MMLU": 43.99, + "TruthfulQA": 39.32, + "Winogrande": 72.93, + "GSM8K": 5.0, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 9.05, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": true, + "Model sha": "ecd7ab9f6adc36ecbe0d751eeea0d90ae1863c3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/WizardLM-13B-Uncensored", + "Average \u2b06\ufe0f": 48.48, + "ARC": 50.94, + "HellaSwag": 76.64, + "MMLU": 43.96, + "TruthfulQA": 46.73, + "Winogrande": 70.56, + "GSM8K": 2.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9025c5f96fef9525da9238369ad082961b0e9494", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cognitivecomputations\/yayi2-30b-llama", + "Average \u2b06\ufe0f": 48.46, + "ARC": 35.67, + "HellaSwag": 53.37, + "MMLU": 70.6, + "TruthfulQA": 49.08, + "Winogrande": 63.14, + "GSM8K": 18.88, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.4, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "01b331f04153b84a4ac049e71fd122d891424756", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "medalpaca\/medalpaca-7b", + "Average \u2b06\ufe0f": 48.45, + "ARC": 54.1, + "HellaSwag": 80.42, + "MMLU": 41.47, + "TruthfulQA": 40.46, + "Winogrande": 71.19, + "GSM8K": 3.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 52.0, + "Available on the hub": true, + "Model sha": "b57b9f5ff34059e485b769973d023021fc66a8f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/vicuna-7B-chemical", + "Average \u2b06\ufe0f": 48.42, + "ARC": 49.83, + "HellaSwag": 74.42, + "MMLU": 44.1, + "TruthfulQA": 51.7, + "Winogrande": 67.17, + "GSM8K": 3.34, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "fbf6476ebfa856ffe743e41f8d4413c15b2127c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-7b-gpt4-1.4", + "Average \u2b06\ufe0f": 48.4, + "ARC": 53.92, + "HellaSwag": 80.33, + "MMLU": 38.61, + "TruthfulQA": 41.05, + "Winogrande": 72.77, + "GSM8K": 3.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "cae1ab8991f66bbe66ae95ed23a87846e7343047", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-7b-gpt4-2.0", + "Average \u2b06\ufe0f": 48.38, + "ARC": 52.9, + "HellaSwag": 78.53, + "MMLU": 45.09, + "TruthfulQA": 39.45, + "Winogrande": 71.11, + "GSM8K": 3.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "8432fe95c426ca7709cf2d31a64eee612c4dea42", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "AlpinDale\/pygmalion-instruct", + "Average \u2b06\ufe0f": 48.37, + "ARC": 52.56, + "HellaSwag": 77.65, + "MMLU": 35.94, + "TruthfulQA": 42.13, + "Winogrande": 72.06, + "GSM8K": 9.86, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1665b271316dfee05b2a8daf8b9d6c22ed0aef60", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LLMs\/AlpacaGPT4-7B-elina", + "Average \u2b06\ufe0f": 48.35, + "ARC": 55.03, + "HellaSwag": 78.79, + "MMLU": 37.5, + "TruthfulQA": 41.53, + "Winogrande": 72.69, + "GSM8K": 4.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": false, + "Model sha": "bbece5e3f8ee9be09c8defc536a95c6ef780c681", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Monero\/WizardLM-13b-OpenAssistant-Uncensored", + "Average \u2b06\ufe0f": 48.32, + "ARC": 48.55, + "HellaSwag": 76.03, + "MMLU": 43.15, + "TruthfulQA": 49.4, + "Winogrande": 69.77, + "GSM8K": 3.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "ff8e15fd68119d36ae1f0cebaa87f16e2ad3c732", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Juniplayground\/Mist_LLaMA-2-7B-1024_V3", + "Average \u2b06\ufe0f": 48.31, + "ARC": 51.37, + "HellaSwag": 77.74, + "MMLU": 41.34, + "TruthfulQA": 41.21, + "Winogrande": 73.32, + "GSM8K": 4.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "05ec8f4a568777e1e543acdf8a587e080fb18fba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Wizard-Vicuna-7B-Uncensored-HF", + "Average \u2b06\ufe0f": 48.27, + "ARC": 53.41, + "HellaSwag": 78.85, + "MMLU": 37.09, + "TruthfulQA": 43.48, + "Winogrande": 72.22, + "GSM8K": 4.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "b802f1b4401d0b2242137160c20cc11b9ffd3a4c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/Wizard-Vicuna-7B-Uncensored", + "Average \u2b06\ufe0f": 48.27, + "ARC": 53.41, + "HellaSwag": 78.85, + "MMLU": 37.09, + "TruthfulQA": 43.48, + "Winogrande": 72.22, + "GSM8K": 4.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1097285acd9c48a1d09bc0a9844d365384732111", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mayacinka\/frankencup-dpo", + "Average \u2b06\ufe0f": 48.26, + "ARC": 42.66, + "HellaSwag": 60.55, + "MMLU": 62.21, + "TruthfulQA": 50.72, + "Winogrande": 73.4, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9248c7340053361655743f40acd4b9c1b5d0815d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Nexusflow\/NexusRaven-V2-13B", + "Average \u2b06\ufe0f": 48.21, + "ARC": 45.14, + "HellaSwag": 67.4, + "MMLU": 44.88, + "TruthfulQA": 44.54, + "Winogrande": 66.38, + "GSM8K": 20.92, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 380.0, + "Available on the hub": true, + "Model sha": "3bec1dcc7cb6f1895a923e66d87438e903bebb57", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/3BigReasonCinder", + "Average \u2b06\ufe0f": 48.16, + "ARC": 41.72, + "HellaSwag": 65.16, + "MMLU": 44.79, + "TruthfulQA": 44.76, + "Winogrande": 64.96, + "GSM8K": 27.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 3.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ec1da6e96831dcebcc044280fb2ac5cd7e3d49ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-mctaco", + "Average \u2b06\ufe0f": 48.02, + "ARC": 45.65, + "HellaSwag": 75.65, + "MMLU": 49.27, + "TruthfulQA": 43.12, + "Winogrande": 69.93, + "GSM8K": 4.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "883b0fa4158de8207d0a94f4b8cb188e6250aa9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/multimaster-7b", + "Average \u2b06\ufe0f": 48.01, + "ARC": 41.04, + "HellaSwag": 75.0, + "MMLU": 46.93, + "TruthfulQA": 44.98, + "Winogrande": 68.35, + "GSM8K": 11.75, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ae4dbb285559be9ae6f1eb4bd75db30d08dde5c6", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "titan087\/OpenLlama13B-Guanaco", + "Average \u2b06\ufe0f": 47.99, + "ARC": 51.19, + "HellaSwag": 75.24, + "MMLU": 43.76, + "TruthfulQA": 38.4, + "Winogrande": 71.74, + "GSM8K": 7.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "42ed3023ae1afe861f533570be881a03b10fc860", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lmsys\/longchat-7b-v1.5-32k", + "Average \u2b06\ufe0f": 47.95, + "ARC": 51.71, + "HellaSwag": 74.97, + "MMLU": 43.16, + "TruthfulQA": 44.42, + "Winogrande": 68.67, + "GSM8K": 4.78, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 54.0, + "Available on the hub": false, + "Model sha": "16deb633ef4d6a18d5750239edc5a85ffeaf3918", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-l2-7b-gpt4-m2.0", + "Average \u2b06\ufe0f": 47.95, + "ARC": 50.51, + "HellaSwag": 76.87, + "MMLU": 45.35, + "TruthfulQA": 41.34, + "Winogrande": 69.53, + "GSM8K": 4.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "67729407add902e3d4d36bb105d7c011fb368ea5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "LLMs\/Stable-Vicuna-13B", + "Average \u2b06\ufe0f": 47.95, + "ARC": 53.41, + "HellaSwag": 78.57, + "MMLU": 50.37, + "TruthfulQA": 48.36, + "Winogrande": 56.99, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": false, + "Model sha": "51f3d9eaa71de287c96195abd0ff954839857b19", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TigerResearch\/tigerbot-7b-base", + "Average \u2b06\ufe0f": 47.93, + "ARC": 47.7, + "HellaSwag": 72.08, + "MMLU": 45.11, + "TruthfulQA": 42.27, + "Winogrande": 69.61, + "GSM8K": 10.84, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "300831494aa1eb16e59799310a09531f60dcc904", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "itsliupeng\/openllama-7b-icl", + "Average \u2b06\ufe0f": 47.93, + "ARC": 47.95, + "HellaSwag": 77.04, + "MMLU": 44.37, + "TruthfulQA": 37.06, + "Winogrande": 70.17, + "GSM8K": 10.99, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "d6317fed3b190cc4d4c27b9f27ccf7c77f0b2e3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vibhorag101\/llama-2-7b-chat-hf-phr_mental_health-2048", + "Average \u2b06\ufe0f": 47.92, + "ARC": 52.39, + "HellaSwag": 75.39, + "MMLU": 39.77, + "TruthfulQA": 42.89, + "Winogrande": 71.19, + "GSM8K": 5.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "81d424a431ab7fa4ff725925b6d0e4269d4563e4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DevaMalla\/llama_7b_qlora_pds-eval", + "Average \u2b06\ufe0f": 47.9, + "ARC": 53.92, + "HellaSwag": 78.13, + "MMLU": 32.98, + "TruthfulQA": 45.6, + "Winogrande": 72.61, + "GSM8K": 4.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d20419e1d9e9a6a59ced3edf5169e8e7b3e8394c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/Uncensored-Frank-7B", + "Average \u2b06\ufe0f": 47.9, + "ARC": 54.27, + "HellaSwag": 76.52, + "MMLU": 37.5, + "TruthfulQA": 43.86, + "Winogrande": 70.24, + "GSM8K": 5.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "65bbcb80158a6d2e133bba99a90142caf4e2e242", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "namirocks\/vicuna-tutor-shishya-model-7b-ep3", + "Average \u2b06\ufe0f": 47.9, + "ARC": 43.86, + "HellaSwag": 76.63, + "MMLU": 51.24, + "TruthfulQA": 43.53, + "Winogrande": 71.82, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e1c3514e5cec2e7c871adc85e27a19d596f2c70e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-class-shishya-ac-hal-7b-ep3", + "Average \u2b06\ufe0f": 47.89, + "ARC": 44.62, + "HellaSwag": 76.98, + "MMLU": 50.96, + "TruthfulQA": 43.03, + "Winogrande": 71.74, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a76df6b71b959745a5f1804791071332ee6522ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "synapsoft\/Llama-2-7b-chat-hf-flan2022-1.2M", + "Average \u2b06\ufe0f": 47.89, + "ARC": 49.57, + "HellaSwag": 76.25, + "MMLU": 45.99, + "TruthfulQA": 42.17, + "Winogrande": 71.82, + "GSM8K": 1.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "825506858e4603745a479215b8dea1524bfab6a0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "allbyai\/ToRoLaMa-7b-v1.0", + "Average \u2b06\ufe0f": 47.87, + "ARC": 51.71, + "HellaSwag": 73.82, + "MMLU": 45.34, + "TruthfulQA": 44.89, + "Winogrande": 70.09, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "9dd9ebe69ae8b391722c4edbfe70bd6c59b3b14d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "webbigdata\/ALMA-7B-Ja-V2", + "Average \u2b06\ufe0f": 47.85, + "ARC": 52.39, + "HellaSwag": 77.92, + "MMLU": 44.72, + "TruthfulQA": 38.66, + "Winogrande": 73.4, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "c2497586b28f419ad12c734600d08b2a5784ddc1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azazelle\/Sina-Odin-7b-Merge", + "Average \u2b06\ufe0f": 47.82, + "ARC": 52.82, + "HellaSwag": 68.86, + "MMLU": 45.54, + "TruthfulQA": 39.2, + "Winogrande": 72.22, + "GSM8K": 8.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c60ddc48eabbd4e7629afd26eb5a79efb4278084", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ConvexAI\/Pelican-9b-v0.1", + "Average \u2b06\ufe0f": 47.8, + "ARC": 43.34, + "HellaSwag": 57.86, + "MMLU": 63.31, + "TruthfulQA": 50.63, + "Winogrande": 71.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "9be2074aae989c40e9c77b6ade2ab3a3d2c37677", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "golaxy\/goims", + "Average \u2b06\ufe0f": 47.8, + "ARC": 49.49, + "HellaSwag": 72.67, + "MMLU": 43.85, + "TruthfulQA": 44.8, + "Winogrande": 69.69, + "GSM8K": 6.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9ef1045ca31f670d9cbf820af904b33a097cd787", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mosaicml\/mpt-7b-8k-chat", + "Average \u2b06\ufe0f": 47.78, + "ARC": 48.04, + "HellaSwag": 77.62, + "MMLU": 41.88, + "TruthfulQA": 43.68, + "Winogrande": 71.03, + "GSM8K": 4.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": false, + "Model sha": "ef97b878a279cd1765fbed7b8321fb3cff1aa5b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "h2m\/mhm-7b-v1.3-DPO-1", + "Average \u2b06\ufe0f": 47.77, + "ARC": 49.57, + "HellaSwag": 68.1, + "MMLU": 45.76, + "TruthfulQA": 45.88, + "Winogrande": 62.04, + "GSM8K": 15.24, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6ebd98fba486278e82be038bdc4b410c6bbd9c2d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bofenghuang\/vigogne-7b-instruct", + "Average \u2b06\ufe0f": 47.76, + "ARC": 51.96, + "HellaSwag": 78.11, + "MMLU": 38.43, + "TruthfulQA": 42.47, + "Winogrande": 72.85, + "GSM8K": 2.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "c6e2f515a0b289478118b5b75ff74107002ad962", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "quantumaikr\/KoreanLM-hf", + "Average \u2b06\ufe0f": 47.73, + "ARC": 51.45, + "HellaSwag": 76.77, + "MMLU": 40.61, + "TruthfulQA": 44.34, + "Winogrande": 69.77, + "GSM8K": 3.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "a7261e7ae6ee76c78e1ba1ac8c59bcc3e0868bf9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LeoLM\/leo-hessianai-7b", + "Average \u2b06\ufe0f": 47.72, + "ARC": 51.96, + "HellaSwag": 75.84, + "MMLU": 42.85, + "TruthfulQA": 37.94, + "Winogrande": 72.14, + "GSM8K": 5.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 36.0, + "Available on the hub": false, + "Model sha": "88c5ac07006ea8f1b5d10aa4f03f0d624dd27e56", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-7b-gpt4", + "Average \u2b06\ufe0f": 47.7, + "ARC": 53.07, + "HellaSwag": 78.69, + "MMLU": 38.9, + "TruthfulQA": 40.72, + "Winogrande": 73.09, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "d9bcb0ad365bfacdf95128bc1272b4106aff7be9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/airoboros-7b-gpt4-fp16", + "Average \u2b06\ufe0f": 47.7, + "ARC": 53.07, + "HellaSwag": 78.67, + "MMLU": 38.88, + "TruthfulQA": 40.73, + "Winogrande": 73.09, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "14aa50fba9f6418c0d5e2d24087eb802931040ef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "microsoft\/phi-1_5", + "Average \u2b06\ufe0f": 47.69, + "ARC": 52.9, + "HellaSwag": 63.79, + "MMLU": 43.89, + "TruthfulQA": 40.89, + "Winogrande": 72.22, + "GSM8K": 12.43, + "Type": "pretrained", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.5, + "Hub \u2764\ufe0f": 1216.0, + "Available on the hub": true, + "Model sha": "ea95720a352172db6fcbcd89032bfb1cb8481797", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "azale-ai\/DukunLM-7B-V1.0-Uncensored", + "Average \u2b06\ufe0f": 47.68, + "ARC": 51.11, + "HellaSwag": 75.62, + "MMLU": 39.82, + "TruthfulQA": 43.95, + "Winogrande": 69.53, + "GSM8K": 6.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "11a78fd948f70407f78b74fe599af572dbda15fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "elyza\/ELYZA-japanese-Llama-2-7b-fast", + "Average \u2b06\ufe0f": 47.67, + "ARC": 51.88, + "HellaSwag": 75.46, + "MMLU": 44.34, + "TruthfulQA": 36.45, + "Winogrande": 71.59, + "GSM8K": 6.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "e326078aa122fb1c4973997952d7b8630071776a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jphme\/orca_mini_v2_ger_7b", + "Average \u2b06\ufe0f": 47.65, + "ARC": 49.83, + "HellaSwag": 75.5, + "MMLU": 39.1, + "TruthfulQA": 45.74, + "Winogrande": 71.59, + "GSM8K": 4.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "175965f50907c6a8cd40f1a4b10d28342969c066", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "openthaigpt\/openthaigpt-1.0.0-alpha-7b-chat-ckpt-hf", + "Average \u2b06\ufe0f": 47.65, + "ARC": 50.85, + "HellaSwag": 74.89, + "MMLU": 40.02, + "TruthfulQA": 47.23, + "Winogrande": 69.06, + "GSM8K": 3.87, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "cdffb3488c5cb1a9aa5039a6b3bc72af24827db0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "keyfan\/vicuna-chinese-replication-v1.1", + "Average \u2b06\ufe0f": 47.65, + "ARC": 42.83, + "HellaSwag": 71.47, + "MMLU": 47.47, + "TruthfulQA": 47.24, + "Winogrande": 67.4, + "GSM8K": 9.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "259ab0967975012a546f2362d6cd03ab10768157", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "golaxy\/gowizardlm", + "Average \u2b06\ufe0f": 47.64, + "ARC": 49.74, + "HellaSwag": 71.9, + "MMLU": 42.96, + "TruthfulQA": 47.66, + "Winogrande": 69.61, + "GSM8K": 3.94, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "385f2d164e7fe780e053276d95d36240f2368c21", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "teilomillet\/MiniMerlin-3B", + "Average \u2b06\ufe0f": 47.63, + "ARC": 44.37, + "HellaSwag": 66.56, + "MMLU": 43.21, + "TruthfulQA": 47.07, + "Winogrande": 64.4, + "GSM8K": 20.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7fefc3d23e77c699aadba55c40d9e364eb73baf0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "project-baize\/baize-healthcare-lora-7B", + "Average \u2b06\ufe0f": 47.62, + "ARC": 54.1, + "HellaSwag": 77.32, + "MMLU": 37.09, + "TruthfulQA": 39.96, + "Winogrande": 72.85, + "GSM8K": 4.4, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e3eb8bb0d8840431afe24760d964f8ba57edd83e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bigcode\/starcoderplus", + "Average \u2b06\ufe0f": 47.61, + "ARC": 48.72, + "HellaSwag": 77.3, + "MMLU": 43.72, + "TruthfulQA": 37.85, + "Winogrande": 70.01, + "GSM8K": 8.04, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 207.0, + "Available on the hub": false, + "Model sha": "95be82087c33f14ee9941c812a154a9dd66efe72", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Tensoic\/Kan-Llama-SFT-v0.5", + "Average \u2b06\ufe0f": 47.56, + "ARC": 47.44, + "HellaSwag": 72.71, + "MMLU": 42.71, + "TruthfulQA": 47.44, + "Winogrande": 69.69, + "GSM8K": 5.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 6.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6307576da2b462571e804356a4b96803f56197d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "s3nh\/nsfw-noromaid-mistral-instruct", + "Average \u2b06\ufe0f": 47.49, + "ARC": 51.79, + "HellaSwag": 75.39, + "MMLU": 46.47, + "TruthfulQA": 33.49, + "Winogrande": 71.19, + "GSM8K": 6.6, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a1f9d4f788c52967433396cbbb46e8bec4e0d891", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Neko-Institute-of-Science\/metharme-7b", + "Average \u2b06\ufe0f": 47.48, + "ARC": 53.67, + "HellaSwag": 78.62, + "MMLU": 35.91, + "TruthfulQA": 39.16, + "Winogrande": 72.53, + "GSM8K": 5.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": false, + "Model sha": "62ca156891feead8db117be8f5f35687b6274e6e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DevaMalla\/llama_7b_qlora_cds", + "Average \u2b06\ufe0f": 47.43, + "ARC": 52.47, + "HellaSwag": 77.76, + "MMLU": 32.38, + "TruthfulQA": 46.14, + "Winogrande": 71.74, + "GSM8K": 4.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b6b5c65c5c1cce34d24c8f790bb0cc011e0f0808", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aiplanet\/effi-7b", + "Average \u2b06\ufe0f": 47.42, + "ARC": 55.12, + "HellaSwag": 78.07, + "MMLU": 35.91, + "TruthfulQA": 39.71, + "Winogrande": 72.53, + "GSM8K": 3.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "d58c62ee27cae60392bd0bd53e1fd05ea82e273b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-7b-gpt4-1.2", + "Average \u2b06\ufe0f": 47.42, + "ARC": 52.13, + "HellaSwag": 78.14, + "MMLU": 38.64, + "TruthfulQA": 41.79, + "Winogrande": 71.67, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "431fda60009d9b37a73211123ffb9c797764e182", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/orca_mini_v2_7b", + "Average \u2b06\ufe0f": 47.41, + "ARC": 50.77, + "HellaSwag": 76.02, + "MMLU": 39.5, + "TruthfulQA": 43.86, + "Winogrande": 71.43, + "GSM8K": 2.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "165850882991d7fa4eabab577a03ed84e0713bfa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-7b", + "Average \u2b06\ufe0f": 47.4, + "ARC": 53.07, + "HellaSwag": 77.65, + "MMLU": 37.23, + "TruthfulQA": 43.39, + "Winogrande": 70.96, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "7ea67f85ff3a7a8ec77f1819dec3e56779b764b1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-shishya-7b-ep3-v1", + "Average \u2b06\ufe0f": 47.4, + "ARC": 45.9, + "HellaSwag": 76.36, + "MMLU": 50.04, + "TruthfulQA": 40.32, + "Winogrande": 71.74, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "082cf758aa3f6d8f956056003b5b3b6cde447d88", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jxhong\/CAlign-alpaca-7b", + "Average \u2b06\ufe0f": 47.39, + "ARC": 50.94, + "HellaSwag": 74.55, + "MMLU": 38.56, + "TruthfulQA": 46.89, + "Winogrande": 72.06, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f5cc642a10160a014e2afeefcd57d4781994c51e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mosaicml\/mpt-7b-8k-instruct", + "Average \u2b06\ufe0f": 47.37, + "ARC": 45.9, + "HellaSwag": 74.47, + "MMLU": 41.97, + "TruthfulQA": 35.21, + "Winogrande": 65.98, + "GSM8K": 20.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": false, + "Model sha": "736f68aceeb61298a5de3cf5ae81d0bc2697edf4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/LLaMarada-7B-v0.1-16bit", + "Average \u2b06\ufe0f": 47.35, + "ARC": 53.33, + "HellaSwag": 76.02, + "MMLU": 39.68, + "TruthfulQA": 37.13, + "Winogrande": 70.96, + "GSM8K": 6.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3ad8fb00e2646d606fe53989de8d7449b6c542b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/guanaco-7B-HF", + "Average \u2b06\ufe0f": 47.34, + "ARC": 52.99, + "HellaSwag": 80.05, + "MMLU": 35.32, + "TruthfulQA": 39.2, + "Winogrande": 71.43, + "GSM8K": 5.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "293c24105fa15afa127a2ec3905fdc2a0a3a6dac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "h2m\/mhm-7b-v1.3", + "Average \u2b06\ufe0f": 47.29, + "ARC": 47.53, + "HellaSwag": 65.31, + "MMLU": 45.74, + "TruthfulQA": 46.22, + "Winogrande": 62.27, + "GSM8K": 16.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "0e8363818fdbdc8bacb1467e019f49fa8a9f4329", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "openlm-research\/open_llama_13b", + "Average \u2b06\ufe0f": 47.26, + "ARC": 51.19, + "HellaSwag": 75.23, + "MMLU": 43.75, + "TruthfulQA": 38.08, + "Winogrande": 72.06, + "GSM8K": 3.26, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 449.0, + "Available on the hub": true, + "Model sha": "b6d7fde8392250730d24cc2fcfa3b7e5f9a03ce8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rufjdk5480\/mixtral-ko-qna-merged", + "Average \u2b06\ufe0f": 47.24, + "ARC": 39.51, + "HellaSwag": 39.06, + "MMLU": 71.86, + "TruthfulQA": 48.61, + "Winogrande": 56.75, + "GSM8K": 27.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "810c90db1842f6c5f314f23b7549d58316e0db95", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rufjdk5480\/gov-qna-ko-merged", + "Average \u2b06\ufe0f": 47.24, + "ARC": 39.51, + "HellaSwag": 39.06, + "MMLU": 71.86, + "TruthfulQA": 48.61, + "Winogrande": 56.75, + "GSM8K": 27.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "810c90db1842f6c5f314f23b7549d58316e0db95", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "mosaicml\/mpt-7b-8k", + "Average \u2b06\ufe0f": 47.24, + "ARC": 47.35, + "HellaSwag": 77.4, + "MMLU": 42.58, + "TruthfulQA": 36.65, + "Winogrande": 71.11, + "GSM8K": 8.34, + "Type": "pretrained", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": false, + "Model sha": "c94f57239fed80eac0dc62507aee049681c799a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Undi95\/Mixtral-8x7B-MoE-RP-Story", + "Average \u2b06\ufe0f": 47.23, + "ARC": 51.54, + "HellaSwag": 70.0, + "MMLU": 43.04, + "TruthfulQA": 41.53, + "Winogrande": 67.32, + "GSM8K": 9.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 33.0, + "Available on the hub": true, + "Model sha": "ce4a4e4ffec063a3e338b6ebc328365270b6c5f0", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/CodeLlama13B-Finetune-v1", + "Average \u2b06\ufe0f": 47.19, + "ARC": 45.82, + "HellaSwag": 69.36, + "MMLU": 45.05, + "TruthfulQA": 44.97, + "Winogrande": 66.93, + "GSM8K": 10.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "40ff78ce37efcaf83718534c494829a573b9d719", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mosaicml\/mpt-7b-8k-instruct", + "Average \u2b06\ufe0f": 47.18, + "ARC": 45.48, + "HellaSwag": 74.41, + "MMLU": 42.11, + "TruthfulQA": 35.06, + "Winogrande": 65.51, + "GSM8K": 20.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": false, + "Model sha": "736f68aceeb61298a5de3cf5ae81d0bc2697edf4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "starmpcc\/Asclepius-Llama2-7B", + "Average \u2b06\ufe0f": 47.15, + "ARC": 50.85, + "HellaSwag": 76.53, + "MMLU": 43.61, + "TruthfulQA": 43.31, + "Winogrande": 68.27, + "GSM8K": 0.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "2f15bd8250d7825307e59cc2c785074ebbec3395", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "rinna\/youri-7b", + "Average \u2b06\ufe0f": 47.11, + "ARC": 49.06, + "HellaSwag": 74.89, + "MMLU": 42.22, + "TruthfulQA": 36.03, + "Winogrande": 71.82, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "2be40b8a7b669c4520bc04ce954bdbd7d4b0da7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "itsliupeng\/openllama-7b-base", + "Average \u2b06\ufe0f": 47.09, + "ARC": 46.16, + "HellaSwag": 76.4, + "MMLU": 42.82, + "TruthfulQA": 36.65, + "Winogrande": 70.88, + "GSM8K": 9.63, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "24d98f339fabfa479e3c85404f5e4dda9e43dcd1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/LLaMA-2-7B-32K", + "Average \u2b06\ufe0f": 47.07, + "ARC": 47.53, + "HellaSwag": 76.14, + "MMLU": 43.33, + "TruthfulQA": 39.23, + "Winogrande": 71.9, + "GSM8K": 4.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 498.0, + "Available on the hub": true, + "Model sha": "aef6d8946ae1015bdb65c478a2dd73b58daaef47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-gpt-3.5-turbo-100k-7b", + "Average \u2b06\ufe0f": 47.05, + "ARC": 53.07, + "HellaSwag": 76.16, + "MMLU": 33.63, + "TruthfulQA": 45.07, + "Winogrande": 70.8, + "GSM8K": 3.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "53887996c0f17f7711d182537505a895fb404542", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "notstoic\/PygmalionCoT-7b", + "Average \u2b06\ufe0f": 47.0, + "ARC": 51.45, + "HellaSwag": 76.92, + "MMLU": 33.35, + "TruthfulQA": 48.13, + "Winogrande": 68.9, + "GSM8K": 3.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c03ac527360663d17bb142405251028eec843ed9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mncai\/chatdoctor", + "Average \u2b06\ufe0f": 46.95, + "ARC": 53.75, + "HellaSwag": 78.54, + "MMLU": 35.95, + "TruthfulQA": 43.55, + "Winogrande": 69.93, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LLaMAForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": false, + "Model sha": "8fdcfdda6877d7f21173dfac48b2c14499ba8264", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "ausboss\/llama7b-wizardlm-unfiltered", + "Average \u2b06\ufe0f": 46.94, + "ARC": 52.99, + "HellaSwag": 77.89, + "MMLU": 36.41, + "TruthfulQA": 37.75, + "Winogrande": 72.3, + "GSM8K": 4.32, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "2123beec77083c414b2ae51dd25b7a870b0b936c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/dolphin-llama2-7b", + "Average \u2b06\ufe0f": 46.94, + "ARC": 46.59, + "HellaSwag": 67.52, + "MMLU": 48.37, + "TruthfulQA": 49.72, + "Winogrande": 63.77, + "GSM8K": 5.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "85aa4f67191fd016ab7ea8c389fddb5d9e5a9a52", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WhiteRabbitNeo\/WhiteRabbitNeo-33B-v1", + "Average \u2b06\ufe0f": 46.93, + "ARC": 44.37, + "HellaSwag": 60.22, + "MMLU": 40.56, + "TruthfulQA": 41.68, + "Winogrande": 61.01, + "GSM8K": 33.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": true, + "Model sha": "e508c81aaf6b8bf8d1c7cbad5c9ddaed85fbb7dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-7b-gpt4-1.3", + "Average \u2b06\ufe0f": 46.91, + "ARC": 52.47, + "HellaSwag": 77.98, + "MMLU": 41.97, + "TruthfulQA": 35.73, + "Winogrande": 72.3, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7b5f77827636bbf3174c48ca16e774c89d71d7bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "stanford-oval\/Llama-2-7b-WikiChat-fused", + "Average \u2b06\ufe0f": 46.81, + "ARC": 50.68, + "HellaSwag": 75.0, + "MMLU": 39.69, + "TruthfulQA": 46.36, + "Winogrande": 69.06, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "47cc2d3e1719da0f0300d07111ea6a9b6e3aa2d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Qwen\/Qwen1.5-4B-Chat", + "Average \u2b06\ufe0f": 46.79, + "ARC": 43.26, + "HellaSwag": 69.73, + "MMLU": 55.55, + "TruthfulQA": 44.79, + "Winogrande": 64.96, + "GSM8K": 2.43, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "15bf46b13b1e6b6dd18ff7fa3242af406cc7e791", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DevaMalla\/llama_7b_lora", + "Average \u2b06\ufe0f": 46.77, + "ARC": 54.86, + "HellaSwag": 79.1, + "MMLU": 33.63, + "TruthfulQA": 34.74, + "Winogrande": 72.77, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7f4cbd810b4bef0d75c1fd3f551146b4ea97d9fd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "project-baize\/baize-v2-7b", + "Average \u2b06\ufe0f": 46.72, + "ARC": 48.98, + "HellaSwag": 75.06, + "MMLU": 39.6, + "TruthfulQA": 41.39, + "Winogrande": 71.11, + "GSM8K": 4.17, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "e4731c2c2671e2d0b47b5eba08c753ca21671fab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-codellama-dolphin-orca-platypus-13b", + "Average \u2b06\ufe0f": 46.7, + "ARC": 44.8, + "HellaSwag": 68.6, + "MMLU": 44.03, + "TruthfulQA": 46.28, + "Winogrande": 66.93, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "0c41023f8f665946a2c46c3823afee431408bcbd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-codellama-platypus-13b", + "Average \u2b06\ufe0f": 46.68, + "ARC": 46.16, + "HellaSwag": 68.88, + "MMLU": 44.55, + "TruthfulQA": 44.98, + "Winogrande": 66.14, + "GSM8K": 9.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7a771bd8899b9ef4ba9680e96f84dc85810a67d6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/dolphin-2.2-yi-34b-200k", + "Average \u2b06\ufe0f": 46.67, + "ARC": 42.24, + "HellaSwag": 68.22, + "MMLU": 55.51, + "TruthfulQA": 45.94, + "Winogrande": 64.17, + "GSM8K": 3.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 30.0, + "Available on the hub": true, + "Model sha": "33950ffa68b9f8cd5dc2f046c6c9a2d0f0bf7eff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ehartford\/dolphin-2.2-yi-34b-200k", + "Average \u2b06\ufe0f": 46.67, + "ARC": 42.15, + "HellaSwag": 68.18, + "MMLU": 55.47, + "TruthfulQA": 45.93, + "Winogrande": 64.56, + "GSM8K": 3.71, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c4e02a3a5c7a9d51f8b0cad85952dfdfb34c9413", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "golaxy\/gogpt2-7b", + "Average \u2b06\ufe0f": 46.65, + "ARC": 46.76, + "HellaSwag": 71.53, + "MMLU": 42.85, + "TruthfulQA": 47.85, + "Winogrande": 68.67, + "GSM8K": 2.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "ee60ed402dedf24b6154aef05df54512e02fc9e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sarvamai\/OpenHathi-7B-Hi-v0.1-Base", + "Average \u2b06\ufe0f": 46.64, + "ARC": 49.49, + "HellaSwag": 74.34, + "MMLU": 41.38, + "TruthfulQA": 37.46, + "Winogrande": 71.27, + "GSM8K": 5.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.87, + "Hub \u2764\ufe0f": 72.0, + "Available on the hub": true, + "Model sha": "2cbb156ab4426113115bc3387b06d1940015119a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vikash06\/llama-2-7b-small-model-new", + "Average \u2b06\ufe0f": 46.62, + "ARC": 45.22, + "HellaSwag": 72.35, + "MMLU": 46.23, + "TruthfulQA": 42.46, + "Winogrande": 63.93, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "eefcb721d116ff2e486c4b70cf506e6c0d00fb0f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DevaMalla\/llama_7b_qlora", + "Average \u2b06\ufe0f": 46.61, + "ARC": 55.12, + "HellaSwag": 78.26, + "MMLU": 35.71, + "TruthfulQA": 33.98, + "Winogrande": 72.06, + "GSM8K": 4.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7f94b0be78193abc54722cf723541c3800426f7b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "stabilityai\/stablelm-3b-4e1t", + "Average \u2b06\ufe0f": 46.58, + "ARC": 46.59, + "HellaSwag": 75.94, + "MMLU": 45.23, + "TruthfulQA": 37.2, + "Winogrande": 71.19, + "GSM8K": 3.34, + "Type": "pretrained", + "Architecture": "StableLMEpochForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 2.8, + "Hub \u2764\ufe0f": 299.0, + "Available on the hub": true, + "Model sha": "a4750ace0db6f08d7bbba0aa52a585f231ea3cde", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "chavinlo\/alpaca-native", + "Average \u2b06\ufe0f": 46.58, + "ARC": 52.3, + "HellaSwag": 77.09, + "MMLU": 41.6, + "TruthfulQA": 37.58, + "Winogrande": 69.46, + "GSM8K": 1.44, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 257.0, + "Available on the hub": false, + "Model sha": "cc7773cac2478231807c56ef2f02292d98f85cf5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen1.5-1.8B", + "Average \u2b06\ufe0f": 46.55, + "ARC": 37.88, + "HellaSwag": 61.42, + "MMLU": 46.71, + "TruthfulQA": 39.43, + "Winogrande": 60.3, + "GSM8K": 33.59, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "921f88e4573192da5a10c809ed188603ea0f3937", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "golaxy\/gogpt2-13b", + "Average \u2b06\ufe0f": 46.55, + "ARC": 48.38, + "HellaSwag": 71.78, + "MMLU": 44.5, + "TruthfulQA": 44.73, + "Winogrande": 67.88, + "GSM8K": 2.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "16d4c4214fa8d5a962b9064a8b958076b7c79a17", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "google\/gemma-2b", + "Average \u2b06\ufe0f": 46.51, + "ARC": 48.46, + "HellaSwag": 71.65, + "MMLU": 41.68, + "TruthfulQA": 33.13, + "Winogrande": 66.77, + "GSM8K": 17.36, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 426.0, + "Available on the hub": true, + "Model sha": "b903623f4be99493dba7e415a6f6c7c609ecf674", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DevaMalla\/llama7b_alpaca_1gpu_bf16", + "Average \u2b06\ufe0f": 46.49, + "ARC": 52.73, + "HellaSwag": 78.78, + "MMLU": 36.26, + "TruthfulQA": 33.71, + "Winogrande": 72.93, + "GSM8K": 4.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "305683c1b95f6888b8668dbc6b56d9efa5d07fef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/Pygmalion_AlpacaLora-7b", + "Average \u2b06\ufe0f": 46.49, + "ARC": 53.24, + "HellaSwag": 76.92, + "MMLU": 35.92, + "TruthfulQA": 39.44, + "Winogrande": 72.22, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "1f61442e1238062095b31b4909c5e9ab26105794", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cognitivecomputations\/dolphin-2.2-yi-34b-200k", + "Average \u2b06\ufe0f": 46.47, + "ARC": 42.06, + "HellaSwag": 68.13, + "MMLU": 55.35, + "TruthfulQA": 45.93, + "Winogrande": 64.25, + "GSM8K": 3.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 30.0, + "Available on the hub": true, + "Model sha": "33950ffa68b9f8cd5dc2f046c6c9a2d0f0bf7eff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "glenn2\/gemma-7b-lora-distilabel-intel-orca-dpo-pairs", + "Average \u2b06\ufe0f": 46.47, + "ARC": 49.15, + "HellaSwag": 71.78, + "MMLU": 41.52, + "TruthfulQA": 33.1, + "Winogrande": 65.98, + "GSM8K": 17.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a2b71eb940722a0a5597d62044ad2e5d37352a94", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "0x7194633\/fialka-7B-v3", + "Average \u2b06\ufe0f": 46.4, + "ARC": 48.55, + "HellaSwag": 71.05, + "MMLU": 43.06, + "TruthfulQA": 44.79, + "Winogrande": 69.46, + "GSM8K": 1.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d0dae57538d9379526726e66d5156ec0042528be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jerryjalapeno\/nart-100k-7b", + "Average \u2b06\ufe0f": 46.39, + "ARC": 54.1, + "HellaSwag": 78.47, + "MMLU": 34.98, + "TruthfulQA": 36.74, + "Winogrande": 70.48, + "GSM8K": 3.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": false, + "Model sha": "50e61b8e6cc17cb3fbcb490fe3dc7e2c8b248378", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "golaxy\/gogpt-7b", + "Average \u2b06\ufe0f": 46.38, + "ARC": 48.81, + "HellaSwag": 73.79, + "MMLU": 43.03, + "TruthfulQA": 41.0, + "Winogrande": 69.77, + "GSM8K": 1.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7eb70c0e330b7d3ff490047ddbb153bb96294882", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "huggyllama\/llama-7b", + "Average \u2b06\ufe0f": 46.37, + "ARC": 50.94, + "HellaSwag": 77.81, + "MMLU": 35.69, + "TruthfulQA": 34.33, + "Winogrande": 71.43, + "GSM8K": 8.04, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 243.0, + "Available on the hub": true, + "Model sha": "8416d3fefb0cb3ff5775a7b13c1692d10ff1aa16", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "google\/gemma-2b", + "Average \u2b06\ufe0f": 46.37, + "ARC": 48.38, + "HellaSwag": 71.77, + "MMLU": 41.77, + "TruthfulQA": 33.08, + "Winogrande": 66.3, + "GSM8K": 16.91, + "Type": "pretrained", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 426.0, + "Available on the hub": true, + "Model sha": "9d067f00def958594aaa16b39a65b07d69ca655b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jondurbin\/airoboros-7b-gpt4-1.4.1-qlora", + "Average \u2b06\ufe0f": 46.34, + "ARC": 52.73, + "HellaSwag": 77.89, + "MMLU": 38.77, + "TruthfulQA": 36.07, + "Winogrande": 70.32, + "GSM8K": 2.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "91ffa900ed637cf5fd904d96e6985b6f7857ad64", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wenge-research\/yayi-13b-llama2", + "Average \u2b06\ufe0f": 46.32, + "ARC": 48.55, + "HellaSwag": 74.82, + "MMLU": 38.68, + "TruthfulQA": 42.19, + "Winogrande": 69.69, + "GSM8K": 4.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "9fc1bc4409b9e71f54213245a91c2742fbf7b3d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "speechlessai\/speechless-codellama-dolphin-orca-platypus-13b", + "Average \u2b06\ufe0f": 46.32, + "ARC": 45.82, + "HellaSwag": 67.71, + "MMLU": 45.88, + "TruthfulQA": 44.67, + "Winogrande": 65.35, + "GSM8K": 8.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "25e1c346c2a01588a728307d5c35fbeecd58b51b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-codellama-orca-13b", + "Average \u2b06\ufe0f": 46.28, + "ARC": 46.33, + "HellaSwag": 67.71, + "MMLU": 47.19, + "TruthfulQA": 46.66, + "Winogrande": 63.77, + "GSM8K": 5.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "a82467de3cb9438aa8f9e0ea8ea692f16a5724b2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yhyhy3\/open_llama_7b_v2_med_instruct", + "Average \u2b06\ufe0f": 46.24, + "ARC": 46.5, + "HellaSwag": 76.91, + "MMLU": 42.32, + "TruthfulQA": 40.33, + "Winogrande": 69.3, + "GSM8K": 2.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "cabb47abd422a2d67161e2d038265ee23be45fb8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-llama2-7b-pretrain", + "Average \u2b06\ufe0f": 46.18, + "ARC": 48.63, + "HellaSwag": 74.83, + "MMLU": 41.04, + "TruthfulQA": 39.08, + "Winogrande": 70.24, + "GSM8K": 3.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "444c85ef809f8793d84b0813ab78bec50700cfcf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "stabilityai\/stablelm-base-alpha-7b-v2", + "Average \u2b06\ufe0f": 46.18, + "ARC": 47.35, + "HellaSwag": 77.08, + "MMLU": 45.1, + "TruthfulQA": 36.46, + "Winogrande": 68.51, + "GSM8K": 2.58, + "Type": "pretrained", + "Architecture": "StableLMAlphaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 6.89, + "Hub \u2764\ufe0f": 47.0, + "Available on the hub": true, + "Model sha": "eb3b56fee1ad4b1efe6625bbbc7a277df8ab5b96", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ajibawa-2023\/carl-7b", + "Average \u2b06\ufe0f": 46.16, + "ARC": 53.5, + "HellaSwag": 78.29, + "MMLU": 33.96, + "TruthfulQA": 40.29, + "Winogrande": 68.59, + "GSM8K": 2.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "de4c7af9598bebc47dd43253c972be719f3195d6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/vicuna-class-shishya-7b-ep3", + "Average \u2b06\ufe0f": 46.14, + "ARC": 40.61, + "HellaSwag": 76.72, + "MMLU": 50.77, + "TruthfulQA": 36.87, + "Winogrande": 71.9, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c2bd682b9f3babbb3bc84f84856fabe69a3c21d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vilm\/Quyen-Mini-v0.1", + "Average \u2b06\ufe0f": 46.14, + "ARC": 39.33, + "HellaSwag": 60.57, + "MMLU": 43.93, + "TruthfulQA": 46.44, + "Winogrande": 59.12, + "GSM8K": 27.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "e6178976a00495b6e0b9cec54ee6ac342bbd4d71", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "namirocks\/mistral-class-tutor-7b-ep3", + "Average \u2b06\ufe0f": 46.09, + "ARC": 47.95, + "HellaSwag": 77.8, + "MMLU": 34.57, + "TruthfulQA": 44.69, + "Winogrande": 71.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e571e0278702171cc460f8fe35b053278b0a9d7b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigscience\/bloom", + "Average \u2b06\ufe0f": 46.07, + "ARC": 50.43, + "HellaSwag": 76.41, + "MMLU": 30.85, + "TruthfulQA": 39.76, + "Winogrande": 72.06, + "GSM8K": 6.9, + "Type": "pretrained", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 176.25, + "Hub \u2764\ufe0f": 4415.0, + "Available on the hub": true, + "Model sha": "053d9cd9fbe814e091294f67fcfedb3397b954bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fireballoon\/baichuan-vicuna-chinese-7b", + "Average \u2b06\ufe0f": 46.06, + "ARC": 43.52, + "HellaSwag": 71.12, + "MMLU": 46.87, + "TruthfulQA": 42.45, + "Winogrande": 66.85, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 62.0, + "Available on the hub": false, + "Model sha": "6cdb9e75cd473e31e87067c2a0b646083247d9ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "illuin\/test-custom-llama", + "Average \u2b06\ufe0f": 46.05, + "ARC": 52.3, + "HellaSwag": 77.49, + "MMLU": 36.61, + "TruthfulQA": 33.81, + "Winogrande": 72.06, + "GSM8K": 4.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d985610bef080473e40f01c53266083c5f0c3169", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Neko-Institute-of-Science\/pygmalion-7b", + "Average \u2b06\ufe0f": 46.04, + "ARC": 51.37, + "HellaSwag": 77.81, + "MMLU": 35.68, + "TruthfulQA": 34.54, + "Winogrande": 72.22, + "GSM8K": 4.62, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 39.0, + "Available on the hub": false, + "Model sha": "6473f9996d758fde48a181f37cc5de575aff1606", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-mctaco-modified2", + "Average \u2b06\ufe0f": 46.03, + "ARC": 42.92, + "HellaSwag": 73.97, + "MMLU": 48.49, + "TruthfulQA": 40.43, + "Winogrande": 69.69, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8e1930bbbbdeb4f6f4639e837f09d9878bbf7831", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/TheTop-5x7B-Instruct-P-v0.1", + "Average \u2b06\ufe0f": 46.02, + "ARC": 38.57, + "HellaSwag": 51.54, + "MMLU": 63.36, + "TruthfulQA": 50.07, + "Winogrande": 72.61, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "22669ba7d1924596b6cd224b5909b6ba6c646475", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "shuvom\/yuj-v1", + "Average \u2b06\ufe0f": 45.97, + "ARC": 45.65, + "HellaSwag": 70.1, + "MMLU": 43.78, + "TruthfulQA": 41.69, + "Winogrande": 69.85, + "GSM8K": 4.78, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.87, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "acf11b386f17e81d357b93bc6c89efd743b5ddfc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aloobun\/Reyna-Mini-1.8B-v0.2", + "Average \u2b06\ufe0f": 45.94, + "ARC": 36.6, + "HellaSwag": 60.19, + "MMLU": 44.75, + "TruthfulQA": 41.24, + "Winogrande": 61.56, + "GSM8K": 31.31, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "c754104ac85b9a598fb1f3c7b879af7f87a466ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fierysurf\/Ambari-7B-base-v0.1-sharded", + "Average \u2b06\ufe0f": 45.92, + "ARC": 47.95, + "HellaSwag": 74.62, + "MMLU": 40.39, + "TruthfulQA": 38.91, + "Winogrande": 72.06, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a8305467fb07f667c4aa1ba61a78ab3b3c0c23e1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "qnguyen3\/quan-1.8b-chat", + "Average \u2b06\ufe0f": 45.91, + "ARC": 39.08, + "HellaSwag": 62.37, + "MMLU": 44.09, + "TruthfulQA": 43.15, + "Winogrande": 59.27, + "GSM8K": 27.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.8, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "3b648e8a549888292a73a21b7312d958de6e875d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/ssh_1.8B", + "Average \u2b06\ufe0f": 45.91, + "ARC": 39.08, + "HellaSwag": 62.37, + "MMLU": 44.09, + "TruthfulQA": 43.15, + "Winogrande": 59.27, + "GSM8K": 27.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5dc3d8d5c08c014c43adc23678b31c0ac7d615c8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vikash06\/mistral_v1", + "Average \u2b06\ufe0f": 45.85, + "ARC": 47.01, + "HellaSwag": 67.58, + "MMLU": 48.68, + "TruthfulQA": 37.53, + "Winogrande": 64.8, + "GSM8K": 9.48, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "9b7bd68c8105ff8ab2b6a5d6c9ad32f82c3190a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "codellama\/CodeLlama-13b-Instruct-hf", + "Average \u2b06\ufe0f": 45.82, + "ARC": 44.54, + "HellaSwag": 64.93, + "MMLU": 38.89, + "TruthfulQA": 45.88, + "Winogrande": 68.03, + "GSM8K": 12.66, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 123.0, + "Available on the hub": true, + "Model sha": "b9f91b7351ecd589118d883afa23d5c93a38c612", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "nxn1231\/yi6", + "Average \u2b06\ufe0f": 45.82, + "ARC": 47.78, + "HellaSwag": 68.25, + "MMLU": 54.05, + "TruthfulQA": 35.8, + "Winogrande": 64.64, + "GSM8K": 4.4, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cfd5055e80eef946245f0ff4a49d46f9857ba482", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TheBloke\/CodeLlama-13B-Instruct-fp16", + "Average \u2b06\ufe0f": 45.82, + "ARC": 44.62, + "HellaSwag": 64.94, + "MMLU": 38.77, + "TruthfulQA": 45.88, + "Winogrande": 68.03, + "GSM8K": 12.66, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "521c208c7251ccd3e44ccd9500b6bed419bca565", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fierysurf\/Kan-LLaMA-7B-SFT-v0.1-sharded", + "Average \u2b06\ufe0f": 45.76, + "ARC": 45.9, + "HellaSwag": 71.43, + "MMLU": 40.86, + "TruthfulQA": 45.04, + "Winogrande": 68.82, + "GSM8K": 2.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a04fd8b0958c11d7316965207d67b707cf4702f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fierysurf\/Ambari-7B-Instruct-v0.1-sharded", + "Average \u2b06\ufe0f": 45.74, + "ARC": 50.0, + "HellaSwag": 74.59, + "MMLU": 38.03, + "TruthfulQA": 40.39, + "Winogrande": 69.53, + "GSM8K": 1.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d5f311d103dab0eeac1d5208130645c5a3dbfcd5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/llama2-7b-raw-sft", + "Average \u2b06\ufe0f": 45.67, + "ARC": 47.44, + "HellaSwag": 75.25, + "MMLU": 33.86, + "TruthfulQA": 40.77, + "Winogrande": 73.01, + "GSM8K": 3.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cd167d27b6c116b23863da859a07d08c6359c207", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/mistral-7b-raw-sft", + "Average \u2b06\ufe0f": 45.67, + "ARC": 47.44, + "HellaSwag": 75.25, + "MMLU": 33.86, + "TruthfulQA": 40.77, + "Winogrande": 73.01, + "GSM8K": 3.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e1b241a26e35b87137fba8a54e352f1e4c98eebf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MAISAAI\/gemma-2b-coder", + "Average \u2b06\ufe0f": 45.65, + "ARC": 48.98, + "HellaSwag": 71.43, + "MMLU": 37.02, + "TruthfulQA": 33.54, + "Winogrande": 66.85, + "GSM8K": 16.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e5e4e5bfb8eb4cc11a82cff08db51a213fa66e42", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mlabonne\/Gemmalpaca-2B", + "Average \u2b06\ufe0f": 45.65, + "ARC": 48.72, + "HellaSwag": 71.36, + "MMLU": 36.3, + "TruthfulQA": 41.24, + "Winogrande": 65.59, + "GSM8K": 10.69, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "33fa56fd6dde243144c8d6ed2e91830f43b69c15", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "huggingface\/llama-7b", + "Average \u2b06\ufe0f": 45.65, + "ARC": 51.02, + "HellaSwag": 77.82, + "MMLU": 35.71, + "TruthfulQA": 34.33, + "Winogrande": 71.43, + "GSM8K": 3.56, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f356572651e58fb337d610470d4b36976e7fb802", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Planner-7B-fp16", + "Average \u2b06\ufe0f": 45.65, + "ARC": 51.02, + "HellaSwag": 77.82, + "MMLU": 35.71, + "TruthfulQA": 34.33, + "Winogrande": 71.43, + "GSM8K": 3.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "afb4604a06c8541960fb51240259777764c4ce7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "uukuguy\/speechless-codellama-platypus-13b", + "Average \u2b06\ufe0f": 45.64, + "ARC": 45.31, + "HellaSwag": 68.63, + "MMLU": 42.82, + "TruthfulQA": 42.38, + "Winogrande": 65.59, + "GSM8K": 9.1, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "81cb1bca46ce646b8339501537837e02116de1b8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "DevaMalla\/llama-base-7b", + "Average \u2b06\ufe0f": 45.62, + "ARC": 50.94, + "HellaSwag": 77.8, + "MMLU": 35.67, + "TruthfulQA": 34.34, + "Winogrande": 71.43, + "GSM8K": 3.56, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e01d89d8e444f7d751ea58feaf22ff8c9af69d2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WeOpenML\/PandaLM-Alpaca-7B-v1", + "Average \u2b06\ufe0f": 45.59, + "ARC": 50.85, + "HellaSwag": 77.36, + "MMLU": 35.91, + "TruthfulQA": 36.63, + "Winogrande": 71.9, + "GSM8K": 0.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "7fe5cb1a7009fdade8dfcfec335527997a730fcf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "yeontaek\/WizardCoder-Python-13B-LoRa", + "Average \u2b06\ufe0f": 45.56, + "ARC": 47.78, + "HellaSwag": 69.6, + "MMLU": 38.76, + "TruthfulQA": 43.97, + "Winogrande": 65.43, + "GSM8K": 7.81, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "32ffc44ffdf1adfe2d8ef219327fbd534f3d5955", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/falcon-7B-case-4", + "Average \u2b06\ufe0f": 45.54, + "ARC": 47.61, + "HellaSwag": 78.69, + "MMLU": 29.21, + "TruthfulQA": 37.79, + "Winogrande": 71.67, + "GSM8K": 8.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1e628df64fbce4c4e5e913ddaf4b8c861ffe1fea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/falcon-7B-case-1", + "Average \u2b06\ufe0f": 45.54, + "ARC": 47.61, + "HellaSwag": 78.69, + "MMLU": 29.21, + "TruthfulQA": 37.79, + "Winogrande": 71.67, + "GSM8K": 8.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0eea42282e92b4f2e90d2d37f660ac9b192aa171", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "namirocks\/mistral-shishya-model-7b-ep3", + "Average \u2b06\ufe0f": 45.53, + "ARC": 44.71, + "HellaSwag": 76.81, + "MMLU": 46.77, + "TruthfulQA": 33.87, + "Winogrande": 71.03, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ff7ee1544ff0d270c81146e9c9b681202bcf59be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ai4bharat\/Airavata", + "Average \u2b06\ufe0f": 45.52, + "ARC": 46.5, + "HellaSwag": 69.26, + "MMLU": 43.9, + "TruthfulQA": 40.62, + "Winogrande": 68.82, + "GSM8K": 4.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.87, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "3fd8340a3683c8e7695c89a463428fcc0b2a875a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhinand\/tamil-llama-7b-instruct-v0.1", + "Average \u2b06\ufe0f": 45.52, + "ARC": 48.04, + "HellaSwag": 70.97, + "MMLU": 39.95, + "TruthfulQA": 41.7, + "Winogrande": 70.64, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "36f04b36c781ff994af41060df09491bde54105d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Linly-AI\/Chinese-LLaMA-2-7B-hf", + "Average \u2b06\ufe0f": 45.44, + "ARC": 48.04, + "HellaSwag": 73.25, + "MMLU": 35.04, + "TruthfulQA": 39.92, + "Winogrande": 70.17, + "GSM8K": 6.22, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": false, + "Model sha": "a2d55220b3d0693825fe69e1174653dc6cc4a920", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shibing624\/chinese-llama-plus-13b-hf", + "Average \u2b06\ufe0f": 45.39, + "ARC": 46.25, + "HellaSwag": 71.88, + "MMLU": 40.74, + "TruthfulQA": 39.89, + "Winogrande": 73.09, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "f17a52b8067d551a814069d2c710e1f5c487a3ce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mosaicml\/mpt-7b-chat", + "Average \u2b06\ufe0f": 45.39, + "ARC": 46.5, + "HellaSwag": 75.51, + "MMLU": 37.62, + "TruthfulQA": 40.16, + "Winogrande": 68.43, + "GSM8K": 4.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 501.0, + "Available on the hub": false, + "Model sha": "64e5c9c9fb53a8e89690c2dee75a5add37f7113e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-mctaco-modified1", + "Average \u2b06\ufe0f": 45.38, + "ARC": 40.87, + "HellaSwag": 73.4, + "MMLU": 47.42, + "TruthfulQA": 39.87, + "Winogrande": 69.46, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a7749ff092ef03900de34b69d41c767a6a48ea9e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openthaigpt\/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf", + "Average \u2b06\ufe0f": 45.35, + "ARC": 44.97, + "HellaSwag": 70.19, + "MMLU": 36.22, + "TruthfulQA": 49.99, + "Winogrande": 69.38, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "dfc8a1e7ac47765466764dc48c285c5bd23de1fd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "luqmanxyz\/FrankenVillain-7B-v1", + "Average \u2b06\ufe0f": 45.34, + "ARC": 42.75, + "HellaSwag": 51.52, + "MMLU": 48.6, + "TruthfulQA": 56.19, + "Winogrande": 73.01, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "62078c66843dc86acb23ed546f6facb0199a489b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beomi\/llama-2-ko-7b", + "Average \u2b06\ufe0f": 45.32, + "ARC": 48.46, + "HellaSwag": 75.28, + "MMLU": 39.56, + "TruthfulQA": 34.49, + "Winogrande": 72.14, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.86, + "Hub \u2764\ufe0f": 150.0, + "Available on the hub": false, + "Model sha": "d5c58cc2cae21b4fb96aaad2658acc898ab22d99", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "haoranxu\/ALMA-7B", + "Average \u2b06\ufe0f": 45.32, + "ARC": 50.34, + "HellaSwag": 75.5, + "MMLU": 38.04, + "TruthfulQA": 35.64, + "Winogrande": 72.38, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "b570315dd26452a07cf15cf6feecce839e1327a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GeneZC\/MiniChat-3B", + "Average \u2b06\ufe0f": 45.31, + "ARC": 44.03, + "HellaSwag": 67.19, + "MMLU": 39.17, + "TruthfulQA": 45.67, + "Winogrande": 65.27, + "GSM8K": 10.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.02, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": true, + "Model sha": "123d23bd291bb2d5fdb3b91dc1570d0b11654a78", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ashercn97\/giraffe-7b", + "Average \u2b06\ufe0f": 45.29, + "ARC": 47.18, + "HellaSwag": 75.53, + "MMLU": 38.89, + "TruthfulQA": 38.48, + "Winogrande": 68.98, + "GSM8K": 2.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9af88449bed5be4709befcfbbba123ee75805479", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "facebook\/opt-iml-max-30b", + "Average \u2b06\ufe0f": 45.28, + "ARC": 43.86, + "HellaSwag": 72.39, + "MMLU": 41.09, + "TruthfulQA": 38.16, + "Winogrande": 73.72, + "GSM8K": 2.5, + "Type": "", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": true, + "Model sha": "291753b04817a31a742631053ee361874d6db8a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-openllama-7b-v12-bf16", + "Average \u2b06\ufe0f": 45.28, + "ARC": 42.06, + "HellaSwag": 62.01, + "MMLU": 46.53, + "TruthfulQA": 45.18, + "Winogrande": 65.04, + "GSM8K": 10.84, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "bb94ff691996484b1a9d899a6c0956ef6750d86a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/falcon-7B-case-3", + "Average \u2b06\ufe0f": 45.27, + "ARC": 47.78, + "HellaSwag": 78.3, + "MMLU": 31.96, + "TruthfulQA": 36.43, + "Winogrande": 71.03, + "GSM8K": 6.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "86c14bd09f6ebb9d3ebf59bb08b773c2b15630d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "stabilityai\/stablelm-2-1_6b", + "Average \u2b06\ufe0f": 45.25, + "ARC": 43.34, + "HellaSwag": 70.45, + "MMLU": 38.95, + "TruthfulQA": 36.78, + "Winogrande": 64.56, + "GSM8K": 17.44, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.64, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "810b45c00ea0af42ded794f9e613f6fc52330921", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NurtureAI\/Orca-2-13B-16k", + "Average \u2b06\ufe0f": 45.22, + "ARC": 53.67, + "HellaSwag": 69.48, + "MMLU": 41.02, + "TruthfulQA": 45.3, + "Winogrande": 60.06, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "0daee08a5e065d02726e9ae0f05cdfd78992cfba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PotatoOff\/HamSter-0.1", + "Average \u2b06\ufe0f": 45.19, + "ARC": 46.93, + "HellaSwag": 68.08, + "MMLU": 43.03, + "TruthfulQA": 51.24, + "Winogrande": 61.88, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "14b81a0c6870d400cd6216682f182d4615203c2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/llama-shishya-7b-ep3-v1", + "Average \u2b06\ufe0f": 45.19, + "ARC": 48.04, + "HellaSwag": 76.63, + "MMLU": 46.12, + "TruthfulQA": 30.9, + "Winogrande": 69.46, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8dc109f45ef36cc7bbd0f5d83fb65ac8e768d1bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Enno-Ai\/ennodata-7b", + "Average \u2b06\ufe0f": 45.13, + "ARC": 51.02, + "HellaSwag": 77.62, + "MMLU": 33.95, + "TruthfulQA": 33.53, + "Winogrande": 70.96, + "GSM8K": 3.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7872a492ebbb3c6a899f9acbd34dfd5f7e674fdd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jlevin\/guanaco-unchained-llama-2-7b", + "Average \u2b06\ufe0f": 45.11, + "ARC": 47.35, + "HellaSwag": 72.16, + "MMLU": 41.76, + "TruthfulQA": 41.49, + "Winogrande": 64.48, + "GSM8K": 3.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "43f3de8bcef63eec03a1b00079c08b5932c1a429", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-coding-7b-16k-tora", + "Average \u2b06\ufe0f": 45.1, + "ARC": 41.21, + "HellaSwag": 64.45, + "MMLU": 39.14, + "TruthfulQA": 44.91, + "Winogrande": 63.61, + "GSM8K": 17.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d56b5c4f649d8e722efb927d16d7589967a67fbe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/vicuna-7b-v1.5-lora-mctaco-modified4", + "Average \u2b06\ufe0f": 45.1, + "ARC": 40.7, + "HellaSwag": 73.08, + "MMLU": 47.26, + "TruthfulQA": 41.59, + "Winogrande": 67.88, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "715b03c8573df06f3825d1c08b307e2a83fa8bf9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "speechlessai\/speechless-coding-7b-16k-tora", + "Average \u2b06\ufe0f": 45.05, + "ARC": 41.13, + "HellaSwag": 64.48, + "MMLU": 38.86, + "TruthfulQA": 44.95, + "Winogrande": 63.85, + "GSM8K": 17.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "37281f20d54d895f8e3bc660e68564244c775ac2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JosephusCheung\/Qwen-VL-LLaMAfied-7B-Chat", + "Average \u2b06\ufe0f": 45.0, + "ARC": 47.35, + "HellaSwag": 69.97, + "MMLU": 44.12, + "TruthfulQA": 42.87, + "Winogrande": 65.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 32.0, + "Available on the hub": true, + "Model sha": "ccbd599ac46bcfbf7020be393afeecef404bce2b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "tyson0420\/stack_codellama-7b-inst", + "Average \u2b06\ufe0f": 44.97, + "ARC": 43.52, + "HellaSwag": 66.17, + "MMLU": 39.59, + "TruthfulQA": 39.03, + "Winogrande": 65.67, + "GSM8K": 15.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5191aaffef22c923e714c5856a91e7f5a8dcc000", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "csitfun\/llama-7b-logicot", + "Average \u2b06\ufe0f": 44.95, + "ARC": 47.01, + "HellaSwag": 72.56, + "MMLU": 38.93, + "TruthfulQA": 43.63, + "Winogrande": 67.56, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "8e9c93c09e6a6c7d504c88d6ca598144829bced8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/WizardLM-7B-Uncensored", + "Average \u2b06\ufe0f": 44.92, + "ARC": 47.87, + "HellaSwag": 73.08, + "MMLU": 35.42, + "TruthfulQA": 41.49, + "Winogrande": 68.43, + "GSM8K": 3.26, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "14c23f9fa775ab5ce49010418f00df06d92b0b13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenAssistant\/codellama-13b-oasst-sft-v10", + "Average \u2b06\ufe0f": 44.85, + "ARC": 45.39, + "HellaSwag": 62.36, + "MMLU": 35.36, + "TruthfulQA": 45.02, + "Winogrande": 67.8, + "GSM8K": 13.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 63.0, + "Available on the hub": true, + "Model sha": "612dab2a8b2d77edb4fd36cfc28b3ffbbb20ffc1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "M4-ai\/NeuralReyna-Mini-1.8B-v0.2", + "Average \u2b06\ufe0f": 44.85, + "ARC": 37.8, + "HellaSwag": 60.51, + "MMLU": 45.04, + "TruthfulQA": 37.75, + "Winogrande": 60.93, + "GSM8K": 27.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a38dc9a562b52fe228636ac9099e121524187bf1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shareAI\/CodeLLaMA-chat-13b-Chinese", + "Average \u2b06\ufe0f": 44.84, + "ARC": 43.26, + "HellaSwag": 63.87, + "MMLU": 34.29, + "TruthfulQA": 48.97, + "Winogrande": 67.88, + "GSM8K": 10.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "675b3e35a9601683c2cb4ec7f1b11d2869842f36", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Menouar\/saqr-7b-beta", + "Average \u2b06\ufe0f": 44.84, + "ARC": 47.78, + "HellaSwag": 77.61, + "MMLU": 25.8, + "TruthfulQA": 39.38, + "Winogrande": 70.56, + "GSM8K": 7.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9f1f11790bb0ac4ae6ab8081bf798f5b7cd2331d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mosaicml\/mpt-7b-instruct", + "Average \u2b06\ufe0f": 44.83, + "ARC": 50.34, + "HellaSwag": 77.91, + "MMLU": 32.35, + "TruthfulQA": 35.08, + "Winogrande": 70.48, + "GSM8K": 2.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 450.0, + "Available on the hub": false, + "Model sha": "925e0d80e50e77aaddaf9c3ced41ca4ea23a1025", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "uukuguy\/speechless-codellama-orca-13b", + "Average \u2b06\ufe0f": 44.83, + "ARC": 44.37, + "HellaSwag": 65.2, + "MMLU": 43.46, + "TruthfulQA": 45.94, + "Winogrande": 64.01, + "GSM8K": 5.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "6fdfeabe817235df3d560a6e6465c3722bc3a4ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zorobin\/mistral-class-shishya-all-hal-7b-ep3", + "Average \u2b06\ufe0f": 44.8, + "ARC": 46.59, + "HellaSwag": 78.87, + "MMLU": 34.45, + "TruthfulQA": 35.98, + "Winogrande": 72.93, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8f15bc3f0d0235fdb67a8dfb6be36a1ac9c1b8b8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shibing624\/chinese-alpaca-plus-7b-hf", + "Average \u2b06\ufe0f": 44.77, + "ARC": 49.23, + "HellaSwag": 70.48, + "MMLU": 38.39, + "TruthfulQA": 39.72, + "Winogrande": 70.09, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 50.0, + "Available on the hub": true, + "Model sha": "0deb5a13732f1e3e3240ea83f403c57283fe2dc8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GeneZC\/MiniMA-2-3B", + "Average \u2b06\ufe0f": 44.75, + "ARC": 44.71, + "HellaSwag": 69.33, + "MMLU": 41.22, + "TruthfulQA": 38.44, + "Winogrande": 66.69, + "GSM8K": 8.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "03c9985b5427e143a4e8b513393d65b9bb24a2d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "KnutJaegersberg\/Qwen-1_8B-Llamafied", + "Average \u2b06\ufe0f": 44.75, + "ARC": 37.71, + "HellaSwag": 58.87, + "MMLU": 46.37, + "TruthfulQA": 39.41, + "Winogrande": 61.72, + "GSM8K": 24.41, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "2d58d553f3b54abbb6cc49cdb4f2b47336c3c17e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Writer\/palmyra-med-20b", + "Average \u2b06\ufe0f": 44.71, + "ARC": 46.93, + "HellaSwag": 73.51, + "MMLU": 44.34, + "TruthfulQA": 35.47, + "Winogrande": 65.35, + "GSM8K": 2.65, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "407810f75698c95000dc0ae1a9a0457be625e972", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TheBloke\/Poro-34B-GPTQ", + "Average \u2b06\ufe0f": 44.67, + "ARC": 47.01, + "HellaSwag": 73.75, + "MMLU": 32.47, + "TruthfulQA": 38.37, + "Winogrande": 71.35, + "GSM8K": 5.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 48.06, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "f6e034384e36b411d6b831157fb6063060ec1169", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "freecs\/ThetaWave-14B-v0.1", + "Average \u2b06\ufe0f": 44.54, + "ARC": 42.83, + "HellaSwag": 47.09, + "MMLU": 61.45, + "TruthfulQA": 50.41, + "Winogrande": 65.43, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 14.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9e9745166b6f4e125511739d06900e72e5859617", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhinand\/tamil-llama-7b-base-v0.1", + "Average \u2b06\ufe0f": 44.52, + "ARC": 46.67, + "HellaSwag": 72.85, + "MMLU": 40.95, + "TruthfulQA": 35.93, + "Winogrande": 70.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "e40f072bf68a157a18247eb08bf5b18ab8138986", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/Project-Baize-v2-7B-GPTQ", + "Average \u2b06\ufe0f": 44.5, + "ARC": 45.99, + "HellaSwag": 73.44, + "MMLU": 35.46, + "TruthfulQA": 39.92, + "Winogrande": 69.69, + "GSM8K": 2.5, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 9.04, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "5dc039834e1ea42ac334458b2e3090fe3705cc59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "h2oai\/h2o-danube-1.8b-chat", + "Average \u2b06\ufe0f": 44.49, + "ARC": 41.13, + "HellaSwag": 68.06, + "MMLU": 33.41, + "TruthfulQA": 41.64, + "Winogrande": 65.35, + "GSM8K": 17.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.83, + "Hub \u2764\ufe0f": 33.0, + "Available on the hub": true, + "Model sha": "e2a18423798fa43e6c9935073d9c24c0cd901c6d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "qblocks\/falcon_7b_norobots", + "Average \u2b06\ufe0f": 44.46, + "ARC": 47.87, + "HellaSwag": 77.92, + "MMLU": 27.94, + "TruthfulQA": 36.81, + "Winogrande": 71.74, + "GSM8K": 4.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bbe8e4a0c19ec5a94f6eff680b5a55bd08e11e31", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jisukim8873\/falcon-7B-case-6", + "Average \u2b06\ufe0f": 44.44, + "ARC": 46.5, + "HellaSwag": 78.49, + "MMLU": 28.97, + "TruthfulQA": 36.46, + "Winogrande": 70.09, + "GSM8K": 6.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "af9e538c8c2758bfe09a538f2093a6f4196a2b76", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WeOpenML\/Alpaca-7B-v1", + "Average \u2b06\ufe0f": 44.41, + "ARC": 49.06, + "HellaSwag": 75.71, + "MMLU": 33.76, + "TruthfulQA": 36.28, + "Winogrande": 71.51, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "be5cb84a84a859dd6e5e3efc4648d6d5d1a5d188", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "qblocks\/falcon_7b_norobots", + "Average \u2b06\ufe0f": 44.4, + "ARC": 48.12, + "HellaSwag": 77.9, + "MMLU": 28.11, + "TruthfulQA": 36.76, + "Winogrande": 71.59, + "GSM8K": 3.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bbe8e4a0c19ec5a94f6eff680b5a55bd08e11e31", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "castorini\/rank_vicuna_7b_v1_fp16", + "Average \u2b06\ufe0f": 44.36, + "ARC": 44.62, + "HellaSwag": 65.67, + "MMLU": 44.14, + "TruthfulQA": 45.13, + "Winogrande": 66.61, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "0f3556bb0227cb59bcc652584d879f3bc40102e6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/llama-shishya-7b-ep3-v2", + "Average \u2b06\ufe0f": 44.33, + "ARC": 47.35, + "HellaSwag": 75.88, + "MMLU": 43.84, + "TruthfulQA": 30.16, + "Winogrande": 68.75, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "679c6cb9e869df686b1ae415ed440e6cfc05f80b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "codellama\/CodeLlama-34b-Instruct-hf", + "Average \u2b06\ufe0f": 44.33, + "ARC": 40.78, + "HellaSwag": 35.66, + "MMLU": 39.72, + "TruthfulQA": 44.29, + "Winogrande": 74.51, + "GSM8K": 31.01, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 256.0, + "Available on the hub": true, + "Model sha": "c109b9dde086b31725fa09ff7effdc04c03c033d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "liminerity\/ultra0", + "Average \u2b06\ufe0f": 44.32, + "ARC": 41.47, + "HellaSwag": 68.02, + "MMLU": 33.37, + "TruthfulQA": 41.49, + "Winogrande": 65.51, + "GSM8K": 16.07, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.83, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "046f98426c1b0da043e82a110f9690268b826b5f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/koala-7B-HF", + "Average \u2b06\ufe0f": 44.29, + "ARC": 47.1, + "HellaSwag": 73.58, + "MMLU": 25.53, + "TruthfulQA": 45.96, + "Winogrande": 69.93, + "GSM8K": 3.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "d102fe3b68f1a5a50d547e4fd1c8b33b783c993b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "anas-awadalla\/mpt-7b", + "Average \u2b06\ufe0f": 44.28, + "ARC": 47.7, + "HellaSwag": 77.57, + "MMLU": 30.8, + "TruthfulQA": 33.44, + "Winogrande": 72.14, + "GSM8K": 4.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "b772e556c8e8a17d087db6935e7cd019e5eefb0f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "mosaicml\/mpt-7b", + "Average \u2b06\ufe0f": 44.28, + "ARC": 47.7, + "HellaSwag": 77.57, + "MMLU": 30.8, + "TruthfulQA": 33.44, + "Winogrande": 72.14, + "GSM8K": 4.02, + "Type": "pretrained", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1129.0, + "Available on the hub": false, + "Model sha": "72e5f594ce36f9cabfa2a9fd8f58b491eb467ee7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zorobin\/mistral-class-shishya-7b-ep3", + "Average \u2b06\ufe0f": 44.28, + "ARC": 46.59, + "HellaSwag": 76.62, + "MMLU": 39.07, + "TruthfulQA": 33.54, + "Winogrande": 69.85, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e85b73ce67deaa5b40633c5ce2545b23fa3ff3a0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "openlm-research\/open_llama_7b_v2", + "Average \u2b06\ufe0f": 44.26, + "ARC": 43.69, + "HellaSwag": 72.2, + "MMLU": 41.29, + "TruthfulQA": 35.54, + "Winogrande": 69.38, + "GSM8K": 3.49, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 104.0, + "Available on the hub": true, + "Model sha": "e5961def23172a2384543940e773ab676033c963", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Charlie911\/MultiLora-sharegpt", + "Average \u2b06\ufe0f": 44.26, + "ARC": 45.65, + "HellaSwag": 65.54, + "MMLU": 37.95, + "TruthfulQA": 45.85, + "Winogrande": 66.61, + "GSM8K": 3.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9375b805eaaf89eff195d7a2b74a3590a1c525f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "llm-agents\/tora-code-13b-v1.0", + "Average \u2b06\ufe0f": 44.19, + "ARC": 44.71, + "HellaSwag": 69.15, + "MMLU": 36.69, + "TruthfulQA": 34.98, + "Winogrande": 63.14, + "GSM8K": 16.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "4bf5b528d95a507b435c24a8986afe80d5951782", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Writer\/palmyra-20b-chat", + "Average \u2b06\ufe0f": 44.18, + "ARC": 43.52, + "HellaSwag": 72.83, + "MMLU": 35.18, + "TruthfulQA": 43.17, + "Winogrande": 66.46, + "GSM8K": 3.94, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": false, + "Model sha": "3b7442b7e2240846bc9cfac545bd8861c1660aa2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "tiiuae\/falcon-7b", + "Average \u2b06\ufe0f": 44.17, + "ARC": 47.87, + "HellaSwag": 78.13, + "MMLU": 27.79, + "TruthfulQA": 34.26, + "Winogrande": 72.38, + "GSM8K": 4.62, + "Type": "pretrained", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 997.0, + "Available on the hub": true, + "Model sha": "378337427557d1df3e742264a2901a49f25d4eb1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "speechlessai\/speechless-codellama-airoboros-orca-platypus-13b", + "Average \u2b06\ufe0f": 44.1, + "ARC": 44.88, + "HellaSwag": 67.7, + "MMLU": 43.16, + "TruthfulQA": 40.88, + "Winogrande": 66.14, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f01d3ab70cc23e31dcf5d6418406b08dc2003153", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "qblocks\/falcon_7b_DolphinCoder", + "Average \u2b06\ufe0f": 44.09, + "ARC": 48.72, + "HellaSwag": 78.03, + "MMLU": 27.08, + "TruthfulQA": 35.12, + "Winogrande": 70.48, + "GSM8K": 5.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "15a07f5340cbb9b6f37db3cda7aa02169feed89f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zangs3011\/falcon_7b_DolphinCoder", + "Average \u2b06\ufe0f": 44.09, + "ARC": 48.72, + "HellaSwag": 78.03, + "MMLU": 27.08, + "TruthfulQA": 35.12, + "Winogrande": 70.48, + "GSM8K": 5.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "72558e09e54869de3d8fc9fdd42633b81a1839f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "bn999\/mistral-4.2B", + "Average \u2b06\ufe0f": 44.06, + "ARC": 40.87, + "HellaSwag": 61.51, + "MMLU": 41.78, + "TruthfulQA": 44.82, + "Winogrande": 63.77, + "GSM8K": 11.6, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8818646580d58ba59268e6d9bb3a43ffafe90fd2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/GPT-JT-6B-v0", + "Average \u2b06\ufe0f": 44.05, + "ARC": 42.06, + "HellaSwag": 67.96, + "MMLU": 49.34, + "TruthfulQA": 38.89, + "Winogrande": 64.8, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "41bd1937dbc51f9e589d310bddab5b4c1409e783", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "cyberagent\/calm2-7b-chat-dpo-experimental", + "Average \u2b06\ufe0f": 44.03, + "ARC": 41.04, + "HellaSwag": 68.99, + "MMLU": 39.82, + "TruthfulQA": 43.13, + "Winogrande": 65.67, + "GSM8K": 5.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 7.01, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "d55a77e9843b4c3848f4e82a4bc303d5a9ec47ff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "luffycodes\/llama-class-shishya-7b-ep3", + "Average \u2b06\ufe0f": 43.88, + "ARC": 40.78, + "HellaSwag": 77.04, + "MMLU": 46.74, + "TruthfulQA": 27.94, + "Winogrande": 70.8, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "92802ec9c58b1ed64d758c0f0c8420f4000636ff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/BigTranslate-13B-GPTQ", + "Average \u2b06\ufe0f": 43.86, + "ARC": 45.31, + "HellaSwag": 75.1, + "MMLU": 31.18, + "TruthfulQA": 40.6, + "Winogrande": 70.96, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 17.99, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "f2968552d2f522023f3289747234aea5508980e2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lvxy1117\/amber_fine_tune_sgall", + "Average \u2b06\ufe0f": 43.77, + "ARC": 44.28, + "HellaSwag": 74.77, + "MMLU": 31.29, + "TruthfulQA": 40.48, + "Winogrande": 67.48, + "GSM8K": 4.32, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "242e01d032be75c8e3282917a8f39b721296f645", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ise-uiuc\/Magicoder-S-CL-7B", + "Average \u2b06\ufe0f": 43.73, + "ARC": 43.34, + "HellaSwag": 67.01, + "MMLU": 36.87, + "TruthfulQA": 38.67, + "Winogrande": 62.19, + "GSM8K": 14.33, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 36.0, + "Available on the hub": true, + "Model sha": "cf49bc9879266bfc0a0123aaa4ef644af1b20c04", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "AI-Sweden-Models\/gpt-sw3-20b-instruct", + "Average \u2b06\ufe0f": 43.7, + "ARC": 43.17, + "HellaSwag": 71.09, + "MMLU": 31.32, + "TruthfulQA": 41.02, + "Winogrande": 66.77, + "GSM8K": 8.79, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 20.92, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "006477ad4c4875611f20cd927f1fd76bbf5ba5ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2o-danube-1.8b-sft", + "Average \u2b06\ufe0f": 43.68, + "ARC": 40.19, + "HellaSwag": 67.34, + "MMLU": 33.75, + "TruthfulQA": 40.29, + "Winogrande": 65.43, + "GSM8K": 15.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.83, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "251a6e5b0749135c6109532734b803d15dd49b7a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "synapsoft\/Llama-2-7b-hf-flan2022-1.2M", + "Average \u2b06\ufe0f": 43.68, + "ARC": 23.29, + "HellaSwag": 78.46, + "MMLU": 42.33, + "TruthfulQA": 37.97, + "Winogrande": 75.53, + "GSM8K": 4.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "792f946a1413a7c58378d7a350b7d75b9df80561", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "souvik0306\/falcon_7b_3epoch_norobots", + "Average \u2b06\ufe0f": 43.65, + "ARC": 47.61, + "HellaSwag": 77.24, + "MMLU": 29.73, + "TruthfulQA": 36.27, + "Winogrande": 69.53, + "GSM8K": 1.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "55b11c279d1a5b83f59cec0381fb41c31fd02d8d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hyunseoki\/ko-ref-llama2-13b", + "Average \u2b06\ufe0f": 43.62, + "ARC": 48.38, + "HellaSwag": 73.56, + "MMLU": 34.83, + "TruthfulQA": 35.82, + "Winogrande": 69.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "c5d09631c88ab5012b48187ecd90ae773cd4bbd9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "deepseek-ai\/deepseek-coder-6.7b-instruct", + "Average \u2b06\ufe0f": 43.57, + "ARC": 38.14, + "HellaSwag": 55.09, + "MMLU": 39.02, + "TruthfulQA": 45.56, + "Winogrande": 56.83, + "GSM8K": 26.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 213.0, + "Available on the hub": true, + "Model sha": "cbb77d7448ea3168d884758817e7f895e3828d1c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lvxy1117\/amber_fine_tune_sg_part1", + "Average \u2b06\ufe0f": 43.5, + "ARC": 44.88, + "HellaSwag": 75.1, + "MMLU": 29.36, + "TruthfulQA": 40.85, + "Winogrande": 67.01, + "GSM8K": 3.79, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b9ed86588ba7f315e10072c4976b6a71cbf0f747", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AI-Sweden-Models\/gpt-sw3-40b", + "Average \u2b06\ufe0f": 43.42, + "ARC": 43.0, + "HellaSwag": 72.37, + "MMLU": 34.97, + "TruthfulQA": 37.52, + "Winogrande": 67.96, + "GSM8K": 4.7, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 39.93, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "ed18193e7292b5a821e5271d5dac95fffdf9617c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "l3utterfly\/minima-3b-layla-v2", + "Average \u2b06\ufe0f": 43.39, + "ARC": 44.2, + "HellaSwag": 69.93, + "MMLU": 28.53, + "TruthfulQA": 43.64, + "Winogrande": 65.43, + "GSM8K": 8.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "118b6f7cf649f829afdec715eb4720dcd2a572b9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/CodeLlama-13b-hf", + "Average \u2b06\ufe0f": 43.35, + "ARC": 40.87, + "HellaSwag": 63.35, + "MMLU": 32.81, + "TruthfulQA": 43.79, + "Winogrande": 67.17, + "GSM8K": 12.13, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b7cfbbce945b966607d15ae275704922a6d04afc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "codellama\/CodeLlama-13b-hf", + "Average \u2b06\ufe0f": 43.35, + "ARC": 40.87, + "HellaSwag": 63.35, + "MMLU": 32.81, + "TruthfulQA": 43.79, + "Winogrande": 67.17, + "GSM8K": 12.13, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 81.0, + "Available on the hub": true, + "Model sha": "55876f398020b287ac845b34ca08089acf4f4bc3", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TigerResearch\/tigerbot-7b-sft", + "Average \u2b06\ufe0f": 43.35, + "ARC": 41.64, + "HellaSwag": 60.56, + "MMLU": 29.89, + "TruthfulQA": 58.18, + "Winogrande": 63.54, + "GSM8K": 6.29, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.07, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "98b847905d63f74624e834db1ff95ee2814cbbd3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "qnguyen3\/quan-1.8b-base", + "Average \u2b06\ufe0f": 43.35, + "ARC": 36.95, + "HellaSwag": 58.46, + "MMLU": 45.44, + "TruthfulQA": 41.6, + "Winogrande": 57.93, + "GSM8K": 19.71, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.8, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ae98577d590a16cdbad681e981c5b431f9e246ea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "namirocks\/mistral-shishya-all-hal-7b-ep3-v2", + "Average \u2b06\ufe0f": 43.31, + "ARC": 45.9, + "HellaSwag": 74.29, + "MMLU": 30.21, + "TruthfulQA": 39.71, + "Winogrande": 69.77, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1f0c52aff9af9a5b49ed2dc255670946f98c04cb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fierysurf\/Kan-LLaMA-7B-base", + "Average \u2b06\ufe0f": 43.31, + "ARC": 43.94, + "HellaSwag": 70.75, + "MMLU": 37.06, + "TruthfulQA": 39.57, + "Winogrande": 68.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.88, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "66ae057862e1201128113b4c8f3875c1a3fd8ef2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lvxy1117\/amber_fine_tune_001", + "Average \u2b06\ufe0f": 43.28, + "ARC": 44.8, + "HellaSwag": 73.78, + "MMLU": 30.41, + "TruthfulQA": 42.93, + "Winogrande": 64.09, + "GSM8K": 3.64, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "389916bd805c635b3c118b896ed1a8f2333a3e4d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "cyberagent\/calm2-7b-chat", + "Average \u2b06\ufe0f": 43.27, + "ARC": 40.27, + "HellaSwag": 68.12, + "MMLU": 39.39, + "TruthfulQA": 41.96, + "Winogrande": 64.96, + "GSM8K": 4.93, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 60.0, + "Available on the hub": true, + "Model sha": "f666a1e43500643cb3ff8c988a6ea5b56afe934a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/finetune_test_qwen15-1-8b-sft-lora", + "Average \u2b06\ufe0f": 43.27, + "ARC": 36.18, + "HellaSwag": 57.77, + "MMLU": 44.96, + "TruthfulQA": 38.0, + "Winogrande": 61.17, + "GSM8K": 21.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "07c78da7631c0e3b0f22558803de182d9255a19b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "tiiuae\/falcon-7b-instruct", + "Average \u2b06\ufe0f": 43.26, + "ARC": 46.16, + "HellaSwag": 70.85, + "MMLU": 25.84, + "TruthfulQA": 44.08, + "Winogrande": 67.96, + "GSM8K": 4.7, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 830.0, + "Available on the hub": true, + "Model sha": "cf4b3c42ce2fdfe24f753f0f0d179202fea59c99", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "JosephusCheung\/Guanaco", + "Average \u2b06\ufe0f": 43.25, + "ARC": 50.17, + "HellaSwag": 72.69, + "MMLU": 30.3, + "TruthfulQA": 37.64, + "Winogrande": 68.67, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 225.0, + "Available on the hub": true, + "Model sha": "bed6f3bd18f07a4a379525645cbd86d622b12836", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "l3utterfly\/minima-3b-layla-v1", + "Average \u2b06\ufe0f": 43.21, + "ARC": 42.32, + "HellaSwag": 67.48, + "MMLU": 28.44, + "TruthfulQA": 46.46, + "Winogrande": 65.9, + "GSM8K": 8.64, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "844bfa44b1b3cdd1c0e39c13fbb2fdaee82ff874", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "tiiuae\/falcon-7b-instruct", + "Average \u2b06\ufe0f": 43.16, + "ARC": 45.82, + "HellaSwag": 70.78, + "MMLU": 25.66, + "TruthfulQA": 44.07, + "Winogrande": 68.03, + "GSM8K": 4.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 830.0, + "Available on the hub": true, + "Model sha": "eb410fb6ffa9028e97adb801f0d6ec46d02f8b07", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ziqingyang\/chinese-llama-2-7b", + "Average \u2b06\ufe0f": 43.14, + "ARC": 44.45, + "HellaSwag": 69.5, + "MMLU": 37.47, + "TruthfulQA": 37.0, + "Winogrande": 68.98, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "557b5cbd48a4a4eb5a08e975c4b6e11ac1ed4cbc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/GPT-JT-6B-v1", + "Average \u2b06\ufe0f": 43.13, + "ARC": 40.87, + "HellaSwag": 67.15, + "MMLU": 47.19, + "TruthfulQA": 37.07, + "Winogrande": 65.27, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 301.0, + "Available on the hub": true, + "Model sha": "f34aa35f906895602c1f86f5685e598afdea8051", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "u-chom\/ex-llm-e1", + "Average \u2b06\ufe0f": 43.11, + "ARC": 39.93, + "HellaSwag": 68.11, + "MMLU": 39.44, + "TruthfulQA": 42.01, + "Winogrande": 64.88, + "GSM8K": 4.32, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5838bea0ad7153520a0a105fb81c5b895820f710", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "FreedomIntelligence\/phoenix-inst-chat-7b", + "Average \u2b06\ufe0f": 43.03, + "ARC": 44.71, + "HellaSwag": 63.23, + "MMLU": 39.06, + "TruthfulQA": 47.08, + "Winogrande": 62.83, + "GSM8K": 1.29, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 43.0, + "Available on the hub": true, + "Model sha": "5ed4d9570e0f76e1becb05bf467a7b4ff7b66055", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/GPT-NeoXT-Chat-Base-20B", + "Average \u2b06\ufe0f": 43.02, + "ARC": 45.65, + "HellaSwag": 74.03, + "MMLU": 29.92, + "TruthfulQA": 34.51, + "Winogrande": 67.09, + "GSM8K": 6.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 694.0, + "Available on the hub": true, + "Model sha": "d386708e84d862a65f7d2b4989f64750cb657227", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GeorgiaTechResearchInstitute\/galpaca-30b", + "Average \u2b06\ufe0f": 43.0, + "ARC": 49.57, + "HellaSwag": 58.2, + "MMLU": 43.78, + "TruthfulQA": 41.16, + "Winogrande": 62.51, + "GSM8K": 2.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 56.0, + "Available on the hub": true, + "Model sha": "a1f0c4bedd65b485a0d4d3a3bd60d7a4599f1eaf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TheBloke\/CodeLlama-34B-Instruct-fp16", + "Average \u2b06\ufe0f": 43.0, + "ARC": 40.78, + "HellaSwag": 35.66, + "MMLU": 39.72, + "TruthfulQA": 44.29, + "Winogrande": 74.51, + "GSM8K": 23.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "a4d0ce949de4d5b5f74691641efb5b70736a32a8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lyogavin\/Anima-7B-100K", + "Average \u2b06\ufe0f": 42.98, + "ARC": 46.59, + "HellaSwag": 72.28, + "MMLU": 33.4, + "TruthfulQA": 37.84, + "Winogrande": 67.09, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "e303cf09e553c38ca5e0c0816d83631801ca5776", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Deita-1_8B", + "Average \u2b06\ufe0f": 42.96, + "ARC": 36.52, + "HellaSwag": 60.63, + "MMLU": 45.62, + "TruthfulQA": 40.02, + "Winogrande": 59.35, + "GSM8K": 15.62, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 8.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7709179d3919f48660b0bf58e5efcca2c45e2659", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Qwen-1_8B-Chat-llama", + "Average \u2b06\ufe0f": 42.94, + "ARC": 36.95, + "HellaSwag": 54.34, + "MMLU": 44.55, + "TruthfulQA": 43.7, + "Winogrande": 58.88, + "GSM8K": 19.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a84c11285875fecd9c1cc4e22543efbd4f89f5fe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Writer\/InstructPalmyra-20b", + "Average \u2b06\ufe0f": 42.91, + "ARC": 47.1, + "HellaSwag": 73.0, + "MMLU": 28.26, + "TruthfulQA": 41.81, + "Winogrande": 64.72, + "GSM8K": 2.58, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 39.0, + "Available on the hub": true, + "Model sha": "c78df447c70d4677b128b1df864b9fff8338d900", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vihangd\/dopeyshearedplats-2.7b-v1", + "Average \u2b06\ufe0f": 42.9, + "ARC": 46.08, + "HellaSwag": 75.17, + "MMLU": 29.01, + "TruthfulQA": 44.12, + "Winogrande": 62.67, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c125218041c01662dc4c59b3f344aaa4e53dfd18", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/gpt-neox-20b-full-precision", + "Average \u2b06\ufe0f": 42.87, + "ARC": 48.81, + "HellaSwag": 74.44, + "MMLU": 26.16, + "TruthfulQA": 36.89, + "Winogrande": 68.27, + "GSM8K": 2.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "20b347273d90da7c2c9eb4c32d4173dba862a0d2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Pierre-obi\/Mistral_solar-slerp", + "Average \u2b06\ufe0f": 42.86, + "ARC": 43.0, + "HellaSwag": 57.93, + "MMLU": 40.48, + "TruthfulQA": 46.96, + "Winogrande": 68.19, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "874e9960000eb9abadc57755cc4251bcfe369302", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/landmark-attention-llama7b-fp16", + "Average \u2b06\ufe0f": 42.84, + "ARC": 47.35, + "HellaSwag": 65.81, + "MMLU": 31.59, + "TruthfulQA": 42.63, + "Winogrande": 68.03, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bf8bdcb0c30cceb0ceda33cf5fde683807e39a58", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "azarafrooz\/gemma-2b-it-sp-test1", + "Average \u2b06\ufe0f": 42.79, + "ARC": 44.03, + "HellaSwag": 62.82, + "MMLU": 37.67, + "TruthfulQA": 45.77, + "Winogrande": 61.17, + "GSM8K": 5.31, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "788d71c479bb22a4030e48ae4eb1378bc1631f08", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/opt-66b", + "Average \u2b06\ufe0f": 42.78, + "ARC": 46.33, + "HellaSwag": 76.25, + "MMLU": 26.99, + "TruthfulQA": 35.43, + "Winogrande": 70.01, + "GSM8K": 1.67, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 66.0, + "Hub \u2764\ufe0f": 173.0, + "Available on the hub": true, + "Model sha": "7259969061237fe940036d22bea0fd349e4485e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Syed-Hasan-8503\/openhermes-gemma-2b-it", + "Average \u2b06\ufe0f": 42.78, + "ARC": 43.94, + "HellaSwag": 62.74, + "MMLU": 37.62, + "TruthfulQA": 45.83, + "Winogrande": 60.93, + "GSM8K": 5.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "a104bc34d3a72e1ed7f3d469591b15dc03dd9725", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abideen\/gemma-2b-openhermes", + "Average \u2b06\ufe0f": 42.78, + "ARC": 43.94, + "HellaSwag": 62.74, + "MMLU": 37.62, + "TruthfulQA": 45.83, + "Winogrande": 60.93, + "GSM8K": 5.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1a8acd4de3c052bd07b6acc89c416d75033e710b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Qwen-1_8b-EverythingLM", + "Average \u2b06\ufe0f": 42.77, + "ARC": 38.65, + "HellaSwag": 62.66, + "MMLU": 44.94, + "TruthfulQA": 38.7, + "Winogrande": 58.96, + "GSM8K": 12.74, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "41d81d4bc5408e4632c967448eb8ec22851fdef5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "google\/gemma-2b-it", + "Average \u2b06\ufe0f": 42.75, + "ARC": 43.94, + "HellaSwag": 62.7, + "MMLU": 37.65, + "TruthfulQA": 45.82, + "Winogrande": 60.93, + "GSM8K": 5.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GemmaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.51, + "Hub \u2764\ufe0f": 317.0, + "Available on the hub": true, + "Model sha": "9642e777f24fde593d204a9b2471dce33334e64a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "llm-agents\/tora-code-13b-v1.0", + "Average \u2b06\ufe0f": 42.7, + "ARC": 44.45, + "HellaSwag": 69.29, + "MMLU": 36.67, + "TruthfulQA": 34.98, + "Winogrande": 62.59, + "GSM8K": 8.19, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "4bf5b528d95a507b435c24a8986afe80d5951782", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "VMware\/open-llama-7b-open-instruct", + "Average \u2b06\ufe0f": 42.59, + "ARC": 49.74, + "HellaSwag": 73.67, + "MMLU": 31.52, + "TruthfulQA": 34.65, + "Winogrande": 65.43, + "GSM8K": 0.53, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-3.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "fdf9f034163cce67e04d55172155f0e07b1b19a0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Salesforce\/codegen-16B-nl", + "Average \u2b06\ufe0f": 42.59, + "ARC": 46.76, + "HellaSwag": 71.87, + "MMLU": 32.35, + "TruthfulQA": 33.95, + "Winogrande": 67.96, + "GSM8K": 2.65, + "Type": "pretrained", + "Architecture": "CodeGenForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bsd-3-clause", + "#Params (B)": 16.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "b65951b0cf7c5639f73caea801a892788608ed69", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-gm-oasst1-en-1024-20b", + "Average \u2b06\ufe0f": 42.58, + "ARC": 48.04, + "HellaSwag": 72.76, + "MMLU": 25.96, + "TruthfulQA": 39.92, + "Winogrande": 66.3, + "GSM8K": 2.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "1a5b8d25587eab67d837621a6c9423e7ef6df289", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/oasst-gpt-neox-20b-1000-steps", + "Average \u2b06\ufe0f": 42.51, + "ARC": 48.55, + "HellaSwag": 74.61, + "MMLU": 26.39, + "TruthfulQA": 35.63, + "Winogrande": 66.77, + "GSM8K": 3.11, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4aec11ef19103796fb21387ce925b63c9d61dae1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vibhorag101\/llama-2-13b-chat-hf-phr_mental_therapy", + "Average \u2b06\ufe0f": 42.5, + "ARC": 38.82, + "HellaSwag": 72.76, + "MMLU": 23.12, + "TruthfulQA": 46.92, + "Winogrande": 65.59, + "GSM8K": 7.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0fe5a48f3d99492cb180fc6efda5b138677ca1de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "aevalone\/Test-7B-pthrough", + "Average \u2b06\ufe0f": 42.47, + "ARC": 44.37, + "HellaSwag": 51.19, + "MMLU": 49.31, + "TruthfulQA": 48.57, + "Winogrande": 60.14, + "GSM8K": 1.21, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "67127c0796b2c49f86f68ebb10e6a5707e0d59cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-oasst1-512-20b", + "Average \u2b06\ufe0f": 42.44, + "ARC": 46.93, + "HellaSwag": 72.77, + "MMLU": 26.25, + "TruthfulQA": 37.5, + "Winogrande": 68.03, + "GSM8K": 3.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 38.0, + "Available on the hub": true, + "Model sha": "3bdf6f870ca14bcc5587b666fbe57488f7854d30", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhinand\/tamil-llama-7b-instruct-v0.2", + "Average \u2b06\ufe0f": 42.41, + "ARC": 40.19, + "HellaSwag": 68.83, + "MMLU": 23.12, + "TruthfulQA": 50.04, + "Winogrande": 66.77, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "eef294818ba3fa799055e80ea28d12d2b7176070", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "qblocks\/codellama_7b_DolphinCoder", + "Average \u2b06\ufe0f": 42.39, + "ARC": 41.98, + "HellaSwag": 65.5, + "MMLU": 38.11, + "TruthfulQA": 35.45, + "Winogrande": 63.61, + "GSM8K": 9.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7a0aaba040ae0b122737172db4581f2d0b1064bf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zangs3011\/codellama_7b_DolphinCoder", + "Average \u2b06\ufe0f": 42.39, + "ARC": 41.98, + "HellaSwag": 65.5, + "MMLU": 38.11, + "TruthfulQA": 35.45, + "Winogrande": 63.61, + "GSM8K": 9.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "600d70148047ad1ec7cb99a596dfeb8ba6a2c42c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ise-uiuc\/Magicoder-S-DS-6.7B", + "Average \u2b06\ufe0f": 42.39, + "ARC": 38.31, + "HellaSwag": 54.48, + "MMLU": 38.71, + "TruthfulQA": 41.0, + "Winogrande": 58.41, + "GSM8K": 23.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 179.0, + "Available on the hub": true, + "Model sha": "cff055b1e110cbe75c0c3759bd436299c6d6bb66", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abhinand\/tamil-llama-7b-instruct-v0.2", + "Average \u2b06\ufe0f": 42.39, + "ARC": 40.44, + "HellaSwag": 68.88, + "MMLU": 23.12, + "TruthfulQA": 50.11, + "Winogrande": 66.46, + "GSM8K": 5.31, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "eef294818ba3fa799055e80ea28d12d2b7176070", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "JosephusCheung\/LL7M", + "Average \u2b06\ufe0f": 42.38, + "ARC": 44.97, + "HellaSwag": 68.81, + "MMLU": 34.44, + "TruthfulQA": 41.39, + "Winogrande": 64.09, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 0.01, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": true, + "Model sha": "9b31bbf38a43d41eaf166fb3573f706b23cb1c13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/RedPajama-INCITE-7B-Instruct", + "Average \u2b06\ufe0f": 42.38, + "ARC": 44.11, + "HellaSwag": 72.02, + "MMLU": 37.62, + "TruthfulQA": 33.96, + "Winogrande": 64.96, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 103.0, + "Available on the hub": true, + "Model sha": "95667a602ff2646bf67fe3a57c4eb9a1edec87fe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/RedPajama-INCITE-Instruct-7B-v0.1", + "Average \u2b06\ufe0f": 42.38, + "ARC": 44.11, + "HellaSwag": 72.02, + "MMLU": 37.62, + "TruthfulQA": 33.96, + "Winogrande": 64.96, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.65, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "95667a602ff2646bf67fe3a57c4eb9a1edec87fe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "openlm-research\/open_llama_7b", + "Average \u2b06\ufe0f": 42.31, + "ARC": 47.01, + "HellaSwag": 71.98, + "MMLU": 30.49, + "TruthfulQA": 34.85, + "Winogrande": 67.96, + "GSM8K": 1.59, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 119.0, + "Available on the hub": true, + "Model sha": "6fb184ff23774c25bf84b3628e49c8b78372c7be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "occultml\/Helios-10.7B-v2", + "Average \u2b06\ufe0f": 42.25, + "ARC": 39.16, + "HellaSwag": 46.63, + "MMLU": 41.57, + "TruthfulQA": 55.51, + "Winogrande": 70.64, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "79b8aaa82a404ee79cbd724213d3c85910e4dec2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cmarkea\/bloomz-7b1-mt-sft-chat", + "Average \u2b06\ufe0f": 42.24, + "ARC": 44.03, + "HellaSwag": 62.6, + "MMLU": 38.64, + "TruthfulQA": 44.34, + "Winogrande": 63.3, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 7.07, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "8c2dc302780fe320ee3428f3db2ee7ff3684dcef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Galpaca-30b-MiniOrca", + "Average \u2b06\ufe0f": 42.23, + "ARC": 48.89, + "HellaSwag": 57.8, + "MMLU": 43.72, + "TruthfulQA": 41.1, + "Winogrande": 60.06, + "GSM8K": 1.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 29.97, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "681d92f8f71ca3e8425da19afee89ed84baedf1d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenAssistant\/pythia-12b-sft-v8-7k-steps", + "Average \u2b06\ufe0f": 42.21, + "ARC": 44.03, + "HellaSwag": 70.28, + "MMLU": 26.55, + "TruthfulQA": 36.53, + "Winogrande": 65.27, + "GSM8K": 10.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "275c9b71bfab4e271d1ed85515c61e317b6ef65e", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "bigscience\/bloomz-7b1", + "Average \u2b06\ufe0f": 42.21, + "ARC": 42.49, + "HellaSwag": 63.01, + "MMLU": 37.85, + "TruthfulQA": 45.2, + "Winogrande": 64.64, + "GSM8K": 0.08, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 121.0, + "Available on the hub": true, + "Model sha": "2f4c4f3ebcf171dbbe2bae989ea2d2f3d3486a97", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "klosax\/open_llama_13b_600bt_preview", + "Average \u2b06\ufe0f": 42.21, + "ARC": 44.28, + "HellaSwag": 72.43, + "MMLU": 31.47, + "TruthfulQA": 34.66, + "Winogrande": 68.43, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3465eaca4d293ccc6ce66888e6c8bd9032ae7071", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "namirocks\/mistral-shishya-all-hal-model-7b-ep3", + "Average \u2b06\ufe0f": 42.19, + "ARC": 37.97, + "HellaSwag": 77.77, + "MMLU": 26.56, + "TruthfulQA": 36.43, + "Winogrande": 74.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "582f60bf69f13025142983fa4b655049d65efd0a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "occultml\/Helios-10.7B", + "Average \u2b06\ufe0f": 42.19, + "ARC": 38.91, + "HellaSwag": 46.6, + "MMLU": 41.4, + "TruthfulQA": 55.52, + "Winogrande": 70.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7f6e3c76304241500e010979e243d712a0dedb67", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TehVenom\/Moderator-Chan_GPT-JT-6b", + "Average \u2b06\ufe0f": 42.17, + "ARC": 43.69, + "HellaSwag": 70.77, + "MMLU": 35.61, + "TruthfulQA": 36.05, + "Winogrande": 65.59, + "GSM8K": 1.29, + "Type": "", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f2b7cda25f6965c1551fa78e9e38676994bc6638", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "bigscience\/bloomz-7b1-mt", + "Average \u2b06\ufe0f": 42.14, + "ARC": 43.86, + "HellaSwag": 62.91, + "MMLU": 37.35, + "TruthfulQA": 45.65, + "Winogrande": 63.06, + "GSM8K": 0.0, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 128.0, + "Available on the hub": true, + "Model sha": "76875e6ea8df98157fb032c48ad6e354fd6a077b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Heng666\/EastAsia-4x7B-Moe-experiment", + "Average \u2b06\ufe0f": 42.12, + "ARC": 39.51, + "HellaSwag": 48.92, + "MMLU": 56.2, + "TruthfulQA": 49.83, + "Winogrande": 58.09, + "GSM8K": 0.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 18.52, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "44d2f9bfc6538102d101054d2366cb389fb713d9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "princeton-nlp\/Sheared-LLaMA-2.7B-ShareGPT", + "Average \u2b06\ufe0f": 42.11, + "ARC": 41.04, + "HellaSwag": 71.26, + "MMLU": 28.5, + "TruthfulQA": 47.71, + "Winogrande": 64.17, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "802be8903ec44f49a883915882868b479ecdcc3b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Writer\/palmyra-large", + "Average \u2b06\ufe0f": 42.09, + "ARC": 44.97, + "HellaSwag": 71.85, + "MMLU": 28.54, + "TruthfulQA": 35.93, + "Winogrande": 67.88, + "GSM8K": 3.41, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "40086d791942cb28f55e679cd3fb6f6b5ba4effd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "RWKV\/rwkv-raven-14b", + "Average \u2b06\ufe0f": 42.09, + "ARC": 44.62, + "HellaSwag": 71.25, + "MMLU": 25.92, + "TruthfulQA": 41.93, + "Winogrande": 66.69, + "GSM8K": 2.12, + "Type": "pretrained", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 14.0, + "Hub \u2764\ufe0f": 55.0, + "Available on the hub": false, + "Model sha": "359c0649b4f1d10a26ebea32908035bc00d152ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AlekseyKorshuk\/pygmalion-6b-vicuna-chatml", + "Average \u2b06\ufe0f": 42.08, + "ARC": 40.61, + "HellaSwag": 67.73, + "MMLU": 33.92, + "TruthfulQA": 42.76, + "Winogrande": 63.06, + "GSM8K": 4.4, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ee3ada91a69a194cedfabbfeab98f1499b75cb44", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "acrastt\/Marx-3B-V2", + "Average \u2b06\ufe0f": 42.08, + "ARC": 44.03, + "HellaSwag": 72.92, + "MMLU": 27.84, + "TruthfulQA": 39.92, + "Winogrande": 66.54, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "5fba568304f6f876f5b9e42026f986ea245b836b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NurtureAI\/Orca-2-7B-16k", + "Average \u2b06\ufe0f": 42.05, + "ARC": 50.6, + "HellaSwag": 63.89, + "MMLU": 36.68, + "TruthfulQA": 45.37, + "Winogrande": 54.22, + "GSM8K": 1.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "ab373033e98dcdbcc3aadb51374ae392656c6603", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-tora-code-7b-v1.0", + "Average \u2b06\ufe0f": 42.04, + "ARC": 42.66, + "HellaSwag": 65.16, + "MMLU": 38.56, + "TruthfulQA": 42.06, + "Winogrande": 62.9, + "GSM8K": 0.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f7b1f87a096045f1bba8f68c62e062102218717b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mediocredev\/open-llama-3b-v2-instruct", + "Average \u2b06\ufe0f": 42.02, + "ARC": 38.48, + "HellaSwag": 70.24, + "MMLU": 39.69, + "TruthfulQA": 37.96, + "Winogrande": 65.75, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "4d50e134af1d9806cbdf6bc90795b44ae689deca", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/opt-30b", + "Average \u2b06\ufe0f": 42.0, + "ARC": 43.26, + "HellaSwag": 74.07, + "MMLU": 26.66, + "TruthfulQA": 35.16, + "Winogrande": 70.64, + "GSM8K": 2.2, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 133.0, + "Available on the hub": true, + "Model sha": "ceea0a90ac0f6fae7c2c34bcb40477438c152546", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ed001\/datascience-coder-6.7b", + "Average \u2b06\ufe0f": 41.99, + "ARC": 34.64, + "HellaSwag": 53.83, + "MMLU": 37.96, + "TruthfulQA": 44.82, + "Winogrande": 55.72, + "GSM8K": 24.94, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "02c9e23ecc8d0fdcd84db006ecb608344907c5e1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/oasst-gpt-neox-20b-3000-steps", + "Average \u2b06\ufe0f": 41.97, + "ARC": 46.42, + "HellaSwag": 72.08, + "MMLU": 26.16, + "TruthfulQA": 35.53, + "Winogrande": 68.75, + "GSM8K": 2.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f0462a8b7908f61202d86e6a9a2996d8339363b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenAssistant\/pythia-12b-sft-v8-2.5k-steps", + "Average \u2b06\ufe0f": 41.97, + "ARC": 42.32, + "HellaSwag": 70.15, + "MMLU": 27.36, + "TruthfulQA": 36.75, + "Winogrande": 65.67, + "GSM8K": 9.55, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "142e306db8e279a07c557ea5a919ab7e7a4af17c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-gm-oasst1-multilang-1024-20b", + "Average \u2b06\ufe0f": 41.9, + "ARC": 47.44, + "HellaSwag": 72.58, + "MMLU": 26.37, + "TruthfulQA": 34.39, + "Winogrande": 68.43, + "GSM8K": 2.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "b3a6bf4250a037c09e451344e2a4e987011b79de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "wenge-research\/yayi-7b", + "Average \u2b06\ufe0f": 41.88, + "ARC": 46.33, + "HellaSwag": 61.72, + "MMLU": 36.34, + "TruthfulQA": 43.7, + "Winogrande": 62.27, + "GSM8K": 0.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 29.0, + "Available on the hub": false, + "Model sha": "00be6c9e41a8367a855c6f18ebfa08f5ecdb2cc4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/ereb-test", + "Average \u2b06\ufe0f": 41.85, + "ARC": 40.7, + "HellaSwag": 71.04, + "MMLU": 28.06, + "TruthfulQA": 47.4, + "Winogrande": 63.93, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b3fa34df58d0915a76c367c13a025b64bef1345d", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "togethercomputer\/GPT-JT-Moderation-6B", + "Average \u2b06\ufe0f": 41.8, + "ARC": 40.53, + "HellaSwag": 67.66, + "MMLU": 41.63, + "TruthfulQA": 37.33, + "Winogrande": 62.67, + "GSM8K": 0.99, + "Type": "", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": true, + "Model sha": "1297870783f6091294769014afddf94499966a78", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "M4-ai\/NeuralReyna-Mini-1.8B-v0.3", + "Average \u2b06\ufe0f": 41.77, + "ARC": 35.58, + "HellaSwag": 61.13, + "MMLU": 44.22, + "TruthfulQA": 41.99, + "Winogrande": 60.93, + "GSM8K": 6.75, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "38905b74c36b45f23f416d68dc2f755c81524763", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yukang\/LongAlpaca-13B", + "Average \u2b06\ufe0f": 41.74, + "ARC": 42.58, + "HellaSwag": 72.03, + "MMLU": 34.91, + "TruthfulQA": 36.85, + "Winogrande": 64.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": false, + "Model sha": "e80966ae720de9a844441a4a2bbc661106969915", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Danielbrdz\/Barcenas-3b", + "Average \u2b06\ufe0f": 41.74, + "ARC": 43.17, + "HellaSwag": 67.82, + "MMLU": 29.16, + "TruthfulQA": 41.56, + "Winogrande": 66.22, + "GSM8K": 2.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "2b6b8bfd3946c02fa4a5182ed008df8ad324a406", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "AI-Sweden-Models\/gpt-sw3-6.7b-v2-instruct", + "Average \u2b06\ufe0f": 41.72, + "ARC": 40.78, + "HellaSwag": 67.77, + "MMLU": 31.57, + "TruthfulQA": 40.32, + "Winogrande": 63.54, + "GSM8K": 6.37, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "81ca95a4e93746240994d1e6797ffa64dc796bd9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "acrastt\/Marx-3B", + "Average \u2b06\ufe0f": 41.71, + "ARC": 43.17, + "HellaSwag": 72.68, + "MMLU": 28.46, + "TruthfulQA": 39.09, + "Winogrande": 65.59, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "c0dcc44989cf4e006efae31abbcef7e8be8547c0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/gpt-neox-20b", + "Average \u2b06\ufe0f": 41.69, + "ARC": 45.73, + "HellaSwag": 73.45, + "MMLU": 25.0, + "TruthfulQA": 31.61, + "Winogrande": 68.9, + "GSM8K": 5.46, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.74, + "Hub \u2764\ufe0f": 475.0, + "Available on the hub": true, + "Model sha": "9369f145ca7b66ef62760f9351af951b2d53b77f", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "OpenAssistant\/pythia-12b-sft-v8-rlhf-2k-steps", + "Average \u2b06\ufe0f": 41.65, + "ARC": 43.43, + "HellaSwag": 70.08, + "MMLU": 26.12, + "TruthfulQA": 36.06, + "Winogrande": 64.64, + "GSM8K": 9.55, + "Type": "", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a0debfed4a020d449e3d00f4e75f2c2aefb68db3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vihangd\/shearedplats-2.7b-v2", + "Average \u2b06\ufe0f": 41.61, + "ARC": 42.41, + "HellaSwag": 72.58, + "MMLU": 27.52, + "TruthfulQA": 39.76, + "Winogrande": 65.9, + "GSM8K": 1.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "2837296f28d6aa0fb6c1fe382f553e65c8e1e5f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "teilomillet\/MiniMerlin-3b-v0.1", + "Average \u2b06\ufe0f": 41.6, + "ARC": 40.7, + "HellaSwag": 54.06, + "MMLU": 43.32, + "TruthfulQA": 49.65, + "Winogrande": 60.54, + "GSM8K": 1.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2addcbd985f8a7f8bb7a7c21a5ec0e2505e549c6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "glaiveai\/glaive-coder-7b", + "Average \u2b06\ufe0f": 41.56, + "ARC": 42.66, + "HellaSwag": 64.69, + "MMLU": 37.15, + "TruthfulQA": 39.88, + "Winogrande": 59.75, + "GSM8K": 5.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 52.0, + "Available on the hub": true, + "Model sha": "72a255a58480ef0713eed988312fe82f77f94f37", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "togethercomputer\/RedPajama-INCITE-7B-Base", + "Average \u2b06\ufe0f": 41.49, + "ARC": 46.25, + "HellaSwag": 71.63, + "MMLU": 27.68, + "TruthfulQA": 33.03, + "Winogrande": 67.32, + "GSM8K": 3.03, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 92.0, + "Available on the hub": true, + "Model sha": "78f7e482443971f4873ba3239f0ac810a367833b", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "nomic-ai\/gpt4all-j", + "Average \u2b06\ufe0f": 41.49, + "ARC": 41.98, + "HellaSwag": 64.06, + "MMLU": 28.2, + "TruthfulQA": 42.78, + "Winogrande": 64.72, + "GSM8K": 7.2, + "Type": "", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 282.0, + "Available on the hub": true, + "Model sha": "73c15208cb608be2949b7c6e4ba6d88f0176c267", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/oasst-pythia-12b-pretrained-sft", + "Average \u2b06\ufe0f": 41.48, + "ARC": 45.31, + "HellaSwag": 67.67, + "MMLU": 27.81, + "TruthfulQA": 38.16, + "Winogrande": 65.9, + "GSM8K": 4.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c21fbece4253841f2d6e15f04f60fe1ba6f990dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "harborwater\/open-llama-3b-v2-wizard-evol-instuct-v2-196k", + "Average \u2b06\ufe0f": 41.46, + "ARC": 41.81, + "HellaSwag": 73.01, + "MMLU": 26.36, + "TruthfulQA": 38.99, + "Winogrande": 66.69, + "GSM8K": 1.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "4da0c661e6df1235c9997b996c8e395b87248406", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aloobun\/Reyna-Mini-1.8B-v0.1", + "Average \u2b06\ufe0f": 41.46, + "ARC": 35.24, + "HellaSwag": 60.42, + "MMLU": 45.37, + "TruthfulQA": 41.4, + "Winogrande": 60.85, + "GSM8K": 5.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "beb82e3131ebd6a9fea636b0f009adaa19a6f72d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "GeneZC\/MiniMA-3B", + "Average \u2b06\ufe0f": 41.44, + "ARC": 43.43, + "HellaSwag": 68.06, + "MMLU": 28.69, + "TruthfulQA": 39.76, + "Winogrande": 65.98, + "GSM8K": 2.73, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.02, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "0a2f9d6bbb3959d68fe52e07ee6f54e8242f91ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "harborwater\/open-llama-3b-everything-v2", + "Average \u2b06\ufe0f": 41.41, + "ARC": 42.83, + "HellaSwag": 73.28, + "MMLU": 26.87, + "TruthfulQA": 37.26, + "Winogrande": 66.61, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "31ce2c1611d9f7d56184ceb5bff6a7e95a180c03", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Fredithefish\/ReasonixPajama-3B-HF", + "Average \u2b06\ufe0f": 41.41, + "ARC": 39.25, + "HellaSwag": 63.47, + "MMLU": 26.09, + "TruthfulQA": 55.42, + "Winogrande": 63.69, + "GSM8K": 0.53, + "Type": "", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.91, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "fa87c904b5921231b9f6f94b9c537cdda8783b96", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hakurei\/mommygpt-3B", + "Average \u2b06\ufe0f": 41.36, + "ARC": 41.89, + "HellaSwag": 71.69, + "MMLU": 28.74, + "TruthfulQA": 37.9, + "Winogrande": 65.82, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "0369335d693b753774050ae44dbaf73bac39e9eb", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "psmathur\/orca_mini_13b", + "Average \u2b06\ufe0f": 41.36, + "ARC": 42.06, + "HellaSwag": 63.4, + "MMLU": 35.43, + "TruthfulQA": 43.1, + "Winogrande": 64.17, + "GSM8K": 0.0, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ca900c8f3145de40cd188c559b2901a2e4711546", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "NucleusAI\/nucleus-22B-token-500B", + "Average \u2b06\ufe0f": 41.33, + "ARC": 40.7, + "HellaSwag": 69.39, + "MMLU": 30.11, + "TruthfulQA": 39.16, + "Winogrande": 67.64, + "GSM8K": 0.99, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 21.83, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "49bb1a47c0d32b4bfa6630a4eff04a857adcd4ca", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "chargoddard\/llama-2-34b-uncode", + "Average \u2b06\ufe0f": 41.33, + "ARC": 39.51, + "HellaSwag": 33.9, + "MMLU": 38.49, + "TruthfulQA": 40.94, + "Winogrande": 74.35, + "GSM8K": 20.77, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "d434d06249feb6ca511b0a09162130bcc59d84e3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenAssistant\/oasst-sft-4-pythia-12b-epoch-3.5", + "Average \u2b06\ufe0f": 41.31, + "ARC": 45.73, + "HellaSwag": 68.59, + "MMLU": 26.82, + "TruthfulQA": 37.81, + "Winogrande": 65.9, + "GSM8K": 3.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 351.0, + "Available on the hub": true, + "Model sha": "626b8c140cfdedb119dfb78c626cd772283dee33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/orca_mini_7b", + "Average \u2b06\ufe0f": 41.27, + "ARC": 43.94, + "HellaSwag": 65.22, + "MMLU": 29.97, + "TruthfulQA": 42.03, + "Winogrande": 66.06, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6ed0dca683685cb5b9e7df599f87d311f00ba6db", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/GPT-NeoX-20B-Erebus", + "Average \u2b06\ufe0f": 41.26, + "ARC": 45.48, + "HellaSwag": 72.79, + "MMLU": 26.77, + "TruthfulQA": 32.15, + "Winogrande": 68.11, + "GSM8K": 2.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 75.0, + "Available on the hub": true, + "Model sha": "1a80940a290452af71caf17a8e520955eb338e0f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "togethercomputer\/RedPajama-INCITE-Base-7B-v0.1", + "Average \u2b06\ufe0f": 41.25, + "ARC": 46.25, + "HellaSwag": 71.63, + "MMLU": 27.68, + "TruthfulQA": 33.03, + "Winogrande": 67.32, + "GSM8K": 1.59, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.65, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "78f7e482443971f4873ba3239f0ac810a367833b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CobraMamba\/mamba-gpt-3b-v4", + "Average \u2b06\ufe0f": 41.24, + "ARC": 42.58, + "HellaSwag": 71.04, + "MMLU": 30.04, + "TruthfulQA": 37.26, + "Winogrande": 65.82, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "49cdf710c1a9178ddf616da79211fdcdb2170c3f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/sheared-plus-westlake-normal", + "Average \u2b06\ufe0f": 41.16, + "ARC": 39.76, + "HellaSwag": 70.33, + "MMLU": 26.81, + "TruthfulQA": 46.5, + "Winogrande": 63.54, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9965e14e37b22a35877eb210f28dcad60248c22b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aloobun\/open-llama-3b-v2-elmv3", + "Average \u2b06\ufe0f": 41.14, + "ARC": 42.06, + "HellaSwag": 73.28, + "MMLU": 27.61, + "TruthfulQA": 35.54, + "Winogrande": 64.96, + "GSM8K": 3.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7e43b199ff51dc0e63934ba49758a8a31ff855de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "acrastt\/Griffin-3B", + "Average \u2b06\ufe0f": 41.13, + "ARC": 41.81, + "HellaSwag": 72.3, + "MMLU": 26.36, + "TruthfulQA": 38.33, + "Winogrande": 67.01, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "edbea6fe86d0bc2673c10269828008a1cb451919", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mwitiderrick\/shearedplats-2.7b-v2-instruct-v0.1", + "Average \u2b06\ufe0f": 41.13, + "ARC": 40.19, + "HellaSwag": 70.08, + "MMLU": 28.12, + "TruthfulQA": 41.23, + "Winogrande": 65.04, + "GSM8K": 2.12, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "8eb300dc6a62166048f7ec997a0a2d8d9a5708f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aloobun\/open-llama-3b-v2-elmv3", + "Average \u2b06\ufe0f": 41.13, + "ARC": 42.15, + "HellaSwag": 73.26, + "MMLU": 27.16, + "TruthfulQA": 35.51, + "Winogrande": 64.96, + "GSM8K": 3.71, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7e43b199ff51dc0e63934ba49758a8a31ff855de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-coder-ds-6.7b", + "Average \u2b06\ufe0f": 41.11, + "ARC": 36.86, + "HellaSwag": 52.46, + "MMLU": 38.08, + "TruthfulQA": 41.67, + "Winogrande": 58.88, + "GSM8K": 18.73, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "808ce4ef532c91bcbf826cbdc29ec5094cbd1769", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "VMware\/open-llama-0.7T-7B-open-instruct-v1.1", + "Average \u2b06\ufe0f": 41.11, + "ARC": 46.67, + "HellaSwag": 67.67, + "MMLU": 28.55, + "TruthfulQA": 37.6, + "Winogrande": 65.43, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "75741b55ad462330e3498d1506f438f835152177", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CobraMamba\/mamba-gpt-3b-v3", + "Average \u2b06\ufe0f": 41.11, + "ARC": 41.72, + "HellaSwag": 71.05, + "MMLU": 27.31, + "TruthfulQA": 37.86, + "Winogrande": 67.48, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "d860a90ef6b30c695b985dd2ff382d4bbb80e857", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenAssistant\/pythia-12b-pre-v8-12.5k-steps", + "Average \u2b06\ufe0f": 41.1, + "ARC": 41.47, + "HellaSwag": 68.8, + "MMLU": 26.58, + "TruthfulQA": 36.82, + "Winogrande": 65.27, + "GSM8K": 7.66, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "37ca702e957a4b740689d67c58c284224e2fbae2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/GPT-NeoX-20B-Skein", + "Average \u2b06\ufe0f": 41.1, + "ARC": 44.97, + "HellaSwag": 72.68, + "MMLU": 25.99, + "TruthfulQA": 31.64, + "Winogrande": 68.43, + "GSM8K": 2.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 20.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "dd98d514b5aff4e820922c88a73d6d5bf17f332e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "harborwater\/open-llama-3b-v2-wizard-evol-instuct-v2-196k", + "Average \u2b06\ufe0f": 41.09, + "ARC": 41.21, + "HellaSwag": 72.88, + "MMLU": 25.39, + "TruthfulQA": 38.87, + "Winogrande": 66.61, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "4da0c661e6df1235c9997b996c8e395b87248406", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xaviviro\/FLAMA-0.1-3B", + "Average \u2b06\ufe0f": 41.07, + "ARC": 41.72, + "HellaSwag": 71.41, + "MMLU": 26.59, + "TruthfulQA": 37.19, + "Winogrande": 66.54, + "GSM8K": 2.96, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "380f8c1a59a0e60e704b22720af1494801b57e85", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "RobbeD\/OpenLlama-Platypus-3B", + "Average \u2b06\ufe0f": 41.05, + "ARC": 41.21, + "HellaSwag": 71.67, + "MMLU": 29.86, + "TruthfulQA": 36.45, + "Winogrande": 65.98, + "GSM8K": 1.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d3a0bf8e1181be02cc9c4c4cdfedaedacaefbfac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "acrastt\/Puma-3B", + "Average \u2b06\ufe0f": 41.02, + "ARC": 41.3, + "HellaSwag": 71.85, + "MMLU": 27.51, + "TruthfulQA": 38.34, + "Winogrande": 66.38, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1159e9cdd05c03d31331f329ba58e4e3444943be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "harborwater\/wizard-orca-3b", + "Average \u2b06\ufe0f": 41.0, + "ARC": 41.72, + "HellaSwag": 71.78, + "MMLU": 24.49, + "TruthfulQA": 40.04, + "Winogrande": 66.93, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "ffc81b58375342f12e38a67272d95458a72e8d09", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "LLM360\/Amber", + "Average \u2b06\ufe0f": 40.97, + "ARC": 40.96, + "HellaSwag": 73.79, + "MMLU": 26.84, + "TruthfulQA": 33.56, + "Winogrande": 67.88, + "GSM8K": 2.81, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 58.0, + "Available on the hub": true, + "Model sha": "a1fb934dd7bbba8eff8c6052fa469f979803236b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "harborwater\/open-llama-3b-claude-30k", + "Average \u2b06\ufe0f": 40.93, + "ARC": 41.72, + "HellaSwag": 72.64, + "MMLU": 24.03, + "TruthfulQA": 38.46, + "Winogrande": 66.54, + "GSM8K": 2.2, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "049db7fda44e5ce1e8febf5c3f45e3a93aaaa859", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mediocredev\/open-llama-3b-v2-chat", + "Average \u2b06\ufe0f": 40.93, + "ARC": 40.61, + "HellaSwag": 70.3, + "MMLU": 28.73, + "TruthfulQA": 37.84, + "Winogrande": 65.51, + "GSM8K": 2.58, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "0d171b62a41b2d249cd2ff235b66638e3a894c98", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIGym\/deepseek-coder-6.7b-chat-and-function-calling", + "Average \u2b06\ufe0f": 40.91, + "ARC": 36.09, + "HellaSwag": 53.8, + "MMLU": 38.29, + "TruthfulQA": 42.83, + "Winogrande": 57.22, + "GSM8K": 17.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b7a2725d6576fc88278cb41fb5a35ed14cff7077", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIGym\/deepseek-coder-6.7b-chat", + "Average \u2b06\ufe0f": 40.9, + "ARC": 36.01, + "HellaSwag": 53.74, + "MMLU": 38.22, + "TruthfulQA": 42.94, + "Winogrande": 57.54, + "GSM8K": 16.98, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "00f7902c69c8bc48d8289141392d41fcb7517a14", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIGym\/deepseek-coder-6.7b-chat", + "Average \u2b06\ufe0f": 40.9, + "ARC": 35.75, + "HellaSwag": 53.7, + "MMLU": 38.19, + "TruthfulQA": 42.94, + "Winogrande": 58.01, + "GSM8K": 16.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "00f7902c69c8bc48d8289141392d41fcb7517a14", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/MT7Bi-sft", + "Average \u2b06\ufe0f": 40.85, + "ARC": 41.81, + "HellaSwag": 56.83, + "MMLU": 41.4, + "TruthfulQA": 44.61, + "Winogrande": 60.46, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "c1c15fc44948638d938d56d76b3af8b8fd516193", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "princeton-nlp\/Sheared-LLaMA-2.7B", + "Average \u2b06\ufe0f": 40.84, + "ARC": 41.72, + "HellaSwag": 71.01, + "MMLU": 26.92, + "TruthfulQA": 37.32, + "Winogrande": 67.01, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 53.0, + "Available on the hub": true, + "Model sha": "16347024c4df6cd114720958964a850fc287cac0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lvxy1117\/amber_fine_tune_ori", + "Average \u2b06\ufe0f": 40.83, + "ARC": 44.45, + "HellaSwag": 75.1, + "MMLU": 26.04, + "TruthfulQA": 34.94, + "Winogrande": 63.14, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3d98a26f005cdace09b4ddd9c4ea67ba508946ad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/GPT-R", + "Average \u2b06\ufe0f": 40.8, + "ARC": 41.21, + "HellaSwag": 66.89, + "MMLU": 36.5, + "TruthfulQA": 34.22, + "Winogrande": 64.4, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "92b955a3ff74aa577fa0d8517dfc314847ef60af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AtAndDev\/ShortKing-3b-v0.3", + "Average \u2b06\ufe0f": 40.8, + "ARC": 40.96, + "HellaSwag": 70.72, + "MMLU": 26.21, + "TruthfulQA": 38.78, + "Winogrande": 66.93, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4bcf1610eb1f3959568d5acee74833c41502bf04", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "dvruette\/oasst-pythia-12b-6000-steps", + "Average \u2b06\ufe0f": 40.77, + "ARC": 45.39, + "HellaSwag": 69.68, + "MMLU": 25.97, + "TruthfulQA": 39.85, + "Winogrande": 63.22, + "GSM8K": 0.53, + "Type": "", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e2ccc0ef8d1cc5ffc8b0e2e885f03ef50597ea8a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenAssistant\/oasst-sft-1-pythia-12b", + "Average \u2b06\ufe0f": 40.77, + "ARC": 46.42, + "HellaSwag": 70.0, + "MMLU": 26.19, + "TruthfulQA": 39.19, + "Winogrande": 62.19, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 279.0, + "Available on the hub": true, + "Model sha": "293df535fe7711a5726987fc2f17dfc87de452a1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "golaxy\/gogpt-7b-bloom", + "Average \u2b06\ufe0f": 40.75, + "ARC": 44.62, + "HellaSwag": 62.56, + "MMLU": 33.81, + "TruthfulQA": 40.61, + "Winogrande": 62.9, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "8f9996f852db583b982efbd671465d18ad13ffae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hyunseoki\/ko-ref-llama2-7b", + "Average \u2b06\ufe0f": 40.75, + "ARC": 42.66, + "HellaSwag": 66.58, + "MMLU": 30.41, + "TruthfulQA": 38.62, + "Winogrande": 66.22, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "1ee08c79ae7393473754b77e82b1472ef63d5dd2", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "dvruette\/oasst-pythia-12b-flash-attn-5000-steps", + "Average \u2b06\ufe0f": 40.73, + "ARC": 44.97, + "HellaSwag": 69.75, + "MMLU": 26.64, + "TruthfulQA": 38.89, + "Winogrande": 63.14, + "GSM8K": 0.99, + "Type": "", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5227ec9c9def4b0bdf6c7ad95d9f77cbf458283d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "aevalone\/Pengland-Merge", + "Average \u2b06\ufe0f": 40.72, + "ARC": 40.53, + "HellaSwag": 47.06, + "MMLU": 50.72, + "TruthfulQA": 47.03, + "Winogrande": 58.96, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 8.99, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "404bfbd322f0f5168d23a1ba8dff85e46d971db2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AI-Sweden-Models\/gpt-sw3-20b", + "Average \u2b06\ufe0f": 40.71, + "ARC": 41.81, + "HellaSwag": 68.75, + "MMLU": 28.47, + "TruthfulQA": 37.1, + "Winogrande": 67.17, + "GSM8K": 0.99, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 20.92, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "36797b7835a9e656af456e0006465a3af48735fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AlekseyKorshuk\/chatml-pyg-v1", + "Average \u2b06\ufe0f": 40.7, + "ARC": 37.88, + "HellaSwag": 63.29, + "MMLU": 32.77, + "TruthfulQA": 42.61, + "Winogrande": 62.51, + "GSM8K": 5.16, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "79d5a4d53953ca1c26bc2155f168b7e2108f377f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-gm-oasst1-en-1024-12b", + "Average \u2b06\ufe0f": 40.65, + "ARC": 43.09, + "HellaSwag": 69.75, + "MMLU": 25.87, + "TruthfulQA": 38.0, + "Winogrande": 66.14, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "e547fffafb382fd39ef5de35ba3b5afc1b43e74d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/fairseq-dense-13B", + "Average \u2b06\ufe0f": 40.62, + "ARC": 40.36, + "HellaSwag": 75.51, + "MMLU": 27.07, + "TruthfulQA": 32.83, + "Winogrande": 67.96, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": false, + "Model sha": "785793f6b216afd9fc664fc63e8e6c776a016825", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "harborwater\/open-llama-3b-everythingLM-2048", + "Average \u2b06\ufe0f": 40.62, + "ARC": 42.75, + "HellaSwag": 71.72, + "MMLU": 27.16, + "TruthfulQA": 34.26, + "Winogrande": 66.3, + "GSM8K": 1.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "1f9e8d48163feb63ed190eaa982f393542a75d30", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Rallio67\/7B-redpajama-conditional-alpha", + "Average \u2b06\ufe0f": 40.56, + "ARC": 42.58, + "HellaSwag": 69.91, + "MMLU": 26.53, + "TruthfulQA": 36.42, + "Winogrande": 67.17, + "GSM8K": 0.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "9a3f69a1eba3618930f222d4e013d534102a2af5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Javalion-R", + "Average \u2b06\ufe0f": 40.51, + "ARC": 41.72, + "HellaSwag": 68.02, + "MMLU": 30.81, + "TruthfulQA": 34.44, + "Winogrande": 65.43, + "GSM8K": 2.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "b881231ab6ea85da2a9a139f282df85d1d18b002", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-oasst1-512-12b", + "Average \u2b06\ufe0f": 40.48, + "ARC": 42.32, + "HellaSwag": 70.24, + "MMLU": 26.01, + "TruthfulQA": 36.41, + "Winogrande": 66.22, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": true, + "Model sha": "c6bb0fe363e0105839d34ca757793b61c9606f95", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "freecs\/ThetaWave-28B-v0.1", + "Average \u2b06\ufe0f": 40.4, + "ARC": 36.6, + "HellaSwag": 35.54, + "MMLU": 54.5, + "TruthfulQA": 49.86, + "Winogrande": 65.9, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 28.18, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9efeb3784333a072be4db0b6e413e319327d89e5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Javelin-R", + "Average \u2b06\ufe0f": 40.39, + "ARC": 41.64, + "HellaSwag": 69.01, + "MMLU": 30.7, + "TruthfulQA": 34.5, + "Winogrande": 64.8, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4c4a5caf5d9049a47f5565b72e5a53dede08ac8b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_opt13b_10e5", + "Average \u2b06\ufe0f": 40.37, + "ARC": 42.49, + "HellaSwag": 70.31, + "MMLU": 25.45, + "TruthfulQA": 35.78, + "Winogrande": 66.85, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "08451d85cf04c9f626ad3f8f44508602d877a873", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "dvruette\/oasst-pythia-12b-reference", + "Average \u2b06\ufe0f": 40.33, + "ARC": 43.0, + "HellaSwag": 67.91, + "MMLU": 28.33, + "TruthfulQA": 36.57, + "Winogrande": 64.96, + "GSM8K": 1.21, + "Type": "", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c5a9b7fad884e6c45ce5d2ca551aa1c03db6865f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WizardLM\/WizardCoder-Python-7B-V1.0", + "Average \u2b06\ufe0f": 40.32, + "ARC": 41.81, + "HellaSwag": 65.06, + "MMLU": 32.29, + "TruthfulQA": 36.32, + "Winogrande": 61.72, + "GSM8K": 4.7, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 68.0, + "Available on the hub": true, + "Model sha": "e40673a27a4aefcff2c6d2b3b1e0681a38703e4e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Pirr\/pythia-13b-deduped-green_devil", + "Average \u2b06\ufe0f": 40.31, + "ARC": 42.32, + "HellaSwag": 68.89, + "MMLU": 26.01, + "TruthfulQA": 35.56, + "Winogrande": 66.93, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": false, + "Model sha": "7faeb395c26189eeab9bf3a98994696687ad31a3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vihangd\/smartyplats-3b-v2", + "Average \u2b06\ufe0f": 40.29, + "ARC": 41.04, + "HellaSwag": 71.19, + "MMLU": 24.32, + "TruthfulQA": 36.66, + "Winogrande": 66.93, + "GSM8K": 1.59, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "920609897049f674bc4a9678579f6869f6cbed13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/openllama_3b_EvolInstruct_lora_merged", + "Average \u2b06\ufe0f": 40.28, + "ARC": 40.27, + "HellaSwag": 71.6, + "MMLU": 27.12, + "TruthfulQA": 34.78, + "Winogrande": 67.01, + "GSM8K": 0.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c55e3e114951346f273c519d266170e4d52781e9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "openlm-research\/open_llama_3b_v2", + "Average \u2b06\ufe0f": 40.28, + "ARC": 40.27, + "HellaSwag": 71.6, + "MMLU": 27.12, + "TruthfulQA": 34.78, + "Winogrande": 67.01, + "GSM8K": 0.91, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 113.0, + "Available on the hub": true, + "Model sha": "bce5d60d3b0c68318862270ec4e794d83308d80a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kfkas\/Llama-2-ko-7b-Chat", + "Average \u2b06\ufe0f": 40.27, + "ARC": 40.44, + "HellaSwag": 67.16, + "MMLU": 30.4, + "TruthfulQA": 35.48, + "Winogrande": 66.85, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 65.0, + "Available on the hub": false, + "Model sha": "3293b98cd8204371988f898dafa9b5a297555cbe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TheBloke\/CodeLlama-34B-Python-fp16", + "Average \u2b06\ufe0f": 40.27, + "ARC": 38.14, + "HellaSwag": 34.8, + "MMLU": 32.95, + "TruthfulQA": 43.57, + "Winogrande": 72.14, + "GSM8K": 20.02, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "875f9d97fb6c9619d8867887dd1d80918ff0f593", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "codellama\/CodeLlama-34b-Python-hf", + "Average \u2b06\ufe0f": 40.27, + "ARC": 40.19, + "HellaSwag": 36.82, + "MMLU": 34.79, + "TruthfulQA": 44.28, + "Winogrande": 71.19, + "GSM8K": 14.33, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 33.74, + "Hub \u2764\ufe0f": 91.0, + "Available on the hub": true, + "Model sha": "3dd8ab05bbd273b9f77088b1d4015b7f1848793d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "l3utterfly\/open-llama-3b-v2-layla", + "Average \u2b06\ufe0f": 40.25, + "ARC": 38.23, + "HellaSwag": 66.43, + "MMLU": 28.56, + "TruthfulQA": 44.4, + "Winogrande": 62.83, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "465669ddafad25393ac3cfe94d3726cced112b30", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kfkas\/Llama-2-ko-7b-Chat", + "Average \u2b06\ufe0f": 40.25, + "ARC": 40.44, + "HellaSwag": 67.12, + "MMLU": 30.19, + "TruthfulQA": 35.45, + "Winogrande": 66.61, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 65.0, + "Available on the hub": false, + "Model sha": "3293b98cd8204371988f898dafa9b5a297555cbe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Javelin-GPTJ", + "Average \u2b06\ufe0f": 40.23, + "ARC": 42.66, + "HellaSwag": 70.45, + "MMLU": 26.2, + "TruthfulQA": 36.08, + "Winogrande": 64.17, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "bee7068ab002784420a1a30170db3906185359f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "llm-agents\/tora-code-7b-v1.0", + "Average \u2b06\ufe0f": 40.21, + "ARC": 40.7, + "HellaSwag": 65.86, + "MMLU": 33.34, + "TruthfulQA": 34.84, + "Winogrande": 61.56, + "GSM8K": 4.93, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "777501b69bb0ba2675abdcaf7b1309ab05320c2e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Janin-R", + "Average \u2b06\ufe0f": 40.19, + "ARC": 40.44, + "HellaSwag": 67.36, + "MMLU": 31.24, + "TruthfulQA": 34.49, + "Winogrande": 65.35, + "GSM8K": 2.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f6963f77098d8421ff4a1cf4d36f1e94c6c8f44b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "acrastt\/Bean-3B", + "Average \u2b06\ufe0f": 40.18, + "ARC": 40.36, + "HellaSwag": 72.0, + "MMLU": 26.43, + "TruthfulQA": 36.11, + "Winogrande": 65.67, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4a1ce189a3fb1d58b3fa47ebe30b3c037592670c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TaylorAI\/Flash-Llama-3B", + "Average \u2b06\ufe0f": 40.13, + "ARC": 40.1, + "HellaSwag": 71.56, + "MMLU": 26.88, + "TruthfulQA": 34.74, + "Winogrande": 66.61, + "GSM8K": 0.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "b4c7bb49171ff6955cfc1f7e33143383c57f7606", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/Dolly_Shygmalion-6b-Dev_V8P2", + "Average \u2b06\ufe0f": 40.11, + "ARC": 41.38, + "HellaSwag": 67.67, + "MMLU": 28.48, + "TruthfulQA": 36.86, + "Winogrande": 64.33, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "6413b1d9e8b58df9d3aac91a862e8d505d8c6716", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/gpt-j-6b", + "Average \u2b06\ufe0f": 40.1, + "ARC": 41.38, + "HellaSwag": 67.54, + "MMLU": 26.78, + "TruthfulQA": 35.96, + "Winogrande": 65.98, + "GSM8K": 2.96, + "Type": "pretrained", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 1348.0, + "Available on the hub": true, + "Model sha": "47e169305d2e8376be1d31e765533382721b2cc1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Xilabs\/calypso-3b-alpha-v2", + "Average \u2b06\ufe0f": 40.09, + "ARC": 41.55, + "HellaSwag": 71.48, + "MMLU": 25.82, + "TruthfulQA": 35.73, + "Winogrande": 65.27, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "933fb9db10f131f7ea54f4e6024ed2acf41c711a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Danielbrdz\/CodeBarcenas-7b", + "Average \u2b06\ufe0f": 40.09, + "ARC": 42.32, + "HellaSwag": 63.43, + "MMLU": 33.39, + "TruthfulQA": 38.51, + "Winogrande": 60.38, + "GSM8K": 2.5, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fe7a232baac5394e821f349cb7ef31dbd4ca2078", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/CodeLlama-34b-hf", + "Average \u2b06\ufe0f": 40.08, + "ARC": 37.54, + "HellaSwag": 31.84, + "MMLU": 37.2, + "TruthfulQA": 38.89, + "Winogrande": 73.4, + "GSM8K": 21.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "4e61ec70eb258047f5bc689fa6a66f7753da52b8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/opt-13b", + "Average \u2b06\ufe0f": 40.06, + "ARC": 39.93, + "HellaSwag": 71.2, + "MMLU": 24.9, + "TruthfulQA": 34.1, + "Winogrande": 68.51, + "GSM8K": 1.74, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 62.0, + "Available on the hub": true, + "Model sha": "e515202d1e7750da62d245fbccb2723b9c1790f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "codellama\/CodeLlama-7b-Instruct-hf", + "Average \u2b06\ufe0f": 40.05, + "ARC": 36.52, + "HellaSwag": 55.44, + "MMLU": 34.54, + "TruthfulQA": 41.25, + "Winogrande": 64.56, + "GSM8K": 7.96, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 162.0, + "Available on the hub": true, + "Model sha": "7affc442e639b8aa1c4b3e98a10a2f45a21b8b4f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vihangd\/DopeyTinyLlama-1.1B-v1", + "Average \u2b06\ufe0f": 40.04, + "ARC": 38.4, + "HellaSwag": 63.49, + "MMLU": 25.76, + "TruthfulQA": 37.36, + "Winogrande": 73.4, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "34b3b15e9c37be1a89745f06904c1e89ef98d417", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/GPT-J-6B-Skein", + "Average \u2b06\ufe0f": 40.02, + "ARC": 42.58, + "HellaSwag": 68.69, + "MMLU": 24.88, + "TruthfulQA": 38.7, + "Winogrande": 63.85, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": false, + "Model sha": "acfe27303f74129930fef5e6fadbc5f58c6b8590", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vihangd\/smartyplats-3b-v1", + "Average \u2b06\ufe0f": 40.0, + "ARC": 40.53, + "HellaSwag": 70.85, + "MMLU": 25.31, + "TruthfulQA": 36.53, + "Winogrande": 65.75, + "GSM8K": 1.06, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "89272b9edb323f5ace09e097a6449554c0dcd4e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-tools-7b", + "Average \u2b06\ufe0f": 40.0, + "ARC": 38.91, + "HellaSwag": 57.69, + "MMLU": 33.24, + "TruthfulQA": 44.08, + "Winogrande": 58.56, + "GSM8K": 7.51, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "81aefc8983d1192378c2c803f0e0d14d48561117", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Salesforce\/codegen-6B-nl", + "Average \u2b06\ufe0f": 40.0, + "ARC": 42.32, + "HellaSwag": 68.59, + "MMLU": 25.93, + "TruthfulQA": 34.47, + "Winogrande": 66.46, + "GSM8K": 2.2, + "Type": "pretrained", + "Architecture": "CodeGenForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bsd-3-clause", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "dff91c0aea702edbea3528344d01d8b9aaee6e39", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "KnutJaegersberg\/Nanbeige-16B-Base-32K-llama", + "Average \u2b06\ufe0f": 39.99, + "ARC": 47.61, + "HellaSwag": 73.08, + "MMLU": 45.26, + "TruthfulQA": 0.0, + "Winogrande": 72.93, + "GSM8K": 1.06, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 15.83, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "50f59482965671226cfa7f9c107ab8904f1677cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Javalion-GPTJ", + "Average \u2b06\ufe0f": 39.97, + "ARC": 41.89, + "HellaSwag": 68.69, + "MMLU": 26.85, + "TruthfulQA": 35.44, + "Winogrande": 65.27, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3ce176bc0f91cae416c78e99f964f54b12472de0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/WizardVicuna-Uncensored-3B-instruct-PL-lora_unload", + "Average \u2b06\ufe0f": 39.95, + "ARC": 41.98, + "HellaSwag": 66.82, + "MMLU": 25.69, + "TruthfulQA": 39.67, + "Winogrande": 64.88, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "e471ec778771f29992293d1660cc108f29c9c69e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Kquant03\/Raiden-16x3.43B", + "Average \u2b06\ufe0f": 39.93, + "ARC": 41.89, + "HellaSwag": 66.2, + "MMLU": 26.24, + "TruthfulQA": 39.18, + "Winogrande": 63.61, + "GSM8K": 2.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 35.78, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5403751a298b27603b25c28b1b003cf5f8dbe186", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "RWKV\/rwkv-4-14b-pile", + "Average \u2b06\ufe0f": 39.92, + "ARC": 44.45, + "HellaSwag": 71.07, + "MMLU": 26.12, + "TruthfulQA": 32.04, + "Winogrande": 65.43, + "GSM8K": 0.38, + "Type": "pretrained", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 14.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "4effb0fa9d15c2f383a1d159f4a40df0e09eb6d5", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/WizardLM-30B-GPTQ", + "Average \u2b06\ufe0f": 39.9, + "ARC": 28.84, + "HellaSwag": 26.08, + "MMLU": 24.62, + "TruthfulQA": 49.14, + "Winogrande": 76.32, + "GSM8K": 34.42, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 35.58, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "e2e97475a9775d2fe7afba098aee37e694b9220f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-gm-oasst1-en-1024-open-llama-7b-preview-400bt", + "Average \u2b06\ufe0f": 39.89, + "ARC": 41.3, + "HellaSwag": 62.44, + "MMLU": 27.55, + "TruthfulQA": 42.0, + "Winogrande": 64.56, + "GSM8K": 1.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "29604e6e19822531b0d49d3f19abef603a97d0ec", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/Dolly_Shygmalion-6b", + "Average \u2b06\ufe0f": 39.89, + "ARC": 41.89, + "HellaSwag": 68.48, + "MMLU": 27.58, + "TruthfulQA": 33.91, + "Winogrande": 65.35, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": false, + "Model sha": "108fabf8a916900525492c294c50998d7c09f10b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Skegma-GPTJ", + "Average \u2b06\ufe0f": 39.87, + "ARC": 43.77, + "HellaSwag": 69.22, + "MMLU": 25.37, + "TruthfulQA": 34.67, + "Winogrande": 64.64, + "GSM8K": 1.52, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4dff006b2ea7e8d9b067dfe8af8ca1a16bc44dce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/PPO_Shygmalion-V8p4_Dev-6b", + "Average \u2b06\ufe0f": 39.85, + "ARC": 40.7, + "HellaSwag": 67.04, + "MMLU": 29.31, + "TruthfulQA": 35.57, + "Winogrande": 63.93, + "GSM8K": 2.58, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "fa3d503bca50c947e7a5bbde4bdd82f699f65c02", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/PPO_Pygway-V8p4_Dev-6b", + "Average \u2b06\ufe0f": 39.85, + "ARC": 40.36, + "HellaSwag": 67.15, + "MMLU": 29.3, + "TruthfulQA": 35.26, + "Winogrande": 64.4, + "GSM8K": 2.65, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "f30709dba36c665869f9ac8cd0cef5a8a2e7c8df", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/Pythia-Chat-Base-7B", + "Average \u2b06\ufe0f": 39.81, + "ARC": 40.02, + "HellaSwag": 68.67, + "MMLU": 27.44, + "TruthfulQA": 34.63, + "Winogrande": 64.01, + "GSM8K": 4.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 63.0, + "Available on the hub": true, + "Model sha": "97aa918c383820e1a69f042801091d7deb996c20", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NousResearch\/CodeLlama-7b-hf", + "Average \u2b06\ufe0f": 39.81, + "ARC": 39.85, + "HellaSwag": 59.58, + "MMLU": 30.47, + "TruthfulQA": 38.62, + "Winogrande": 64.88, + "GSM8K": 5.46, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "855c92912ea4a8eb5f0be1db4bf776ffd0815dac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "codellama\/CodeLlama-7b-hf", + "Average \u2b06\ufe0f": 39.81, + "ARC": 39.93, + "HellaSwag": 60.8, + "MMLU": 31.12, + "TruthfulQA": 37.82, + "Winogrande": 64.01, + "GSM8K": 5.16, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 255.0, + "Available on the hub": true, + "Model sha": "be52f4ad322f5a47da121c761aeb5ba20ed77b17", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhinand\/telugu-llama-7b-instruct-v0.1", + "Average \u2b06\ufe0f": 39.77, + "ARC": 37.12, + "HellaSwag": 67.92, + "MMLU": 23.12, + "TruthfulQA": 49.05, + "Winogrande": 61.4, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "5bd17c1a901cd080b0abf11a25ff9f516ad73fa1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/Dolly_Malion-6b", + "Average \u2b06\ufe0f": 39.77, + "ARC": 42.83, + "HellaSwag": 68.43, + "MMLU": 27.13, + "TruthfulQA": 33.03, + "Winogrande": 65.43, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "f239eb8d24fe26db3b0a9a69115dc305fc9351af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mwitiderrick\/open_llama_3b_glaive_code_v0.1", + "Average \u2b06\ufe0f": 39.74, + "ARC": 40.7, + "HellaSwag": 67.45, + "MMLU": 27.74, + "TruthfulQA": 35.86, + "Winogrande": 64.72, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "efa950c69b6cbe1f8629400f3a7e0ccd895551fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mwitiderrick\/open_llama_3b_glaive_v0.1", + "Average \u2b06\ufe0f": 39.74, + "ARC": 40.7, + "HellaSwag": 67.45, + "MMLU": 27.74, + "TruthfulQA": 35.86, + "Winogrande": 64.72, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "efa950c69b6cbe1f8629400f3a7e0ccd895551fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mwitiderrick\/open_llama_3b_glaive_assistant_v0.1", + "Average \u2b06\ufe0f": 39.74, + "ARC": 40.7, + "HellaSwag": 67.45, + "MMLU": 27.74, + "TruthfulQA": 35.86, + "Winogrande": 64.72, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "efa950c69b6cbe1f8629400f3a7e0ccd895551fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "heegyu\/WizardVicuna-Uncensored-3B-0719", + "Average \u2b06\ufe0f": 39.73, + "ARC": 41.38, + "HellaSwag": 66.19, + "MMLU": 26.53, + "TruthfulQA": 39.35, + "Winogrande": 63.77, + "GSM8K": 1.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "36841c80535bc3e8403e3cc084e8e65884c75076", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/ChanMalion", + "Average \u2b06\ufe0f": 39.73, + "ARC": 41.89, + "HellaSwag": 68.25, + "MMLU": 27.29, + "TruthfulQA": 33.89, + "Winogrande": 65.35, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": false, + "Model sha": "2667b0e0b705ed23f81f3e2b69673d722e8f4964", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mwitiderrick\/open_llama_3b_code_instruct_0.1", + "Average \u2b06\ufe0f": 39.72, + "ARC": 41.21, + "HellaSwag": 66.96, + "MMLU": 27.82, + "TruthfulQA": 35.01, + "Winogrande": 65.43, + "GSM8K": 1.9, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "be8055f68a5d53321d98c2b3e0f153034303b96c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abhinand\/telugu-llama-7b-instruct-v0.1", + "Average \u2b06\ufe0f": 39.71, + "ARC": 36.95, + "HellaSwag": 67.88, + "MMLU": 23.12, + "TruthfulQA": 48.97, + "Winogrande": 61.33, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "5bd17c1a901cd080b0abf11a25ff9f516ad73fa1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-12b-deduped", + "Average \u2b06\ufe0f": 39.7, + "ARC": 41.38, + "HellaSwag": 70.26, + "MMLU": 25.63, + "TruthfulQA": 33.0, + "Winogrande": 66.46, + "GSM8K": 1.44, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 50.0, + "Available on the hub": true, + "Model sha": "39c1bd94f9dbe4ebd1d191f364cb33a2e5c47707", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhinand\/malayalam-llama-7b-instruct-v0.1", + "Average \u2b06\ufe0f": 39.69, + "ARC": 37.2, + "HellaSwag": 67.81, + "MMLU": 23.12, + "TruthfulQA": 47.11, + "Winogrande": 62.9, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "f4a9d167819eaffcfafffc3e52530d0af04efdf4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Janin-GPTJ", + "Average \u2b06\ufe0f": 39.67, + "ARC": 40.87, + "HellaSwag": 67.29, + "MMLU": 27.4, + "TruthfulQA": 36.25, + "Winogrande": 64.25, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a6773861798f2abea3849514aa6f60961518af9c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/GPT-J-Pyg_PPO-6B-Dev-V8p4", + "Average \u2b06\ufe0f": 39.61, + "ARC": 40.19, + "HellaSwag": 66.43, + "MMLU": 30.39, + "TruthfulQA": 34.76, + "Winogrande": 64.01, + "GSM8K": 1.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "930dc82245c607ce43558a0e6c0225e77b341ea6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-13B-Erebus", + "Average \u2b06\ufe0f": 39.61, + "ARC": 40.02, + "HellaSwag": 70.07, + "MMLU": 25.32, + "TruthfulQA": 34.93, + "Winogrande": 66.54, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 192.0, + "Available on the hub": true, + "Model sha": "8a949353677d2b971910a6c4afcc70e95d838c2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-13B-Nerybus-Mix", + "Average \u2b06\ufe0f": 39.61, + "ARC": 39.85, + "HellaSwag": 70.6, + "MMLU": 24.9, + "TruthfulQA": 34.02, + "Winogrande": 67.88, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 31.0, + "Available on the hub": true, + "Model sha": "c27a7e2360dd313406719980851e89abf46ebb13", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/GPT-J-6B-Shinen", + "Average \u2b06\ufe0f": 39.6, + "ARC": 39.85, + "HellaSwag": 67.06, + "MMLU": 27.72, + "TruthfulQA": 36.94, + "Winogrande": 64.09, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "afa5a11b24cb23eee708e17c83b920a788e9e07b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Corianas\/gpt-j-6B-Dolly", + "Average \u2b06\ufe0f": 39.6, + "ARC": 41.3, + "HellaSwag": 65.97, + "MMLU": 26.78, + "TruthfulQA": 37.91, + "Winogrande": 64.72, + "GSM8K": 0.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "83d8c754aac12f838d7c847d4352a09396c383d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/GPT-J-Pyg_PPO-6B", + "Average \u2b06\ufe0f": 39.6, + "ARC": 42.06, + "HellaSwag": 67.51, + "MMLU": 28.52, + "TruthfulQA": 31.95, + "Winogrande": 64.72, + "GSM8K": 2.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "cde5bab3ae16e1704c5fec54a6a7ff1169c935e6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-nl2sql-ds-6.7b", + "Average \u2b06\ufe0f": 39.59, + "ARC": 36.35, + "HellaSwag": 52.83, + "MMLU": 36.8, + "TruthfulQA": 40.55, + "Winogrande": 55.96, + "GSM8K": 15.09, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e55ace80c04ed4ace1876ba192e6ecb4ef0353b8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/GPT-J-6B-Janeway", + "Average \u2b06\ufe0f": 39.54, + "ARC": 40.87, + "HellaSwag": 67.11, + "MMLU": 27.45, + "TruthfulQA": 35.74, + "Winogrande": 64.72, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "036bb03496d648ddc8cf932ad91df8ef1287116c", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "amazon\/LightGPT", + "Average \u2b06\ufe0f": 39.54, + "ARC": 39.93, + "HellaSwag": 63.82, + "MMLU": 28.45, + "TruthfulQA": 36.69, + "Winogrande": 64.48, + "GSM8K": 3.87, + "Type": "", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 72.0, + "Available on the hub": true, + "Model sha": "1f6ffd8f162030396a3bc1ca2e3504896dbe6434", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-13B-Nerys-v2", + "Average \u2b06\ufe0f": 39.53, + "ARC": 39.68, + "HellaSwag": 70.53, + "MMLU": 25.36, + "TruthfulQA": 33.5, + "Winogrande": 67.88, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "b0aa4f3630356f7801ca083c00b03d03da13b8bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/RedPajama-INCITE-Chat-3B-v1", + "Average \u2b06\ufe0f": 39.53, + "ARC": 42.83, + "HellaSwag": 67.62, + "MMLU": 26.23, + "TruthfulQA": 34.44, + "Winogrande": 65.51, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 132.0, + "Available on the hub": true, + "Model sha": "f0e0995eba801096ed04cb87931d96a8316871af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "abhinand\/malayalam-llama-7b-instruct-v0.1", + "Average \u2b06\ufe0f": 39.51, + "ARC": 37.03, + "HellaSwag": 67.75, + "MMLU": 23.12, + "TruthfulQA": 47.05, + "Winogrande": 62.12, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "f4a9d167819eaffcfafffc3e52530d0af04efdf4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AI-Sweden-Models\/gpt-sw3-6.7b-v2", + "Average \u2b06\ufe0f": 39.49, + "ARC": 39.42, + "HellaSwag": 66.39, + "MMLU": 30.09, + "TruthfulQA": 35.6, + "Winogrande": 64.25, + "GSM8K": 1.21, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7a7f93d4318658b354c5411cde64e9f0121f6b1f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "heegyu\/WizardVicuna-3B-0719", + "Average \u2b06\ufe0f": 39.48, + "ARC": 40.7, + "HellaSwag": 65.45, + "MMLU": 25.44, + "TruthfulQA": 40.71, + "Winogrande": 63.85, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "62d3d450b8ab2bd2fb9f82383b55d1ecae33a401", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "databricks\/dolly-v2-12b", + "Average \u2b06\ufe0f": 39.46, + "ARC": 42.41, + "HellaSwag": 72.53, + "MMLU": 25.92, + "TruthfulQA": 33.83, + "Winogrande": 60.85, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 1922.0, + "Available on the hub": true, + "Model sha": "19308160448536e378e3db21a73a751579ee7fdd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/llama2-ppo", + "Average \u2b06\ufe0f": 39.44, + "ARC": 41.64, + "HellaSwag": 49.46, + "MMLU": 35.36, + "TruthfulQA": 45.08, + "Winogrande": 64.96, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8619e9870ce3285bf9c2a74921b5947dd6f9e4ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/PPO_Pygway-6b-Mix", + "Average \u2b06\ufe0f": 39.43, + "ARC": 41.81, + "HellaSwag": 67.77, + "MMLU": 28.42, + "TruthfulQA": 32.5, + "Winogrande": 64.4, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "b31d25819e00d5031ccdb22a9584f0850dcfe39c", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "harborwater\/dpo-test-hermes-open-llama-3b", + "Average \u2b06\ufe0f": 39.42, + "ARC": 39.25, + "HellaSwag": 67.46, + "MMLU": 24.21, + "TruthfulQA": 39.81, + "Winogrande": 64.4, + "GSM8K": 1.36, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5cd560152a364f61f92cebe18feaefc181dfd287", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Fredithefish\/RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4", + "Average \u2b06\ufe0f": 39.38, + "ARC": 41.64, + "HellaSwag": 66.23, + "MMLU": 27.26, + "TruthfulQA": 36.1, + "Winogrande": 64.4, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc", + "#Params (B)": 2.91, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c588a5924749b86a6cb36a687dafa544c189bb6f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/RedPajama-INCITE-7B-Chat", + "Average \u2b06\ufe0f": 39.37, + "ARC": 42.06, + "HellaSwag": 70.82, + "MMLU": 26.94, + "TruthfulQA": 36.09, + "Winogrande": 59.83, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 91.0, + "Available on the hub": true, + "Model sha": "47b94a739e2f3164b438501c8684acc5d5acc146", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/RedPajama-INCITE-Chat-7B-v0.1", + "Average \u2b06\ufe0f": 39.37, + "ARC": 42.06, + "HellaSwag": 70.82, + "MMLU": 26.94, + "TruthfulQA": 36.09, + "Winogrande": 59.83, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.65, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "47b94a739e2f3164b438501c8684acc5d5acc146", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yukang\/LongAlpaca-7B", + "Average \u2b06\ufe0f": 39.36, + "ARC": 42.66, + "HellaSwag": 65.89, + "MMLU": 27.28, + "TruthfulQA": 40.16, + "Winogrande": 60.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": false, + "Model sha": "bebfcb894b3f5170ce54e3bb98b6e565fae7b6c0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/PPO_Shygmalion-6b", + "Average \u2b06\ufe0f": 39.35, + "ARC": 40.27, + "HellaSwag": 66.88, + "MMLU": 27.53, + "TruthfulQA": 34.24, + "Winogrande": 65.35, + "GSM8K": 1.82, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": false, + "Model sha": "573e4546fdccc5c8a52b9d7cb23a2e10f0f2ef51", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "digitous\/Adventien-GPTJ", + "Average \u2b06\ufe0f": 39.31, + "ARC": 42.49, + "HellaSwag": 69.21, + "MMLU": 25.4, + "TruthfulQA": 36.95, + "Winogrande": 60.22, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4fbfe9eae03a1d6ecf60fda8cf39c4123f0438bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mosaicml\/mpt-7b-storywriter", + "Average \u2b06\ufe0f": 39.31, + "ARC": 45.65, + "HellaSwag": 74.14, + "MMLU": 28.8, + "TruthfulQA": 36.12, + "Winogrande": 51.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 760.0, + "Available on the hub": false, + "Model sha": "a5e85ae1941e31bb705adbcafce9b0dfd6f3a48b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-6.9b-deduped", + "Average \u2b06\ufe0f": 39.3, + "ARC": 41.3, + "HellaSwag": 67.05, + "MMLU": 26.48, + "TruthfulQA": 35.19, + "Winogrande": 64.09, + "GSM8K": 1.67, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.9, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "372b1c08d9b5b0fc18ce86bbf294930e26e66ed5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/fairseq-dense-6.7B", + "Average \u2b06\ufe0f": 39.26, + "ARC": 39.42, + "HellaSwag": 71.26, + "MMLU": 26.91, + "TruthfulQA": 32.73, + "Winogrande": 65.27, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "d62d83b8eb7a6ba012a762752a5b5679add3b40c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "L-R\/LLmRA-3B-v0.1", + "Average \u2b06\ufe0f": 39.25, + "ARC": 39.42, + "HellaSwag": 59.79, + "MMLU": 25.16, + "TruthfulQA": 50.62, + "Winogrande": 59.43, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7d8a4ccf707de28e924653ba719a18caf8c1db05", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "databricks\/dolly-v2-7b", + "Average \u2b06\ufe0f": 39.24, + "ARC": 44.54, + "HellaSwag": 69.64, + "MMLU": 25.18, + "TruthfulQA": 34.88, + "Winogrande": 60.06, + "GSM8K": 1.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 141.0, + "Available on the hub": true, + "Model sha": "d632f0c8b75b1ae5b26b250d25bfba4e99cb7c6f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xaviviro\/FLAMA-0.5-3B", + "Average \u2b06\ufe0f": 39.23, + "ARC": 37.97, + "HellaSwag": 67.65, + "MMLU": 25.73, + "TruthfulQA": 41.11, + "Winogrande": 62.12, + "GSM8K": 0.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eeec9ee7d50953a27189ac64ee63c93a272d1a12", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "acrastt\/RedPajama-INCITE-Chat-Instruct-3B-V1", + "Average \u2b06\ufe0f": 39.23, + "ARC": 42.58, + "HellaSwag": 67.48, + "MMLU": 25.99, + "TruthfulQA": 33.62, + "Winogrande": 64.8, + "GSM8K": 0.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e19eef572d57fc734bf3ea07c7d0098b3901ec9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "heegyu\/RedTulu-Uncensored-3B-0719", + "Average \u2b06\ufe0f": 39.19, + "ARC": 40.02, + "HellaSwag": 62.55, + "MMLU": 30.37, + "TruthfulQA": 37.59, + "Winogrande": 62.35, + "GSM8K": 2.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c92bf022cddc3f57b4552ec3391df487295a2f87", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigscience\/bloom-7b1", + "Average \u2b06\ufe0f": 39.18, + "ARC": 41.13, + "HellaSwag": 62.0, + "MMLU": 26.25, + "TruthfulQA": 38.9, + "Winogrande": 65.43, + "GSM8K": 1.36, + "Type": "pretrained", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 7.07, + "Hub \u2764\ufe0f": 170.0, + "Available on the hub": true, + "Model sha": "e83e90ba86f87f74aa2731cdab25ccf33976bd66", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DanielSc4\/RedPajama-INCITE-Chat-3B-v1-RL-LoRA-8bit-test1", + "Average \u2b06\ufe0f": 39.16, + "ARC": 41.3, + "HellaSwag": 66.82, + "MMLU": 26.1, + "TruthfulQA": 35.04, + "Winogrande": 65.43, + "GSM8K": 0.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "8bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a2ee88a9fa1c9ad41e0a8c15217a4b1230ec33c8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dvruette\/oasst-pythia-6.9b-4000-steps", + "Average \u2b06\ufe0f": 39.15, + "ARC": 41.64, + "HellaSwag": 64.24, + "MMLU": 26.26, + "TruthfulQA": 40.43, + "Winogrande": 61.8, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.9, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0e201b6f344ac6382dda40d389e1c9144a87d027", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "matsuo-lab\/weblab-10b-instruction-sft", + "Average \u2b06\ufe0f": 39.13, + "ARC": 40.1, + "HellaSwag": 65.3, + "MMLU": 26.66, + "TruthfulQA": 36.79, + "Winogrande": 64.09, + "GSM8K": 1.82, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.0, + "Hub \u2764\ufe0f": 70.0, + "Available on the hub": true, + "Model sha": "112a5ad9f556078ab14a5cd93511b9db4a0d4413", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "h2oai\/h2o-danube-1.8b-base", + "Average \u2b06\ufe0f": 39.12, + "ARC": 39.42, + "HellaSwag": 69.58, + "MMLU": 25.94, + "TruthfulQA": 33.86, + "Winogrande": 64.48, + "GSM8K": 1.44, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.83, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "3201996d3a41b4a485582164db42ca58d51051aa", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/robin-33B-v2-GPTQ", + "Average \u2b06\ufe0f": 39.1, + "ARC": 27.73, + "HellaSwag": 26.29, + "MMLU": 23.53, + "TruthfulQA": 49.54, + "Winogrande": 79.79, + "GSM8K": 27.75, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 35.58, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "4c2588d65302e9ca634548ed81e8650fb2975686", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-6.7B-Erebus", + "Average \u2b06\ufe0f": 39.09, + "ARC": 39.16, + "HellaSwag": 68.66, + "MMLU": 24.58, + "TruthfulQA": 35.12, + "Winogrande": 65.98, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 86.0, + "Available on the hub": true, + "Model sha": "9c4d1af96f93224e01d2f69c303fc6d6f686bdcc", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "YeungNLP\/firefly-bloom-7b1", + "Average \u2b06\ufe0f": 39.09, + "ARC": 40.44, + "HellaSwag": 61.2, + "MMLU": 26.83, + "TruthfulQA": 40.83, + "Winogrande": 64.56, + "GSM8K": 0.68, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "6b4385dc45c47d509b6400c41a2ff3665ad1d189", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/opt-6.7b", + "Average \u2b06\ufe0f": 39.08, + "ARC": 39.16, + "HellaSwag": 68.66, + "MMLU": 24.57, + "TruthfulQA": 35.12, + "Winogrande": 65.98, + "GSM8K": 0.99, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 91.0, + "Available on the hub": true, + "Model sha": "a45aa65bbeb77c1558bc99bedc6779195462dab0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "togethercomputer\/RedPajama-INCITE-Instruct-3B-v1", + "Average \u2b06\ufe0f": 39.06, + "ARC": 41.55, + "HellaSwag": 65.48, + "MMLU": 25.03, + "TruthfulQA": 36.41, + "Winogrande": 64.48, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 88.0, + "Available on the hub": true, + "Model sha": "0c66778ee09a036886741707733620b91057909a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/deacon-3b", + "Average \u2b06\ufe0f": 39.05, + "ARC": 39.68, + "HellaSwag": 66.42, + "MMLU": 27.13, + "TruthfulQA": 36.07, + "Winogrande": 64.64, + "GSM8K": 0.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c96b846ce7bacf5ad231957630dc94d59f329339", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Fredithefish\/ScarletPajama-3B-HF", + "Average \u2b06\ufe0f": 39.04, + "ARC": 39.76, + "HellaSwag": 64.89, + "MMLU": 27.28, + "TruthfulQA": 37.6, + "Winogrande": 64.48, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "9dd07308b6eb3f270c5762250b6d46abd6f87b6f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psmathur\/orca_mini_3b", + "Average \u2b06\ufe0f": 39.03, + "ARC": 41.55, + "HellaSwag": 61.52, + "MMLU": 26.79, + "TruthfulQA": 42.42, + "Winogrande": 61.8, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 3.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fd2754e80ce80757a3a68a840d7d287dd7def676", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/black_goo_recipe_c", + "Average \u2b06\ufe0f": 39.01, + "ARC": 38.74, + "HellaSwag": 66.83, + "MMLU": 26.57, + "TruthfulQA": 36.54, + "Winogrande": 64.72, + "GSM8K": 0.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "78c0a6432ac0a6c2e54a2c3aac4cb70f446eb18b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Fredithefish\/Guanaco-3B-Uncensored-v2", + "Average \u2b06\ufe0f": 38.98, + "ARC": 42.15, + "HellaSwag": 66.72, + "MMLU": 26.18, + "TruthfulQA": 35.21, + "Winogrande": 63.3, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "e07122091fd4b318dcea105b16c73144d95bc2f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "jb723\/cross_lingual_epoch2", + "Average \u2b06\ufe0f": 38.97, + "ARC": 39.25, + "HellaSwag": 47.92, + "MMLU": 36.66, + "TruthfulQA": 47.9, + "Winogrande": 62.12, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "86e59e85b234e6c882758724849d7a1e4fe0b30a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "mwitiderrick\/open_llama_3b_instruct_v_0.2", + "Average \u2b06\ufe0f": 38.97, + "ARC": 38.48, + "HellaSwag": 66.77, + "MMLU": 25.34, + "TruthfulQA": 38.16, + "Winogrande": 63.46, + "GSM8K": 1.59, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "6ae4004fe8901c1dae19108bc37e8b744cd08539", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Guanaco-3B-Uncensored-v2-GPTQ", + "Average \u2b06\ufe0f": 38.95, + "ARC": 41.64, + "HellaSwag": 64.76, + "MMLU": 26.25, + "TruthfulQA": 36.58, + "Winogrande": 64.33, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "GPTQ", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.78, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "c80e2f01377d551ad17c8c9bac3f52578c38d653", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Fredithefish\/Guanaco-3B-Uncensored", + "Average \u2b06\ufe0f": 38.94, + "ARC": 42.49, + "HellaSwag": 66.99, + "MMLU": 25.55, + "TruthfulQA": 34.71, + "Winogrande": 63.38, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "084a12f767b31c1fde681bebb14e9a291e506ea8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "health360\/Healix-3B", + "Average \u2b06\ufe0f": 38.93, + "ARC": 37.71, + "HellaSwag": 65.94, + "MMLU": 26.02, + "TruthfulQA": 37.4, + "Winogrande": 65.75, + "GSM8K": 0.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "52297e0b6845b3c1b26f336fd2a2c9b2f56ce6ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Technoculture\/MT7Bi-wizard-3-alpha-dpo", + "Average \u2b06\ufe0f": 38.88, + "ARC": 41.21, + "HellaSwag": 59.34, + "MMLU": 27.31, + "TruthfulQA": 39.06, + "Winogrande": 65.35, + "GSM8K": 0.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "097011308950f819d70277b5a35ddf2e09fc9122", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "CobraMamba\/mamba-gpt-3b", + "Average \u2b06\ufe0f": 38.87, + "ARC": 40.53, + "HellaSwag": 64.94, + "MMLU": 25.35, + "TruthfulQA": 37.14, + "Winogrande": 65.04, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "21a8212e3641dd14924d6bdead0774b64dda8ce0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "appvoid\/palmer-002.5", + "Average \u2b06\ufe0f": 38.86, + "ARC": 37.54, + "HellaSwag": 61.84, + "MMLU": 25.21, + "TruthfulQA": 40.22, + "Winogrande": 66.38, + "GSM8K": 1.97, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "5a987c226e4935167dbbec5565d16c66853a3932", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "OpenAssistant\/galactica-6.7b-finetuned", + "Average \u2b06\ufe0f": 38.84, + "ARC": 41.55, + "HellaSwag": 51.01, + "MMLU": 38.03, + "TruthfulQA": 41.65, + "Winogrande": 57.7, + "GSM8K": 3.11, + "Type": "", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 34.0, + "Available on the hub": false, + "Model sha": "d86db70e16111175ff7900f71d40806ccf4b8491", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "frank098\/orca_mini_3b_juniper", + "Average \u2b06\ufe0f": 38.83, + "ARC": 40.87, + "HellaSwag": 61.73, + "MMLU": 26.37, + "TruthfulQA": 43.19, + "Winogrande": 60.3, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "c08749034baa053834f1b709b6e7b88b914cd1fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-6.7B-Nerybus-Mix", + "Average \u2b06\ufe0f": 38.83, + "ARC": 39.16, + "HellaSwag": 68.63, + "MMLU": 24.47, + "TruthfulQA": 34.84, + "Winogrande": 65.11, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "9afe4dca5a9dbd71cb90d1050d142837f4c739f6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-12b", + "Average \u2b06\ufe0f": 38.82, + "ARC": 39.59, + "HellaSwag": 68.82, + "MMLU": 26.76, + "TruthfulQA": 31.85, + "Winogrande": 64.17, + "GSM8K": 1.74, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 125.0, + "Available on the hub": true, + "Model sha": "35c9d7f32fbb108fb8b5bdd574eb03369d1eed49", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "heegyu\/WizardVicuna-open-llama-3b-v2", + "Average \u2b06\ufe0f": 38.77, + "ARC": 37.71, + "HellaSwag": 66.6, + "MMLU": 27.23, + "TruthfulQA": 36.8, + "Winogrande": 63.3, + "GSM8K": 0.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1c69905286171d7d3ef3f95f8e1bbc9150bad3cd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/black_goo_recipe_a", + "Average \u2b06\ufe0f": 38.73, + "ARC": 38.14, + "HellaSwag": 66.56, + "MMLU": 25.75, + "TruthfulQA": 37.46, + "Winogrande": 63.93, + "GSM8K": 0.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7067f68d4d9e7b10a1aa2c9fa97456bc04678867", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-6B-nerys-v2", + "Average \u2b06\ufe0f": 38.72, + "ARC": 38.4, + "HellaSwag": 68.57, + "MMLU": 24.34, + "TruthfulQA": 34.73, + "Winogrande": 65.59, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 22.0, + "Available on the hub": true, + "Model sha": "9e1f1498391df2c28ce35a9290a5a24b8022a43b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "andrijdavid\/tinyllama-dare", + "Average \u2b06\ufe0f": 38.64, + "ARC": 37.29, + "HellaSwag": 62.78, + "MMLU": 25.2, + "TruthfulQA": 39.01, + "Winogrande": 65.9, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f3c5e1369064d3167377b6965a74637d26102e6b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hakurei\/instruct-12b", + "Average \u2b06\ufe0f": 38.63, + "ARC": 42.58, + "HellaSwag": 66.76, + "MMLU": 26.79, + "TruthfulQA": 31.96, + "Winogrande": 63.46, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.0, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "ff4699b502b79c716330b6f761002588a65dcba6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-oig-oasst1-256-6_9b", + "Average \u2b06\ufe0f": 38.62, + "ARC": 39.93, + "HellaSwag": 65.42, + "MMLU": 26.39, + "TruthfulQA": 35.0, + "Winogrande": 63.38, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 9.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "f1c9bac89b74d3487cb092788ce828fb9520c1a7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Qwen\/Qwen1.5-0.5B", + "Average \u2b06\ufe0f": 38.62, + "ARC": 31.48, + "HellaSwag": 49.05, + "MMLU": 39.35, + "TruthfulQA": 38.3, + "Winogrande": 57.22, + "GSM8K": 16.3, + "Type": "pretrained", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.62, + "Hub \u2764\ufe0f": 58.0, + "Available on the hub": true, + "Model sha": "fedce23ef6393499effdf4958f9b3256f299cc7d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "matsuo-lab\/weblab-10b", + "Average \u2b06\ufe0f": 38.59, + "ARC": 39.51, + "HellaSwag": 65.76, + "MMLU": 26.29, + "TruthfulQA": 36.02, + "Winogrande": 62.51, + "GSM8K": 1.44, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.0, + "Hub \u2764\ufe0f": 58.0, + "Available on the hub": true, + "Model sha": "d6fc432983b1633a4c1568d121c60de6b8c3e511", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/black_goo_recipe_d", + "Average \u2b06\ufe0f": 38.57, + "ARC": 37.8, + "HellaSwag": 66.5, + "MMLU": 26.64, + "TruthfulQA": 36.46, + "Winogrande": 63.61, + "GSM8K": 0.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fdf7f93837808958f9463d3c683314e7f649a088", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "RWKV\/rwkv-raven-7b", + "Average \u2b06\ufe0f": 38.55, + "ARC": 39.42, + "HellaSwag": 66.48, + "MMLU": 23.64, + "TruthfulQA": 38.56, + "Winogrande": 62.9, + "GSM8K": 0.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": false, + "Model sha": "a2dfc9f659be13556a25d9e38da642c6f67aeee3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "togethercomputer\/RedPajama-INCITE-Base-3B-v1", + "Average \u2b06\ufe0f": 38.54, + "ARC": 40.19, + "HellaSwag": 64.77, + "MMLU": 27.03, + "TruthfulQA": 33.23, + "Winogrande": 64.72, + "GSM8K": 1.29, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 85.0, + "Available on the hub": true, + "Model sha": "094fbdd0c911feb485ce55de1952ab2e75277e1e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Lazycuber\/pyg-instruct-wizardlm", + "Average \u2b06\ufe0f": 38.54, + "ARC": 40.96, + "HellaSwag": 66.71, + "MMLU": 26.33, + "TruthfulQA": 31.93, + "Winogrande": 63.69, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "f00ef7a7b0cc6f02af2a11ac764270dfd61b9e2f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-30B-Erebus", + "Average \u2b06\ufe0f": 38.53, + "ARC": 36.69, + "HellaSwag": 65.6, + "MMLU": 24.8, + "TruthfulQA": 38.76, + "Winogrande": 65.11, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 54.0, + "Available on the hub": true, + "Model sha": "a1041efcf9599c962822274e92040710579a5bf2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Fredithefish\/CrimsonPajama", + "Average \u2b06\ufe0f": 38.52, + "ARC": 40.19, + "HellaSwag": 65.47, + "MMLU": 25.95, + "TruthfulQA": 33.78, + "Winogrande": 65.19, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "ff054eeff9e3541464383d40b36d182057d01113", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-oig-oasst1-512-6_9b", + "Average \u2b06\ufe0f": 38.52, + "ARC": 40.44, + "HellaSwag": 65.58, + "MMLU": 24.9, + "TruthfulQA": 36.68, + "Winogrande": 62.51, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 9.0, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "029a787e0d98fcd3fecffbfbeb4a75a425474937", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_opt6.7b_10e5", + "Average \u2b06\ufe0f": 38.52, + "ARC": 37.03, + "HellaSwag": 65.65, + "MMLU": 25.0, + "TruthfulQA": 37.61, + "Winogrande": 65.43, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "43cd61a5ed4caeedf335aa8f2ccde8c7457ced73", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/guanaco-33B-GPTQ", + "Average \u2b06\ufe0f": 38.51, + "ARC": 28.16, + "HellaSwag": 26.34, + "MMLU": 24.94, + "TruthfulQA": 48.98, + "Winogrande": 78.85, + "GSM8K": 23.81, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 35.58, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": true, + "Model sha": "8e42e031bfc8be3bbf31dc546d7c51fb991ff6e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/LLongMA-3b-LIMA", + "Average \u2b06\ufe0f": 38.51, + "ARC": 39.08, + "HellaSwag": 67.15, + "MMLU": 26.43, + "TruthfulQA": 34.71, + "Winogrande": 63.38, + "GSM8K": 0.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "333b8c41e42a46a6f3aecaf8f3fa8a17c6d83990", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "pszemraj\/pythia-6.9b-HC3", + "Average \u2b06\ufe0f": 38.51, + "ARC": 36.52, + "HellaSwag": 61.76, + "MMLU": 26.94, + "TruthfulQA": 45.05, + "Winogrande": 60.77, + "GSM8K": 0.0, + "Type": "", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.9, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c5c60ea656e921e6c5415f6feaebac4dd9b2aa2a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/black_goo_recipe_b", + "Average \u2b06\ufe0f": 38.49, + "ARC": 37.63, + "HellaSwag": 66.72, + "MMLU": 25.68, + "TruthfulQA": 37.09, + "Winogrande": 63.77, + "GSM8K": 0.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "42faec8429cee8c9f4f5db58ffa193f6f8e0d498", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Fredithefish\/RedPajama-INCITE-Chat-3B-ShareGPT-11K", + "Average \u2b06\ufe0f": 38.47, + "ARC": 40.61, + "HellaSwag": 64.84, + "MMLU": 26.13, + "TruthfulQA": 35.41, + "Winogrande": 63.54, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ec33d12d08d61ed821e67b1a55ad404dc3457ebf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PygmalionAI\/pygmalion-6b", + "Average \u2b06\ufe0f": 38.47, + "ARC": 40.53, + "HellaSwag": 67.47, + "MMLU": 25.73, + "TruthfulQA": 32.53, + "Winogrande": 62.51, + "GSM8K": 2.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 709.0, + "Available on the hub": true, + "Model sha": "30e2405100eac6bd53f75964cc7345eeafd19f7d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/WizardLM-33B-V1.0-Uncensored-GPTQ", + "Average \u2b06\ufe0f": 38.43, + "ARC": 27.39, + "HellaSwag": 26.03, + "MMLU": 25.81, + "TruthfulQA": 48.9, + "Winogrande": 77.9, + "GSM8K": 24.56, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 35.58, + "Hub \u2764\ufe0f": 44.0, + "Available on the hub": true, + "Model sha": "1c65902c620fcdf6b9c8e36ce17f21360e186a1e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "anhnv125\/pygmalion-6b-roleplay", + "Average \u2b06\ufe0f": 38.34, + "ARC": 40.53, + "HellaSwag": 67.47, + "MMLU": 25.73, + "TruthfulQA": 32.53, + "Winogrande": 62.67, + "GSM8K": 1.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "e49ed0bde45de0a436bff678ec4872069e8f230c", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TehVenom\/DiffMerge_Pygmalion_Main-onto-V8P4", + "Average \u2b06\ufe0f": 38.31, + "ARC": 40.53, + "HellaSwag": 67.48, + "MMLU": 25.68, + "TruthfulQA": 32.55, + "Winogrande": 62.51, + "GSM8K": 1.14, + "Type": "", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "f855780745aa34c3bdbe020e4c51253d538cb21e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "acrastt\/OmegLLaMA-3B", + "Average \u2b06\ufe0f": 38.28, + "ARC": 40.36, + "HellaSwag": 66.13, + "MMLU": 28.0, + "TruthfulQA": 33.31, + "Winogrande": 61.64, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "520c5f1ceb5c90d4011887e2a8d3becf15e7e66e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "openlm-research\/open_llama_3b", + "Average \u2b06\ufe0f": 38.26, + "ARC": 39.85, + "HellaSwag": 62.65, + "MMLU": 26.94, + "TruthfulQA": 34.97, + "Winogrande": 64.72, + "GSM8K": 0.45, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 139.0, + "Available on the hub": true, + "Model sha": "141067009124b9c0aea62c76b3eb952174864057", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "aihub-app\/zyte-1B", + "Average \u2b06\ufe0f": 38.23, + "ARC": 37.88, + "HellaSwag": 61.37, + "MMLU": 24.61, + "TruthfulQA": 42.14, + "Winogrande": 61.96, + "GSM8K": 1.44, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6c2b31ee038f8df37547c013d73b91c4a07e41a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xaviviro\/FLOR-6.3B-xat", + "Average \u2b06\ufe0f": 38.23, + "ARC": 38.65, + "HellaSwag": 63.76, + "MMLU": 26.54, + "TruthfulQA": 37.96, + "Winogrande": 62.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.25, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "edd1cbf53f584c6bc7b38a31a0b7beed8e942e8f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aihub-app\/zyte-1.1B", + "Average \u2b06\ufe0f": 38.22, + "ARC": 37.88, + "HellaSwag": 61.37, + "MMLU": 24.62, + "TruthfulQA": 42.15, + "Winogrande": 61.96, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4537b28d9b2e9958c53b6d4aa6e16f46f85c1867", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "venkycs\/zyte-v1-1.1B", + "Average \u2b06\ufe0f": 38.21, + "ARC": 37.29, + "HellaSwag": 61.41, + "MMLU": 24.6, + "TruthfulQA": 42.59, + "Winogrande": 62.04, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b75c703a236c6f0394f7f8641c4ecee016c2e43f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewof\/koishi-instruct-3b", + "Average \u2b06\ufe0f": 38.16, + "ARC": 40.96, + "HellaSwag": 64.54, + "MMLU": 26.58, + "TruthfulQA": 31.65, + "Winogrande": 64.09, + "GSM8K": 1.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 2.91, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "2bb7f3842398b048efa4ae2d1aafb9e2f18a8586", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "RESMPDEV\/Qwen1.5-Wukong-0.5B", + "Average \u2b06\ufe0f": 38.15, + "ARC": 31.74, + "HellaSwag": 47.78, + "MMLU": 38.44, + "TruthfulQA": 38.92, + "Winogrande": 56.51, + "GSM8K": 15.54, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Qwen2ForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cb46afdc603e018e2ec4a672769b0e8a473aa88b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-6.7b", + "Average \u2b06\ufe0f": 38.06, + "ARC": 40.1, + "HellaSwag": 65.0, + "MMLU": 24.64, + "TruthfulQA": 32.85, + "Winogrande": 64.72, + "GSM8K": 1.06, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.65, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b666a6e46eeade607c73ed1334ecda3b9345e4bf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "saberai\/Zro1.5_3B", + "Average \u2b06\ufe0f": 38.02, + "ARC": 35.92, + "HellaSwag": 61.11, + "MMLU": 25.55, + "TruthfulQA": 36.89, + "Winogrande": 58.72, + "GSM8K": 9.93, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "434e3ac9bb300779d677486d5e04d774fc514169", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "RWKV\/rwkv-4-7b-pile", + "Average \u2b06\ufe0f": 37.95, + "ARC": 39.68, + "HellaSwag": 66.31, + "MMLU": 24.96, + "TruthfulQA": 33.65, + "Winogrande": 62.35, + "GSM8K": 0.76, + "Type": "pretrained", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "922e22a761427e50d7be457b31a76b1126021b8b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "indischepartij\/TinyUltra-4x1.1B-Base-Alpha", + "Average \u2b06\ufe0f": 37.94, + "ARC": 34.9, + "HellaSwag": 61.42, + "MMLU": 25.42, + "TruthfulQA": 37.59, + "Winogrande": 65.75, + "GSM8K": 2.58, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 3.38, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c705462832bc69b3ab71cf6e5ebc46388b4145a6", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "gmonsoon\/TinyUltra-4x1.1B-Base-Alpha", + "Average \u2b06\ufe0f": 37.94, + "ARC": 34.9, + "HellaSwag": 61.42, + "MMLU": 25.42, + "TruthfulQA": 37.59, + "Winogrande": 65.75, + "GSM8K": 2.58, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.38, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c705462832bc69b3ab71cf6e5ebc46388b4145a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Tinyllama-Cinder-1.3B-Reason-Test", + "Average \u2b06\ufe0f": 37.88, + "ARC": 34.56, + "HellaSwag": 58.24, + "MMLU": 25.79, + "TruthfulQA": 39.93, + "Winogrande": 63.93, + "GSM8K": 4.85, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.28, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c7f891765a4d43ac972302a24ed67158cec8dc18", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KnutJaegersberg\/Galactica-6.7B-EssayWriter", + "Average \u2b06\ufe0f": 37.75, + "ARC": 40.1, + "HellaSwag": 50.29, + "MMLU": 33.88, + "TruthfulQA": 40.27, + "Winogrande": 58.48, + "GSM8K": 3.49, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 6.66, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "ac74fdd938de1ffd34832d66a25db20b0230983e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Devio\/test-22B", + "Average \u2b06\ufe0f": 37.71, + "ARC": 39.42, + "HellaSwag": 64.51, + "MMLU": 27.13, + "TruthfulQA": 37.13, + "Winogrande": 57.7, + "GSM8K": 0.38, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 21.83, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cd72f5954ab5801dd2c1b499e59265f7504f9ee6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/TinyLlama-MoE-Chat", + "Average \u2b06\ufe0f": 37.71, + "ARC": 34.73, + "HellaSwag": 59.29, + "MMLU": 29.71, + "TruthfulQA": 39.35, + "Winogrande": 62.19, + "GSM8K": 0.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2d786c9077b949d7ee3f5201813d7edccc7bd2da", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "aihub-app\/zyte-1.1b", + "Average \u2b06\ufe0f": 37.7, + "ARC": 37.54, + "HellaSwag": 60.82, + "MMLU": 24.57, + "TruthfulQA": 39.46, + "Winogrande": 62.04, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3d4e61bc3c090a28355cceba8da106c31e3bbb84", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ericzzz\/falcon-rw-1b-instruct-openorca", + "Average \u2b06\ufe0f": 37.63, + "ARC": 34.56, + "HellaSwag": 60.93, + "MMLU": 28.77, + "TruthfulQA": 37.42, + "Winogrande": 60.69, + "GSM8K": 3.41, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "bb5f86170d8d01aa850bb216bb2797899570c13e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "euclaise\/falcon_1b_stage2", + "Average \u2b06\ufe0f": 37.59, + "ARC": 35.49, + "HellaSwag": 65.56, + "MMLU": 23.83, + "TruthfulQA": 38.32, + "Winogrande": 62.35, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "c3ef73a8c9dc06fae4bfe4460d2f293147aecbb0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ikala\/bloom-zh-3b-chat", + "Average \u2b06\ufe0f": 37.58, + "ARC": 38.82, + "HellaSwag": 54.71, + "MMLU": 31.62, + "TruthfulQA": 41.25, + "Winogrande": 58.64, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "4ea0ad223a2623fc15e8824c1c4f8e6539bc40b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2", + "Average \u2b06\ufe0f": 37.55, + "ARC": 36.43, + "HellaSwag": 61.41, + "MMLU": 25.01, + "TruthfulQA": 37.59, + "Winogrande": 64.64, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "fdc6ff469295d0aaabec8948525b70d6688728ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Evaloric\/Evaloric-1.1B", + "Average \u2b06\ufe0f": 37.54, + "ARC": 35.07, + "HellaSwag": 60.93, + "MMLU": 25.36, + "TruthfulQA": 37.78, + "Winogrande": 64.96, + "GSM8K": 1.14, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b3953afa698098e06e03aa14713015b11b4ab421", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/CodeLlama-13B-Python-fp16", + "Average \u2b06\ufe0f": 37.52, + "ARC": 33.19, + "HellaSwag": 44.5, + "MMLU": 25.94, + "TruthfulQA": 43.99, + "Winogrande": 67.4, + "GSM8K": 10.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "442282f4207442b828953a72c51a919c332cba5c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ddyuudd\/merge_dolly-v2-3b_dpo_test", + "Average \u2b06\ufe0f": 37.49, + "ARC": 40.02, + "HellaSwag": 65.14, + "MMLU": 24.99, + "TruthfulQA": 33.3, + "Winogrande": 59.35, + "GSM8K": 2.12, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e624fdbb538362206af1b98400bf44bbc0247226", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "HiTZ\/GoLLIE-7B", + "Average \u2b06\ufe0f": 37.48, + "ARC": 36.09, + "HellaSwag": 57.93, + "MMLU": 29.38, + "TruthfulQA": 39.27, + "Winogrande": 58.96, + "GSM8K": 3.26, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "d3e41fef45f6a7d438c46ba7d9fce5d0d486c7a9", + "Flagged": true, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ddyuudd\/dolly-v2-3b", + "Average \u2b06\ufe0f": 37.46, + "ARC": 39.68, + "HellaSwag": 65.04, + "MMLU": 25.09, + "TruthfulQA": 33.8, + "Winogrande": 59.12, + "GSM8K": 2.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "84519fd8b688e7e1c122b5d9338c225a7ff2cadc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/fairseq-dense-2.7B", + "Average \u2b06\ufe0f": 37.41, + "ARC": 33.79, + "HellaSwag": 65.74, + "MMLU": 26.44, + "TruthfulQA": 34.57, + "Winogrande": 63.93, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 2.78, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "4201f4b101bad2992efc8452009317a354ec52d2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cerebras\/Cerebras-GPT-13B", + "Average \u2b06\ufe0f": 37.4, + "ARC": 38.14, + "HellaSwag": 60.01, + "MMLU": 25.92, + "TruthfulQA": 39.19, + "Winogrande": 59.83, + "GSM8K": 1.29, + "Type": "pretrained", + "Architecture": "GPT2Model", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 636.0, + "Available on the hub": true, + "Model sha": "7e97fa4b15edd955094c4395d62e6f4290e365b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "gardner\/TinyLlama-1.1B-SlimOrca-Function-Calling-3T", + "Average \u2b06\ufe0f": 37.38, + "ARC": 36.09, + "HellaSwag": 59.66, + "MMLU": 28.21, + "TruthfulQA": 36.74, + "Winogrande": 59.12, + "GSM8K": 4.47, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "df79003585fb9af2ac4644a9029c70d5a998a95e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "ericzzz\/falcon-rw-1b-chat", + "Average \u2b06\ufe0f": 37.37, + "ARC": 35.58, + "HellaSwag": 61.12, + "MMLU": 24.51, + "TruthfulQA": 39.62, + "Winogrande": 61.72, + "GSM8K": 1.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "61c2b3f27c8d32912d0b9ff47ebf687af2eb9e86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dball\/zephyr-tiny-dpo-qlora", + "Average \u2b06\ufe0f": 37.35, + "ARC": 36.6, + "HellaSwag": 61.66, + "MMLU": 25.78, + "TruthfulQA": 36.4, + "Winogrande": 61.56, + "GSM8K": 2.12, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6c6f2246d4db07605b714f956f5e48878049b7b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Dampish\/StellarX-4B-V0", + "Average \u2b06\ufe0f": 37.31, + "ARC": 36.95, + "HellaSwag": 61.9, + "MMLU": 26.85, + "TruthfulQA": 34.3, + "Winogrande": 63.85, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 4.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0a79832bd57a8cdadc61626fb77bdc26c85b9fa4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ShieldX\/manovyadh-1.1B-v1-chat", + "Average \u2b06\ufe0f": 37.3, + "ARC": 35.92, + "HellaSwag": 60.03, + "MMLU": 25.82, + "TruthfulQA": 39.17, + "Winogrande": 61.09, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "32dbae5401c03792f275d7f079be568002eafd9a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TinyLlama\/TinyLlama-1.1B-Chat-v1.0", + "Average \u2b06\ufe0f": 37.28, + "ARC": 36.09, + "HellaSwag": 61.1, + "MMLU": 25.39, + "TruthfulQA": 37.48, + "Winogrande": 61.25, + "GSM8K": 2.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 812.0, + "Available on the hub": true, + "Model sha": "de253fa9783f8bd558c9ed398c8ffbe3c55cedb3", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/WizardLM-30B-Uncensored-GPTQ", + "Average \u2b06\ufe0f": 37.27, + "ARC": 29.44, + "HellaSwag": 26.47, + "MMLU": 24.35, + "TruthfulQA": 49.15, + "Winogrande": 73.16, + "GSM8K": 21.08, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 35.58, + "Hub \u2764\ufe0f": 116.0, + "Available on the hub": true, + "Model sha": "43c701ddbe0bceac26c860307e06763cc5203500", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DanielSc4\/RedPajama-INCITE-Chat-3B-v1-FT-LoRA-8bit-test1", + "Average \u2b06\ufe0f": 37.27, + "ARC": 38.65, + "HellaSwag": 63.53, + "MMLU": 25.16, + "TruthfulQA": 36.07, + "Winogrande": 60.14, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "8bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f477d24b00e05fe4c5f8d5f933080994cfd90e4e", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "GeorgiaTechResearchInstitute\/galactica-6.7b-evol-instruct-70k", + "Average \u2b06\ufe0f": 37.27, + "ARC": 42.58, + "HellaSwag": 49.3, + "MMLU": 32.96, + "TruthfulQA": 42.1, + "Winogrande": 56.27, + "GSM8K": 0.38, + "Type": "", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "14fa470051d0bc38fd871643186a9edfd3a8a9aa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "venkycs\/ZySec-1B", + "Average \u2b06\ufe0f": 37.26, + "ARC": 38.4, + "HellaSwag": 61.53, + "MMLU": 25.05, + "TruthfulQA": 35.66, + "Winogrande": 61.33, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4a0f6267424e62319a8c0516af377bf576d9e210", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "euclaise\/falcon_1b_stage1", + "Average \u2b06\ufe0f": 37.25, + "ARC": 35.15, + "HellaSwag": 62.4, + "MMLU": 24.47, + "TruthfulQA": 40.0, + "Winogrande": 61.48, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f85d91ff3f6cadc93f7222a19b9c4930c8842366", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Tinyllama-Cinder-1.3B-Reason-Test.2", + "Average \u2b06\ufe0f": 37.25, + "ARC": 32.76, + "HellaSwag": 58.27, + "MMLU": 24.39, + "TruthfulQA": 39.0, + "Winogrande": 65.04, + "GSM8K": 4.02, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.28, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4c049680e43aa4fdab117c7a440b83efb4560ef5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AI-Sweden-Models\/gpt-sw3-6.7b", + "Average \u2b06\ufe0f": 37.23, + "ARC": 36.35, + "HellaSwag": 60.75, + "MMLU": 26.0, + "TruthfulQA": 39.04, + "Winogrande": 60.69, + "GSM8K": 0.53, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7b20cb87e793e1b73b6a73da5261c6010f2b5410", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Josephgflowers\/TinyLlama-3T-Cinder-v1.3", + "Average \u2b06\ufe0f": 37.23, + "ARC": 33.96, + "HellaSwag": 58.14, + "MMLU": 25.41, + "TruthfulQA": 38.13, + "Winogrande": 63.93, + "GSM8K": 3.79, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "4cd25191268b231cb584c85ce55285902c9fa31a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "sreeramajay\/TinyLlama-1.1B-orca-v1.0", + "Average \u2b06\ufe0f": 37.17, + "ARC": 36.35, + "HellaSwag": 61.23, + "MMLU": 25.18, + "TruthfulQA": 36.58, + "Winogrande": 61.4, + "GSM8K": 2.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7dbbc8ccc85c1c3f1ce7cffbb62b97ca6d2ca046", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TinyLlama\/TinyLlama-1.1B-Chat-v1.0", + "Average \u2b06\ufe0f": 37.17, + "ARC": 35.92, + "HellaSwag": 61.11, + "MMLU": 25.0, + "TruthfulQA": 37.38, + "Winogrande": 61.17, + "GSM8K": 2.43, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 812.0, + "Available on the hub": true, + "Model sha": "de253fa9783f8bd558c9ed398c8ffbe3c55cedb3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "eren23\/DistiLabelOrca-TinyLLama-1.1B", + "Average \u2b06\ufe0f": 37.17, + "ARC": 36.18, + "HellaSwag": 61.15, + "MMLU": 25.09, + "TruthfulQA": 38.05, + "Winogrande": 60.85, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c8fa674a68fe45f8f87a6aef87c8e2cbcee62b81", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIGym\/TinyLlama-1.1B-2.5T-chat-and-function-calling", + "Average \u2b06\ufe0f": 37.16, + "ARC": 34.39, + "HellaSwag": 59.61, + "MMLU": 26.32, + "TruthfulQA": 38.92, + "Winogrande": 61.96, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5dc9334f86c4d5eaa916edd02262416b54343fa8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kevin009\/lamatama", + "Average \u2b06\ufe0f": 37.15, + "ARC": 36.35, + "HellaSwag": 61.12, + "MMLU": 24.72, + "TruthfulQA": 37.67, + "Winogrande": 60.77, + "GSM8K": 2.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bb8349cd64652df9a62bc46c12c24f3226662a5c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "princeton-nlp\/Sheared-LLaMA-1.3B-ShareGPT", + "Average \u2b06\ufe0f": 37.14, + "ARC": 33.96, + "HellaSwag": 62.55, + "MMLU": 26.42, + "TruthfulQA": 43.03, + "Winogrande": 56.83, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "d2f3cfae7746c4ff07353b39828985ea0f36b07d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Danielbrdz\/Barcenas-Tiny-1.1b-DPO", + "Average \u2b06\ufe0f": 37.12, + "ARC": 36.26, + "HellaSwag": 61.2, + "MMLU": 24.83, + "TruthfulQA": 37.45, + "Winogrande": 60.93, + "GSM8K": 2.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "871b3e79f0fe988e2dc601c5e062d612ce17b129", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-2.7b", + "Average \u2b06\ufe0f": 37.09, + "ARC": 37.37, + "HellaSwag": 60.74, + "MMLU": 25.86, + "TruthfulQA": 35.4, + "Winogrande": 62.12, + "GSM8K": 1.06, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 2.91, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b9d8cace80b1a97f5ed380711aea31f2d1b24310", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Deathsquad10\/TinyLlama-repeat", + "Average \u2b06\ufe0f": 37.09, + "ARC": 35.24, + "HellaSwag": 60.25, + "MMLU": 26.07, + "TruthfulQA": 38.78, + "Winogrande": 60.46, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "14728ff7c51471faec92a4c86261951cc4175f61", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "davanstrien\/TinyLlama-1.1B-Chat-v1.0-intel-dpo", + "Average \u2b06\ufe0f": 37.09, + "ARC": 35.84, + "HellaSwag": 61.29, + "MMLU": 25.05, + "TruthfulQA": 37.38, + "Winogrande": 61.01, + "GSM8K": 1.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "da2b792b7edf3d30b6e8ed05ebc8e9bbde442b5c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "tiiuae\/falcon-rw-1b", + "Average \u2b06\ufe0f": 37.07, + "ARC": 35.07, + "HellaSwag": 63.56, + "MMLU": 25.28, + "TruthfulQA": 35.96, + "Winogrande": 62.04, + "GSM8K": 0.53, + "Type": "pretrained", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 90.0, + "Available on the hub": true, + "Model sha": "e4b9872bb803165eb22f0a867d4e6a64d34fce19", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Phind\/Phind-CodeLlama-34B-v1", + "Average \u2b06\ufe0f": 37.06, + "ARC": 27.13, + "HellaSwag": 28.28, + "MMLU": 28.94, + "TruthfulQA": 44.94, + "Winogrande": 72.61, + "GSM8K": 20.47, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 320.0, + "Available on the hub": true, + "Model sha": "b073c9bb418ae52ca76b4ab48ac2dfbc8622f434", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xaviviro\/OpenHermes-2.5-FLOR-6.3B", + "Average \u2b06\ufe0f": 37.04, + "ARC": 33.45, + "HellaSwag": 54.53, + "MMLU": 25.18, + "TruthfulQA": 46.12, + "Winogrande": 62.98, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1ac3215a61b2e11010230d52a6153635def819e6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/TinyLlama-Cinder-1.3B-Test.2", + "Average \u2b06\ufe0f": 37.04, + "ARC": 33.7, + "HellaSwag": 58.66, + "MMLU": 25.69, + "TruthfulQA": 37.98, + "Winogrande": 64.09, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.28, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8ef75bb502bcafe83a03fe7154e302ea6de185df", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "bigscience\/bloomz-3b", + "Average \u2b06\ufe0f": 37.03, + "ARC": 36.86, + "HellaSwag": 54.95, + "MMLU": 32.91, + "TruthfulQA": 40.34, + "Winogrande": 57.14, + "GSM8K": 0.0, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": true, + "Model sha": "31eefcb2bcd69632925adf07e090debafe95436d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kevin009\/TinyNaughtyLlama-v1.0", + "Average \u2b06\ufe0f": 37.03, + "ARC": 35.92, + "HellaSwag": 61.04, + "MMLU": 25.82, + "TruthfulQA": 36.77, + "Winogrande": 60.22, + "GSM8K": 2.43, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "0ed70fbd1075c6f62cf9227023a67dd832e2b710", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alexredna\/TinyLlama-1.1B-Chat-v1.0-reasoning-v2-dpo", + "Average \u2b06\ufe0f": 37.03, + "ARC": 34.39, + "HellaSwag": 61.87, + "MMLU": 26.34, + "TruthfulQA": 36.13, + "Winogrande": 63.46, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f61da97b0c79b404f3dbe88f9379d1c918777338", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aabbhishekk\/TinyLlama-1.1B-miniguanaco", + "Average \u2b06\ufe0f": 37.02, + "ARC": 35.15, + "HellaSwag": 60.26, + "MMLU": 26.26, + "TruthfulQA": 38.84, + "Winogrande": 60.14, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e2495b16f1d812485842b199a026438e037f15f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "codellama\/CodeLlama-13b-Python-hf", + "Average \u2b06\ufe0f": 37.0, + "ARC": 32.59, + "HellaSwag": 43.94, + "MMLU": 27.23, + "TruthfulQA": 44.59, + "Winogrande": 65.04, + "GSM8K": 8.64, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 42.0, + "Available on the hub": true, + "Model sha": "ea1b775799b477fe22e64f8ac9107f28950b5c87", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIChenKai\/TinyLlama-1.1B-Chat-v1.0-x2-MoE", + "Average \u2b06\ufe0f": 36.98, + "ARC": 36.01, + "HellaSwag": 61.04, + "MMLU": 24.81, + "TruthfulQA": 37.37, + "Winogrande": 60.38, + "GSM8K": 2.27, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.86, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fe49be7cae7eb8362e176e4d371fb9dd8c68422d", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-2.7B-Erebus", + "Average \u2b06\ufe0f": 36.96, + "ARC": 34.39, + "HellaSwag": 60.91, + "MMLU": 26.7, + "TruthfulQA": 37.82, + "Winogrande": 61.64, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 34.0, + "Available on the hub": true, + "Model sha": "39ca914ceb82f7f14a38484023bc04f0cd5d0a8d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jan-hq\/LlamaCorn-1.1B", + "Average \u2b06\ufe0f": 36.94, + "ARC": 34.13, + "HellaSwag": 59.33, + "MMLU": 29.01, + "TruthfulQA": 36.78, + "Winogrande": 61.96, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "309e861eb3291666e9bd4e899fc95c8513beda4d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cmarkea\/bloomz-3b-sft-chat", + "Average \u2b06\ufe0f": 36.94, + "ARC": 36.86, + "HellaSwag": 54.34, + "MMLU": 31.49, + "TruthfulQA": 39.69, + "Winogrande": 58.88, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "a35b6ae6809891e253b45fb5795979c33992e548", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIGym\/TinyLlama-1.1B-2.5T-chat", + "Average \u2b06\ufe0f": 36.93, + "ARC": 34.47, + "HellaSwag": 59.71, + "MMLU": 26.45, + "TruthfulQA": 38.8, + "Winogrande": 61.01, + "GSM8K": 1.14, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "17ea96f8da6f61eee63fa430607e3974825a3218", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kevin009\/babyllama-v0.6", + "Average \u2b06\ufe0f": 36.92, + "ARC": 36.09, + "HellaSwag": 61.59, + "MMLU": 25.37, + "TruthfulQA": 35.84, + "Winogrande": 61.01, + "GSM8K": 1.59, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ea9e3e3d79df9769679c5a617ec755359338a425", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azure99\/blossom-v1-3b", + "Average \u2b06\ufe0f": 36.9, + "ARC": 36.86, + "HellaSwag": 55.1, + "MMLU": 26.7, + "TruthfulQA": 43.45, + "Winogrande": 58.88, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3235ee41e3793c98749b7bbd2bb80882a12ac889", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Phind\/Phind-CodeLlama-34B-v2", + "Average \u2b06\ufe0f": 36.89, + "ARC": 24.57, + "HellaSwag": 27.6, + "MMLU": 25.76, + "TruthfulQA": 48.37, + "Winogrande": 71.82, + "GSM8K": 23.2, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 710.0, + "Available on the hub": true, + "Model sha": "949f61e203f91b412efe8f679c798f09f0ff4b0c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "codellama\/CodeLlama-7b-Python-hf", + "Average \u2b06\ufe0f": 36.89, + "ARC": 31.31, + "HellaSwag": 52.86, + "MMLU": 27.32, + "TruthfulQA": 42.21, + "Winogrande": 63.06, + "GSM8K": 4.55, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 107.0, + "Available on the hub": true, + "Model sha": "ec4dd26f30674fdee00ef161b55f464ce28f9c20", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Rallio67\/3B-redpajama-conditional-alpha", + "Average \u2b06\ufe0f": 36.88, + "ARC": 36.26, + "HellaSwag": 61.9, + "MMLU": 25.42, + "TruthfulQA": 36.31, + "Winogrande": 60.77, + "GSM8K": 0.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "7e2156c14b4b7981a4cd6db7b878888a98144df0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "euclaise\/falcon_1b_stage2", + "Average \u2b06\ufe0f": 36.88, + "ARC": 33.11, + "HellaSwag": 63.19, + "MMLU": 24.22, + "TruthfulQA": 38.4, + "Winogrande": 62.35, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "025c77e9ee457c6771c5a36dbacd064c269642a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-2.7B-Nerybus-Mix", + "Average \u2b06\ufe0f": 36.88, + "ARC": 33.7, + "HellaSwag": 61.21, + "MMLU": 26.6, + "TruthfulQA": 37.57, + "Winogrande": 62.04, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "b4131723cfff1fa42f6cbab546c5b4bb0d19fd83", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenBuddy\/openbuddy-openllama-3b-v10-bf16", + "Average \u2b06\ufe0f": 36.87, + "ARC": 36.26, + "HellaSwag": 58.38, + "MMLU": 23.89, + "TruthfulQA": 42.04, + "Winogrande": 59.67, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "7f24d32de53aa4bc150f04ca2418604475173921", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Tinyllama-1.3B-Cinder-Reason-Test-2", + "Average \u2b06\ufe0f": 36.83, + "ARC": 32.76, + "HellaSwag": 57.92, + "MMLU": 25.42, + "TruthfulQA": 37.26, + "Winogrande": 64.8, + "GSM8K": 2.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.28, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3afb28f36d110d6520bb2f08baf40283babf1e9b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "l3utterfly\/tinyllama-1.1b-layla-v1", + "Average \u2b06\ufe0f": 36.82, + "ARC": 34.39, + "HellaSwag": 59.86, + "MMLU": 24.7, + "TruthfulQA": 41.03, + "Winogrande": 59.75, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a12aba8771fb310578d07a76c8666972e3ca21df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Writer\/camel-5b-hf", + "Average \u2b06\ufe0f": 36.81, + "ARC": 35.15, + "HellaSwag": 57.62, + "MMLU": 26.07, + "TruthfulQA": 40.65, + "Winogrande": 61.01, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 5.0, + "Hub \u2764\ufe0f": 108.0, + "Available on the hub": true, + "Model sha": "d1438e22a33b9115af0e47ab3a0fe844cbf588a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "appvoid\/palmer-002", + "Average \u2b06\ufe0f": 36.79, + "ARC": 34.47, + "HellaSwag": 59.41, + "MMLU": 25.94, + "TruthfulQA": 37.06, + "Winogrande": 62.67, + "GSM8K": 1.21, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "8b79b8c2126483baeb3a503c51cd4ffa9d7c11a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TFLai\/pythia-2.8b-4bit-alpaca", + "Average \u2b06\ufe0f": 36.77, + "ARC": 34.73, + "HellaSwag": 58.96, + "MMLU": 25.53, + "TruthfulQA": 39.14, + "Winogrande": 61.64, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 2.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "40e84b6d38aac92a0302c2a682498794ef0fd901", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-2.7B-Nerys-v2", + "Average \u2b06\ufe0f": 36.75, + "ARC": 33.28, + "HellaSwag": 61.23, + "MMLU": 26.44, + "TruthfulQA": 37.23, + "Winogrande": 62.04, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "91d7afd6dbf3bbd1e4ccc6b9a2618d632a8cbb92", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vihangd\/dopeyshearedplats-1.3b-v1", + "Average \u2b06\ufe0f": 36.74, + "ARC": 34.39, + "HellaSwag": 64.31, + "MMLU": 25.4, + "TruthfulQA": 38.21, + "Winogrande": 57.38, + "GSM8K": 0.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "45aa5d406bb6975deb801e5fffa27ca23e5724a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/opt-2.7b", + "Average \u2b06\ufe0f": 36.74, + "ARC": 33.96, + "HellaSwag": 61.43, + "MMLU": 25.43, + "TruthfulQA": 37.43, + "Winogrande": 61.96, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 65.0, + "Available on the hub": true, + "Model sha": "397f71a473a150c00f0fe3fc4a2f78ff3ccaf82d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "L-R\/LLmRa-2.7B", + "Average \u2b06\ufe0f": 36.72, + "ARC": 37.03, + "HellaSwag": 60.65, + "MMLU": 25.58, + "TruthfulQA": 35.23, + "Winogrande": 61.56, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "93201b7d778272fb3252481c1cbd56f726d43e6b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-2.8b-deduped", + "Average \u2b06\ufe0f": 36.72, + "ARC": 36.26, + "HellaSwag": 60.66, + "MMLU": 26.78, + "TruthfulQA": 35.56, + "Winogrande": 60.22, + "GSM8K": 0.83, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.91, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "7d977fed8c4ce9649816af8cd5fe36a639cbe5b2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/chopt-2_7b", + "Average \u2b06\ufe0f": 36.72, + "ARC": 36.01, + "HellaSwag": 63.38, + "MMLU": 25.44, + "TruthfulQA": 37.71, + "Winogrande": 57.77, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "45f57352c10a1fb1ec13c4bf387a15552ca1fe65", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/TinyLlama-MoE-Chat-0.1", + "Average \u2b06\ufe0f": 36.7, + "ARC": 34.39, + "HellaSwag": 56.72, + "MMLU": 29.36, + "TruthfulQA": 37.82, + "Winogrande": 59.67, + "GSM8K": 2.27, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2ebc34217cafbff7812e85fd59c682550bbeb4f8", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "alnrg2arg\/blockchainlabs_tinyllama_fusion_LHK_yunkong_v2", + "Average \u2b06\ufe0f": 36.67, + "ARC": 34.9, + "HellaSwag": 63.11, + "MMLU": 26.75, + "TruthfulQA": 37.33, + "Winogrande": 57.14, + "GSM8K": 0.76, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "374cfd08ccc027f695f045cb4b31794e142769b0", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "danielhanchen\/open_llama_3b_600bt_preview", + "Average \u2b06\ufe0f": 36.65, + "ARC": 36.86, + "HellaSwag": 59.96, + "MMLU": 25.97, + "TruthfulQA": 32.81, + "Winogrande": 63.69, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d8fddf7651dfcae5aefda59d9e868c9111d8bdb3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "42dot\/42dot_LLM-SFT-1.3B", + "Average \u2b06\ufe0f": 36.61, + "ARC": 36.09, + "HellaSwag": 58.96, + "MMLU": 25.51, + "TruthfulQA": 39.98, + "Winogrande": 58.41, + "GSM8K": 0.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 1.44, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": true, + "Model sha": "7474cafe5dc60549c19f89f7c49392a8a32b9199", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "alnrg2arg\/blockchainlabs_tinyllama_fusion_LHK_yunkong", + "Average \u2b06\ufe0f": 36.6, + "ARC": 34.73, + "HellaSwag": 60.41, + "MMLU": 24.96, + "TruthfulQA": 37.45, + "Winogrande": 59.91, + "GSM8K": 2.12, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "90efaf10c2374914063031791059afd1125f1293", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "abhinand\/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft", + "Average \u2b06\ufe0f": 36.59, + "ARC": 33.79, + "HellaSwag": 58.72, + "MMLU": 24.52, + "TruthfulQA": 36.22, + "Winogrande": 60.93, + "GSM8K": 5.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f91c61253e1f80e7a04ee3a002ef6c7681379d42", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "HuggingFaceTB\/cosmo-1b", + "Average \u2b06\ufe0f": 36.59, + "ARC": 38.57, + "HellaSwag": 55.13, + "MMLU": 26.69, + "TruthfulQA": 38.15, + "Winogrande": 55.49, + "GSM8K": 5.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.74, + "Hub \u2764\ufe0f": 82.0, + "Available on the hub": true, + "Model sha": "ffb89c545ae24f7f164e121cf68723a18f5b28c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "PSanni\/Deer-3b", + "Average \u2b06\ufe0f": 36.55, + "ARC": 38.48, + "HellaSwag": 57.41, + "MMLU": 25.64, + "TruthfulQA": 39.98, + "Winogrande": 57.46, + "GSM8K": 0.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "53ea8f8862fc1820f0cd31f62953b7290fd79867", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alexredna\/Tukan-1.1B-Chat-reasoning-sft-COLA", + "Average \u2b06\ufe0f": 36.53, + "ARC": 34.13, + "HellaSwag": 59.78, + "MMLU": 24.86, + "TruthfulQA": 38.25, + "Winogrande": 60.77, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fa129eb7563bc1f8234dc372d6255bec3c3b4143", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "HuggingFaceTB\/cosmo-1b", + "Average \u2b06\ufe0f": 36.52, + "ARC": 38.57, + "HellaSwag": 55.08, + "MMLU": 26.5, + "TruthfulQA": 38.26, + "Winogrande": 55.33, + "GSM8K": 5.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.74, + "Hub \u2764\ufe0f": 82.0, + "Available on the hub": true, + "Model sha": "ffb89c545ae24f7f164e121cf68723a18f5b28c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BEE-spoke-data\/TinyLlama-3T-1.1bee", + "Average \u2b06\ufe0f": 36.46, + "ARC": 33.79, + "HellaSwag": 60.29, + "MMLU": 25.86, + "TruthfulQA": 38.13, + "Winogrande": 60.22, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "eca8e79df61b9872b84df24f61f0d8f0573d383e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "codellama\/CodeLlama-7b-Python-hf", + "Average \u2b06\ufe0f": 36.42, + "ARC": 29.27, + "HellaSwag": 50.12, + "MMLU": 28.37, + "TruthfulQA": 41.61, + "Winogrande": 64.01, + "GSM8K": 5.16, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 107.0, + "Available on the hub": true, + "Model sha": "ec4dd26f30674fdee00ef161b55f464ce28f9c20", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "TinyLlama\/TinyLlama-1.1B-intermediate-step-1431k-3T", + "Average \u2b06\ufe0f": 36.42, + "ARC": 33.87, + "HellaSwag": 60.31, + "MMLU": 26.04, + "TruthfulQA": 37.32, + "Winogrande": 59.51, + "GSM8K": 1.44, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 111.0, + "Available on the hub": true, + "Model sha": "df4c1907f152969ce2850c097e414d79c3a1665a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "ozayezerceli\/TinyLlamax2-1.1b", + "Average \u2b06\ufe0f": 36.42, + "ARC": 33.87, + "HellaSwag": 60.31, + "MMLU": 26.04, + "TruthfulQA": 37.32, + "Winogrande": 59.51, + "GSM8K": 1.44, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "89e5c84a590d840c41ba0ac2147cd6aa517f5320", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/xglm-7.5B", + "Average \u2b06\ufe0f": 36.38, + "ARC": 34.13, + "HellaSwag": 60.77, + "MMLU": 27.79, + "TruthfulQA": 36.66, + "Winogrande": 58.72, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.5, + "Hub \u2764\ufe0f": 53.0, + "Available on the hub": true, + "Model sha": "732d59308a844004bd9a4def972cc7c3896a38e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SanjiWatsuki\/WoolyHermes-1.1B", + "Average \u2b06\ufe0f": 36.37, + "ARC": 34.3, + "HellaSwag": 59.37, + "MMLU": 25.59, + "TruthfulQA": 37.58, + "Winogrande": 59.35, + "GSM8K": 2.05, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "cf2c67039648176ffe45e3ffb9892557a95d3405", + "Flagged": true, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "cognitivecomputations\/TinyDolphin-2.8-1.1b", + "Average \u2b06\ufe0f": 36.34, + "ARC": 34.3, + "HellaSwag": 59.44, + "MMLU": 25.59, + "TruthfulQA": 36.51, + "Winogrande": 60.69, + "GSM8K": 1.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 24.0, + "Available on the hub": true, + "Model sha": "fc3e646d484cf1e48d210b69d7f142f104b996da", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Phind\/Phind-CodeLlama-34B-Python-v1", + "Average \u2b06\ufe0f": 36.33, + "ARC": 24.66, + "HellaSwag": 29.77, + "MMLU": 27.95, + "TruthfulQA": 45.27, + "Winogrande": 68.82, + "GSM8K": 21.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.0, + "Hub \u2764\ufe0f": 245.0, + "Available on the hub": true, + "Model sha": "3aabef8c9bc1b3ec2fffed053645bc1e2d829b6c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/sheared-plus-westlake-50_75p", + "Average \u2b06\ufe0f": 36.31, + "ARC": 34.04, + "HellaSwag": 58.05, + "MMLU": 26.24, + "TruthfulQA": 42.64, + "Winogrande": 56.91, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a0b63698693a3f86d6ba817999d51de850a3fd33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cerebras\/Cerebras-GPT-6.7B", + "Average \u2b06\ufe0f": 36.27, + "ARC": 35.07, + "HellaSwag": 59.36, + "MMLU": 25.93, + "TruthfulQA": 38.02, + "Winogrande": 58.72, + "GSM8K": 0.53, + "Type": "pretrained", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 63.0, + "Available on the hub": true, + "Model sha": "4f56c6e28f9a2a1c470626f1a064238806f19f09", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TinyLlama\/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T", + "Average \u2b06\ufe0f": 36.26, + "ARC": 33.53, + "HellaSwag": 59.38, + "MMLU": 26.22, + "TruthfulQA": 36.79, + "Winogrande": 60.22, + "GSM8K": 1.44, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 44.0, + "Available on the hub": true, + "Model sha": "03978af6c0997cda809de070e056ee5ddb7e7188", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "cognitivecomputations\/TinyDolphin-2.8.1-1.1b", + "Average \u2b06\ufe0f": 36.21, + "ARC": 34.98, + "HellaSwag": 60.11, + "MMLU": 25.31, + "TruthfulQA": 35.51, + "Winogrande": 60.69, + "GSM8K": 0.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "5117b2287bfce3549fc534e16f427cacf521fc7d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/gpt-neo-2.7B", + "Average \u2b06\ufe0f": 36.2, + "ARC": 33.36, + "HellaSwag": 56.24, + "MMLU": 26.45, + "TruthfulQA": 39.78, + "Winogrande": 60.06, + "GSM8K": 1.29, + "Type": "pretrained", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 2.72, + "Hub \u2764\ufe0f": 381.0, + "Available on the hub": true, + "Model sha": "e24fa291132763e59f4a5422741b424fb5d59056", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bertin-project\/bertin-gpt-j-6B-alpaca", + "Average \u2b06\ufe0f": 36.19, + "ARC": 36.01, + "HellaSwag": 54.3, + "MMLU": 27.66, + "TruthfulQA": 43.38, + "Winogrande": 55.8, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "636b17d6044189343475d1889f076aba73036905", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "euclaise\/falcon_1b_stage3_2", + "Average \u2b06\ufe0f": 36.19, + "ARC": 34.56, + "HellaSwag": 58.37, + "MMLU": 23.87, + "TruthfulQA": 39.89, + "Winogrande": 60.46, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aec2f59879ea6dfa5233611c4cf83cf3cb974d40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/sheared-plus-westlake-nearest-50_75p", + "Average \u2b06\ufe0f": 36.18, + "ARC": 36.18, + "HellaSwag": 57.54, + "MMLU": 24.2, + "TruthfulQA": 42.39, + "Winogrande": 56.75, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b3322cdef5234ba6a20928d8aaeee7a9e7c79e2c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Dampish\/StellarX-4B-V0.2", + "Average \u2b06\ufe0f": 36.15, + "ARC": 34.64, + "HellaSwag": 56.74, + "MMLU": 25.55, + "TruthfulQA": 38.55, + "Winogrande": 61.4, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 4.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "605b6812956400dbde24ad7b8649a744a2ddfc8e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigscience\/bloom-3b", + "Average \u2b06\ufe0f": 36.07, + "ARC": 35.75, + "HellaSwag": 54.37, + "MMLU": 26.59, + "TruthfulQA": 40.57, + "Winogrande": 57.62, + "GSM8K": 1.52, + "Type": "pretrained", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 80.0, + "Available on the hub": true, + "Model sha": "52bc5b43010b4844513826b8be3f78c7344c37d7", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ", + "Average \u2b06\ufe0f": 36.06, + "ARC": 29.61, + "HellaSwag": 25.47, + "MMLU": 25.34, + "TruthfulQA": 50.25, + "Winogrande": 75.77, + "GSM8K": 9.93, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 282.0, + "Available on the hub": true, + "Model sha": "d9b00ec47ae3546398432f0693fe2d5d92bf143b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Deacon-1_8b", + "Average \u2b06\ufe0f": 36.03, + "ARC": 33.7, + "HellaSwag": 52.33, + "MMLU": 33.97, + "TruthfulQA": 39.05, + "Winogrande": 57.14, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "77056bdfc4f05eb933a9e9af3af6fe68f89eb0b7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Ba2han\/TinyOpenHermes-1.1B-4k", + "Average \u2b06\ufe0f": 35.98, + "ARC": 33.62, + "HellaSwag": 58.53, + "MMLU": 26.45, + "TruthfulQA": 37.33, + "Winogrande": 59.91, + "GSM8K": 0.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b496ad5f3462828778aa9ec40ec78157f84240e3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Azure99\/blossom-v2-3b", + "Average \u2b06\ufe0f": 35.98, + "ARC": 35.32, + "HellaSwag": 54.1, + "MMLU": 23.99, + "TruthfulQA": 43.11, + "Winogrande": 58.8, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1a403344de52ddb7f18548a526a927714adfe4d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vihangd\/shearedplats-1.3b-v1", + "Average \u2b06\ufe0f": 35.97, + "ARC": 35.41, + "HellaSwag": 62.75, + "MMLU": 24.75, + "TruthfulQA": 33.93, + "Winogrande": 58.48, + "GSM8K": 0.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7ac93152e1807ec1d732500255a747e27922fb1a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "remyxai\/localmentor_25K_3epochs_tinyllama", + "Average \u2b06\ufe0f": 35.96, + "ARC": 34.22, + "HellaSwag": 59.01, + "MMLU": 24.93, + "TruthfulQA": 36.07, + "Winogrande": 60.46, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "670b3f3be7ee5fd09922c033d0fa2d539f98344a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "princeton-nlp\/Sheared-LLaMA-1.3B", + "Average \u2b06\ufe0f": 35.95, + "ARC": 32.85, + "HellaSwag": 60.91, + "MMLU": 25.71, + "TruthfulQA": 37.14, + "Winogrande": 58.64, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 79.0, + "Available on the hub": true, + "Model sha": "b1c3f74c8495e27b3963d64af0781d4a611794f3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/GPT-J-6B-Adventure", + "Average \u2b06\ufe0f": 35.95, + "ARC": 37.12, + "HellaSwag": 61.26, + "MMLU": 25.94, + "TruthfulQA": 34.56, + "Winogrande": 55.96, + "GSM8K": 0.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": false, + "Model sha": "e2c00dc99f986f2430f5d34c0214969cee786755", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "cognitivecomputations\/TinyDolphin-2.8.2-1.1b-laser", + "Average \u2b06\ufe0f": 35.93, + "ARC": 33.36, + "HellaSwag": 58.53, + "MMLU": 25.93, + "TruthfulQA": 36.33, + "Winogrande": 60.14, + "GSM8K": 1.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "471c1ff16a8a78afa702a69f16df98dc14464bf6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ehartford\/CodeLlama-34b-Python-hf", + "Average \u2b06\ufe0f": 35.92, + "ARC": 38.05, + "HellaSwag": 34.79, + "MMLU": 32.96, + "TruthfulQA": 43.57, + "Winogrande": 66.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 33.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "45f38e53a579a2b39298cc57ab04078722bebec0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/TinyLamma-SFT", + "Average \u2b06\ufe0f": 35.88, + "ARC": 34.39, + "HellaSwag": 59.14, + "MMLU": 24.26, + "TruthfulQA": 37.2, + "Winogrande": 58.64, + "GSM8K": 1.67, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4dbfdc67f096a0a801d95c4f4c74cd6dd0c52e1c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "MayaPH\/opt-flan-iml-6.7b", + "Average \u2b06\ufe0f": 35.84, + "ARC": 30.12, + "HellaSwag": 58.82, + "MMLU": 25.12, + "TruthfulQA": 36.74, + "Winogrande": 64.25, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 6.66, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "cbe8d60db6f3c52e653ca73e23a1c34c08127d02", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Tinyllama-1.3B-Cinder-Reason-Test", + "Average \u2b06\ufe0f": 35.84, + "ARC": 32.51, + "HellaSwag": 55.85, + "MMLU": 26.61, + "TruthfulQA": 35.59, + "Winogrande": 62.12, + "GSM8K": 2.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.28, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c747bd4aebbcbe59cd5d9bf5a1b4825a74626f43", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Aryanne\/sheared-silicon10p", + "Average \u2b06\ufe0f": 35.82, + "ARC": 36.18, + "HellaSwag": 51.12, + "MMLU": 25.56, + "TruthfulQA": 44.85, + "Winogrande": 57.22, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "17494d892ed5d6346ebfaf999af697f1310757cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "RWKV\/rwkv-raven-3b", + "Average \u2b06\ufe0f": 35.81, + "ARC": 36.69, + "HellaSwag": 59.78, + "MMLU": 24.87, + "TruthfulQA": 35.6, + "Winogrande": 57.46, + "GSM8K": 0.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "1ddeea6a7313c8ba8824645d7aa88d5449458f67", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigcode\/starcoder", + "Average \u2b06\ufe0f": 35.73, + "ARC": 30.29, + "HellaSwag": 47.88, + "MMLU": 29.47, + "TruthfulQA": 41.3, + "Winogrande": 56.27, + "GSM8K": 9.17, + "Type": "pretrained", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2632.0, + "Available on the hub": true, + "Model sha": "e117ab3b3d0769fd962bd48b099de711757a3d60", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Ba2han\/Tinypus-1.5B", + "Average \u2b06\ufe0f": 35.73, + "ARC": 33.45, + "HellaSwag": 57.35, + "MMLU": 25.53, + "TruthfulQA": 39.35, + "Winogrande": 57.7, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.45, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5bfbd6b5920189dad68217576e0e23be4d2265d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Dans-DiscountModels\/ShearedLlama-1.3b-FFT-Test1", + "Average \u2b06\ufe0f": 35.71, + "ARC": 32.68, + "HellaSwag": 59.99, + "MMLU": 25.69, + "TruthfulQA": 36.97, + "Winogrande": 58.72, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "68e43c006a01764d3ff2bcaeaec5289f2ddad36a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "42dot\/42dot_LLM-PLM-1.3B", + "Average \u2b06\ufe0f": 35.7, + "ARC": 32.42, + "HellaSwag": 56.39, + "MMLU": 27.09, + "TruthfulQA": 38.68, + "Winogrande": 58.88, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 1.44, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "a72bf57eb02cd4ea4388a344b4a5893aa95698da", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "sartmis1\/starcoder-finetune-selfinstruct", + "Average \u2b06\ufe0f": 35.65, + "ARC": 31.23, + "HellaSwag": 47.66, + "MMLU": 29.52, + "TruthfulQA": 41.63, + "Winogrande": 57.77, + "GSM8K": 6.07, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b21bd307ea7417185e7dc59557c399a3e4e0092b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "freecs\/Tiny-Llama-3-7b", + "Average \u2b06\ufe0f": 35.6, + "ARC": 34.64, + "HellaSwag": 56.39, + "MMLU": 24.51, + "TruthfulQA": 38.03, + "Winogrande": 59.67, + "GSM8K": 0.38, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.91, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "778db38d13be6ed3384fa049114a95d56cf420d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "freecs\/Llama-3-7b", + "Average \u2b06\ufe0f": 35.6, + "ARC": 34.64, + "HellaSwag": 56.39, + "MMLU": 24.51, + "TruthfulQA": 38.03, + "Winogrande": 59.67, + "GSM8K": 0.38, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.91, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "778db38d13be6ed3384fa049114a95d56cf420d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "zyh3826\/20231206094523-pretrain-Llama-2-13b-hf-76000", + "Average \u2b06\ufe0f": 35.58, + "ARC": 31.06, + "HellaSwag": 52.03, + "MMLU": 24.43, + "TruthfulQA": 44.71, + "Winogrande": 61.25, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.25, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "28b3ae089b5610053f2294d24667fe248405f031", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "habanoz\/tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1", + "Average \u2b06\ufe0f": 35.58, + "ARC": 32.85, + "HellaSwag": 58.16, + "MMLU": 25.96, + "TruthfulQA": 38.35, + "Winogrande": 57.7, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e55b262cbd0ee52f7a4cbda136dbf1a027987c47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/Cinder-1.3B-Test", + "Average \u2b06\ufe0f": 35.57, + "ARC": 33.19, + "HellaSwag": 55.48, + "MMLU": 26.37, + "TruthfulQA": 36.62, + "Winogrande": 58.96, + "GSM8K": 2.81, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.28, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cf20c861e6ed630c5391640a049b9c4f92748a2b", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/wizard-vicuna-13B-GPTQ", + "Average \u2b06\ufe0f": 35.56, + "ARC": 28.67, + "HellaSwag": 25.94, + "MMLU": 25.84, + "TruthfulQA": 48.53, + "Winogrande": 74.74, + "GSM8K": 9.63, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 100.0, + "Available on the hub": true, + "Model sha": "936a51c0219744d7a9598d0c65a7d18e01660601", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PY007\/TinyLlama-1.1B-Chat-v0.3", + "Average \u2b06\ufe0f": 35.56, + "ARC": 35.07, + "HellaSwag": 57.7, + "MMLU": 25.53, + "TruthfulQA": 36.67, + "Winogrande": 57.7, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "20dd44d78aa09480bf15ca0ecc0c0780951d49a9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigcode\/starcoderbase", + "Average \u2b06\ufe0f": 35.55, + "ARC": 30.29, + "HellaSwag": 47.21, + "MMLU": 32.12, + "TruthfulQA": 40.02, + "Winogrande": 55.8, + "GSM8K": 7.88, + "Type": "pretrained", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 376.0, + "Available on the hub": true, + "Model sha": "88ec5781ad071a9d9e925cd28f327dea22eb5188", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pythainlp\/wangchanglm-7.5B-sft-en-sharded", + "Average \u2b06\ufe0f": 35.55, + "ARC": 34.47, + "HellaSwag": 59.81, + "MMLU": 26.37, + "TruthfulQA": 34.15, + "Winogrande": 58.25, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.5, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dd22eaea8be3fcb8c28f61b513a89d1adac00ffd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "22h\/open-cabrita3b", + "Average \u2b06\ufe0f": 35.54, + "ARC": 33.79, + "HellaSwag": 55.35, + "MMLU": 25.16, + "TruthfulQA": 38.5, + "Winogrande": 59.43, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "fc2a2de94a3b31de54aaace695537c4d1c3e456d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Dans-DiscountModels\/TinyLlama-1.1B-FFT-Test2", + "Average \u2b06\ufe0f": 35.53, + "ARC": 34.22, + "HellaSwag": 57.96, + "MMLU": 25.54, + "TruthfulQA": 36.32, + "Winogrande": 58.8, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dfedea2fbf66c27c88cd4b2eeb0ff0f5041e3b59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dball\/zephyr-tiny-sft-qlora-quantized-2", + "Average \u2b06\ufe0f": 35.53, + "ARC": 33.19, + "HellaSwag": 58.58, + "MMLU": 25.21, + "TruthfulQA": 35.82, + "Winogrande": 58.8, + "GSM8K": 1.59, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "effd86f3284e6472f1a865a208ee68900e9f7318", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "HuggingFaceH4\/starchat-alpha", + "Average \u2b06\ufe0f": 35.49, + "ARC": 31.57, + "HellaSwag": 49.43, + "MMLU": 30.76, + "TruthfulQA": 43.66, + "Winogrande": 55.09, + "GSM8K": 2.43, + "Type": "", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 15.52, + "Hub \u2764\ufe0f": 226.0, + "Available on the hub": true, + "Model sha": "b693a7a7d52bed1cd7cc0fe00399db838b09c74f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bhenrym14\/airoboros-33b-gpt4-1.4.1-PI-8192-fp16", + "Average \u2b06\ufe0f": 35.46, + "ARC": 32.0, + "HellaSwag": 53.88, + "MMLU": 31.43, + "TruthfulQA": 38.59, + "Winogrande": 56.83, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "1dd7804dbbb547c1be852652ce74568ba41d4e73", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AtAndDev\/ShortKingv0.1", + "Average \u2b06\ufe0f": 35.45, + "ARC": 34.22, + "HellaSwag": 54.59, + "MMLU": 25.78, + "TruthfulQA": 41.64, + "Winogrande": 56.04, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6cd9b5bc13ee15b5e7e7cfb46477bc6a7c0b5d47", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "habanoz\/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-2.2epochs-oasst1-top1-instruct-V1", + "Average \u2b06\ufe0f": 35.45, + "ARC": 31.48, + "HellaSwag": 54.4, + "MMLU": 25.47, + "TruthfulQA": 42.34, + "Winogrande": 57.54, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "74cd9eba94e77832b3081689fc5c99c37c063790", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nnpy\/Nape-0", + "Average \u2b06\ufe0f": 35.43, + "ARC": 32.68, + "HellaSwag": 58.68, + "MMLU": 24.88, + "TruthfulQA": 38.99, + "Winogrande": 57.3, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "47e07bd518b989890a7f694d39e2772e703384c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lizhuang144\/starcoder_mirror", + "Average \u2b06\ufe0f": 35.43, + "ARC": 31.31, + "HellaSwag": 45.82, + "MMLU": 29.29, + "TruthfulQA": 43.38, + "Winogrande": 57.22, + "GSM8K": 5.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eb5f39bac15ccab9463001aa203e33d49f4ff7cb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "habanoz\/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1", + "Average \u2b06\ufe0f": 35.42, + "ARC": 31.4, + "HellaSwag": 54.24, + "MMLU": 25.36, + "TruthfulQA": 42.47, + "Winogrande": 57.7, + "GSM8K": 1.36, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b1ec2a1e08eb790b9a32a43053316650921af943", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/openchat_v2_openorca_preview-GPTQ", + "Average \u2b06\ufe0f": 35.38, + "ARC": 27.99, + "HellaSwag": 26.06, + "MMLU": 24.24, + "TruthfulQA": 50.08, + "Winogrande": 70.64, + "GSM8K": 13.27, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "5a4c2ea612b71d7c00118f796db7189bc1a0c930", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/chopt-1_3b", + "Average \u2b06\ufe0f": 35.32, + "ARC": 31.48, + "HellaSwag": 56.63, + "MMLU": 25.35, + "TruthfulQA": 40.19, + "Winogrande": 58.25, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fdd3691978f557baf9d1c20d4ede900c47f7e135", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Walter-Llama-1B", + "Average \u2b06\ufe0f": 35.29, + "ARC": 32.85, + "HellaSwag": 61.05, + "MMLU": 27.46, + "TruthfulQA": 33.93, + "Winogrande": 56.43, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ae782b5a37bc961d0860e6a8edb10547bb5285d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vihangd\/dopeyplats-1.1b-2T-v1", + "Average \u2b06\ufe0f": 35.28, + "ARC": 33.11, + "HellaSwag": 54.31, + "MMLU": 24.55, + "TruthfulQA": 39.26, + "Winogrande": 58.8, + "GSM8K": 1.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "4ca47b470296de0e7bf3261e377aabaff9ad5c06", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "habanoz\/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-4epochs-oasst1-top1-instruct-V1", + "Average \u2b06\ufe0f": 35.28, + "ARC": 31.14, + "HellaSwag": 54.31, + "MMLU": 25.42, + "TruthfulQA": 41.72, + "Winogrande": 57.77, + "GSM8K": 1.29, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "7cd6d5ad10180127771e4326772eae3d40fa8445", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/TinyLlama-3T-Cinder-v1.2", + "Average \u2b06\ufe0f": 35.26, + "ARC": 34.39, + "HellaSwag": 56.51, + "MMLU": 26.14, + "TruthfulQA": 36.78, + "Winogrande": 57.7, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "15c3d37d6d0a6ec7294ce9b5c84851b739f47508", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "RWKV\/rwkv-4-3b-pile", + "Average \u2b06\ufe0f": 35.25, + "ARC": 36.01, + "HellaSwag": 59.66, + "MMLU": 24.67, + "TruthfulQA": 32.14, + "Winogrande": 58.33, + "GSM8K": 0.68, + "Type": "pretrained", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "7fdda3c5570d4a9711f8f02cc3a20941a5623cd3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/platypus-1_8b", + "Average \u2b06\ufe0f": 35.24, + "ARC": 33.28, + "HellaSwag": 50.76, + "MMLU": 33.25, + "TruthfulQA": 40.73, + "Winogrande": 52.96, + "GSM8K": 0.45, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.84, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "688223a26ae6c3f6102bc3f524594cf21ebb752a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beberik\/TinyExperts-v0-4x1B", + "Average \u2b06\ufe0f": 35.23, + "ARC": 31.4, + "HellaSwag": 52.29, + "MMLU": 25.87, + "TruthfulQA": 41.13, + "Winogrande": 60.14, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 2.62, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cf8144d3b97b9f0154d0a84be2ee758cc60ca33c", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Deacon-1b", + "Average \u2b06\ufe0f": 35.21, + "ARC": 32.42, + "HellaSwag": 58.62, + "MMLU": 24.89, + "TruthfulQA": 35.05, + "Winogrande": 59.59, + "GSM8K": 0.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "77f16fd4c605fe043033d4335024fb887cedef69", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "facebook\/opt-iml-max-1.3b", + "Average \u2b06\ufe0f": 35.21, + "ARC": 30.72, + "HellaSwag": 53.81, + "MMLU": 27.61, + "TruthfulQA": 38.34, + "Winogrande": 60.22, + "GSM8K": 0.53, + "Type": "", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 40.0, + "Available on the hub": true, + "Model sha": "d60fa58f50def19751da2075791da359ca19d273", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Writer\/palmyra-base", + "Average \u2b06\ufe0f": 35.18, + "ARC": 31.91, + "HellaSwag": 55.39, + "MMLU": 27.15, + "TruthfulQA": 37.57, + "Winogrande": 58.09, + "GSM8K": 0.99, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 40.0, + "Available on the hub": true, + "Model sha": "df2f3bdb7cbe4295d69cf0cbc35f3ceaf451de82", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/wizard-mega-13B-GPTQ", + "Average \u2b06\ufe0f": 35.18, + "ARC": 27.73, + "HellaSwag": 26.01, + "MMLU": 24.97, + "TruthfulQA": 48.69, + "Winogrande": 74.74, + "GSM8K": 8.95, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 105.0, + "Available on the hub": true, + "Model sha": "848bf2514f804799dd28c188e5428d497dc983fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/fairseq-dense-1.3B", + "Average \u2b06\ufe0f": 35.16, + "ARC": 31.14, + "HellaSwag": 58.39, + "MMLU": 24.98, + "TruthfulQA": 37.43, + "Winogrande": 59.04, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 1.41, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": false, + "Model sha": "20bf1732212ea81adb45b782a25ce69e65a01ad2", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/chronos-wizardlm-uc-scot-st-13B-GPTQ", + "Average \u2b06\ufe0f": 35.15, + "ARC": 27.99, + "HellaSwag": 26.1, + "MMLU": 25.72, + "TruthfulQA": 49.68, + "Winogrande": 74.51, + "GSM8K": 6.9, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "c4246e4b8d3fc77b9fe4ebb1ead61cda4b83575b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/TinyWand-DPO", + "Average \u2b06\ufe0f": 35.13, + "ARC": 31.66, + "HellaSwag": 50.42, + "MMLU": 26.22, + "TruthfulQA": 45.8, + "Winogrande": 54.78, + "GSM8K": 1.9, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.63, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7bf42524d664785d92243576b1f7d3b3ed463819", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HWERI\/pythia-1.4b-deduped-sharegpt", + "Average \u2b06\ufe0f": 35.11, + "ARC": 34.3, + "HellaSwag": 54.49, + "MMLU": 24.0, + "TruthfulQA": 41.81, + "Winogrande": 55.25, + "GSM8K": 0.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.42, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5b50336208840f557ef3301d841e7994caaa63bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beaugogh\/pythia-1.4b-deduped-sharegpt", + "Average \u2b06\ufe0f": 35.11, + "ARC": 34.3, + "HellaSwag": 54.49, + "MMLU": 24.0, + "TruthfulQA": 41.81, + "Winogrande": 55.25, + "GSM8K": 0.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "03dfdc25c111a6a4a16d3da12190697611936426", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pythainlp\/wangchanglm-7.5B-sft-enth", + "Average \u2b06\ufe0f": 35.11, + "ARC": 33.79, + "HellaSwag": 58.99, + "MMLU": 24.52, + "TruthfulQA": 34.9, + "Winogrande": 57.93, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.5, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "eeee33ea6778a5e66184eeb4bf4294d4316b1933", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PygmalionAI\/metharme-1.3b", + "Average \u2b06\ufe0f": 35.04, + "ARC": 34.39, + "HellaSwag": 55.94, + "MMLU": 25.07, + "TruthfulQA": 37.68, + "Winogrande": 56.43, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.52, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": true, + "Model sha": "62ec4ff53042f692ef0661e54f371747214707a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/falcon-1b-t-sft", + "Average \u2b06\ufe0f": 35.02, + "ARC": 32.94, + "HellaSwag": 57.24, + "MMLU": 25.26, + "TruthfulQA": 38.49, + "Winogrande": 55.88, + "GSM8K": 0.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3b891a0c37f8fa98301c85fcf34baae876e4cac1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "L-R\/LLmRa-1.3B", + "Average \u2b06\ufe0f": 35.0, + "ARC": 32.68, + "HellaSwag": 58.77, + "MMLU": 23.23, + "TruthfulQA": 36.21, + "Winogrande": 59.04, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8d5e8bb336cb886e20a7570bc00c2381792338a5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-1.4b-deduped", + "Average \u2b06\ufe0f": 35.0, + "ARC": 32.68, + "HellaSwag": 54.96, + "MMLU": 25.56, + "TruthfulQA": 38.66, + "Winogrande": 57.3, + "GSM8K": 0.83, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.4, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "77f320b24ccae4aa85a5890dbb9514bd11267bb3", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "habanoz\/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-1epch-airoboros3.1-1k-instruct-V1", + "Average \u2b06\ufe0f": 34.98, + "ARC": 30.72, + "HellaSwag": 54.32, + "MMLU": 24.78, + "TruthfulQA": 41.67, + "Winogrande": 57.62, + "GSM8K": 0.76, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2b961bacab9fcd4bf9a0d6979b024fe23f61555e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "euclaise\/falcon_1b_stage3", + "Average \u2b06\ufe0f": 34.95, + "ARC": 33.11, + "HellaSwag": 54.08, + "MMLU": 25.11, + "TruthfulQA": 37.92, + "Winogrande": 59.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "593e48197e91537b203ba288260f6580b9cbcbe6", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TinyLlama\/TinyLlama-1.1B-Chat-v0.6", + "Average \u2b06\ufe0f": 34.94, + "ARC": 31.66, + "HellaSwag": 55.79, + "MMLU": 25.98, + "TruthfulQA": 34.72, + "Winogrande": 59.35, + "GSM8K": 2.12, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 60.0, + "Available on the hub": true, + "Model sha": "bf9ae1c8bf026667e6f810768de259bb4a7f4777", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Deathsquad10\/TinyLlama-1.1B-Remix-V.2", + "Average \u2b06\ufe0f": 34.91, + "ARC": 33.19, + "HellaSwag": 56.62, + "MMLU": 25.99, + "TruthfulQA": 34.64, + "Winogrande": 58.09, + "GSM8K": 0.91, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d60a0c010610de653e55fe498585a44a7202c8b1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "OpenAssistant\/stablelm-7b-sft-v7-epoch-3", + "Average \u2b06\ufe0f": 34.85, + "ARC": 36.01, + "HellaSwag": 55.81, + "MMLU": 25.01, + "TruthfulQA": 37.02, + "Winogrande": 54.85, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 66.0, + "Available on the hub": false, + "Model sha": "4c454bfc0e3618b3d574e28ba71369607e637e91", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Jiayi-Pan\/Tiny-Vicuna-1B", + "Average \u2b06\ufe0f": 34.76, + "ARC": 33.45, + "HellaSwag": 55.92, + "MMLU": 25.45, + "TruthfulQA": 33.82, + "Winogrande": 58.41, + "GSM8K": 1.52, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "175336a0000f36b508575ef1a2da05755faf48c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "w95\/megachat", + "Average \u2b06\ufe0f": 34.75, + "ARC": 30.8, + "HellaSwag": 54.35, + "MMLU": 25.55, + "TruthfulQA": 39.85, + "Winogrande": 56.99, + "GSM8K": 0.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "789b259a18ca7b168ced4995138ad6195cd2e8e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "tyson0420\/mixtral_stack_llama", + "Average \u2b06\ufe0f": 34.74, + "ARC": 34.56, + "HellaSwag": 50.24, + "MMLU": 27.97, + "TruthfulQA": 38.22, + "Winogrande": 57.3, + "GSM8K": 0.15, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 11.07, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b231bdee0dea526b0d7b6df2a182ab1cd224f8eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MBZUAI\/lamini-neo-1.3b", + "Average \u2b06\ufe0f": 34.73, + "ARC": 32.76, + "HellaSwag": 49.13, + "MMLU": 28.79, + "TruthfulQA": 41.05, + "Winogrande": 56.51, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a5c7ecc4d908e7a9469d080308af64ae775c733d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MBZUAI\/LaMini-GPT-1.5B", + "Average \u2b06\ufe0f": 34.67, + "ARC": 31.4, + "HellaSwag": 48.38, + "MMLU": 29.92, + "TruthfulQA": 42.47, + "Winogrande": 55.88, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 1.5, + "Hub \u2764\ufe0f": 35.0, + "Available on the hub": true, + "Model sha": "88ca6f5abe2335bac317e82684e574afdd6046b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt1.3b_10e4", + "Average \u2b06\ufe0f": 34.67, + "ARC": 30.55, + "HellaSwag": 53.52, + "MMLU": 26.89, + "TruthfulQA": 38.67, + "Winogrande": 58.41, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "722619c9735f29fab37c181bc9d2f6178391dc82", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WizardLM\/WizardCoder-15B-V1.0", + "Average \u2b06\ufe0f": 34.64, + "ARC": 32.34, + "HellaSwag": 47.2, + "MMLU": 29.43, + "TruthfulQA": 41.56, + "Winogrande": 55.17, + "GSM8K": 2.12, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-openrail-m", + "#Params (B)": 15.0, + "Hub \u2764\ufe0f": 717.0, + "Available on the hub": true, + "Model sha": "926ca1b215c4631bc5f8c3e47173381452c23e5c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bn22\/tinyllama_frankenmerge", + "Average \u2b06\ufe0f": 34.64, + "ARC": 30.2, + "HellaSwag": 51.01, + "MMLU": 26.11, + "TruthfulQA": 40.18, + "Winogrande": 58.72, + "GSM8K": 1.59, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "086cd453c6d72be4960b6ff15fa5c97dc47993cc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "maywell\/TinyWand-SFT", + "Average \u2b06\ufe0f": 34.61, + "ARC": 31.4, + "HellaSwag": 49.96, + "MMLU": 25.98, + "TruthfulQA": 43.08, + "Winogrande": 55.17, + "GSM8K": 2.05, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.63, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "ac1dffae8e8a8324fdac7a266a8ce82e6d033577", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "facebook\/opt-1.3b", + "Average \u2b06\ufe0f": 34.6, + "ARC": 29.52, + "HellaSwag": 54.53, + "MMLU": 24.96, + "TruthfulQA": 38.71, + "Winogrande": 59.75, + "GSM8K": 0.15, + "Type": "", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 134.0, + "Available on the hub": true, + "Model sha": "8c7b10754972749675d22364c25c428b29face51", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "0x7194633\/fialka-13B-v3", + "Average \u2b06\ufe0f": 34.58, + "ARC": 30.97, + "HellaSwag": 48.83, + "MMLU": 26.36, + "TruthfulQA": 40.58, + "Winogrande": 59.43, + "GSM8K": 1.29, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "81bde04594320c0e8174644be352a98c7b073a88", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PY007\/TinyLlama-1.1B-Chat-v0.1", + "Average \u2b06\ufe0f": 34.57, + "ARC": 32.0, + "HellaSwag": 54.21, + "MMLU": 26.71, + "TruthfulQA": 39.03, + "Winogrande": 54.93, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7abc14e7779eabc3a028bc695342869d0410dea2", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TinyLlama\/TinyLlama-1.1B-intermediate-step-955k-token-2T", + "Average \u2b06\ufe0f": 34.56, + "ARC": 30.29, + "HellaSwag": 54.84, + "MMLU": 26.47, + "TruthfulQA": 36.07, + "Winogrande": 58.33, + "GSM8K": 1.36, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "f62ecb34ea0d4acea9d896040a4616a9538e2f36", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "AI-Sweden-Models\/gpt-sw3-1.3b-instruct", + "Average \u2b06\ufe0f": 34.54, + "ARC": 30.97, + "HellaSwag": 51.42, + "MMLU": 26.17, + "TruthfulQA": 40.31, + "Winogrande": 56.75, + "GSM8K": 1.59, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.44, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "5f2f03167dedc59192ee02694e07424a890d9206", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "habanoz\/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1", + "Average \u2b06\ufe0f": 34.53, + "ARC": 31.06, + "HellaSwag": 55.02, + "MMLU": 26.41, + "TruthfulQA": 35.08, + "Winogrande": 58.01, + "GSM8K": 1.59, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "586c223b539e05fd8a63733c6a540f292460e639", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bhenrym14\/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16", + "Average \u2b06\ufe0f": 34.53, + "ARC": 25.34, + "HellaSwag": 26.66, + "MMLU": 23.36, + "TruthfulQA": 49.51, + "Winogrande": 73.72, + "GSM8K": 8.57, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 32.53, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "468225a547a8cb0a62758d813cf9606b58506ab4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/tinyllama-1.1b-chat-v0.3_platypus", + "Average \u2b06\ufe0f": 34.5, + "ARC": 30.29, + "HellaSwag": 55.12, + "MMLU": 26.13, + "TruthfulQA": 39.15, + "Winogrande": 55.8, + "GSM8K": 0.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "0bb6ebe1d41d394bae0ed9107ec8d776d9d76a68", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-1.3b", + "Average \u2b06\ufe0f": 34.46, + "ARC": 31.14, + "HellaSwag": 51.43, + "MMLU": 26.55, + "TruthfulQA": 39.24, + "Winogrande": 57.38, + "GSM8K": 0.99, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "34b668ff0acfe56f2d541aa46b385557ee39eb3f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "NYTK\/PULI-GPTrio", + "Average \u2b06\ufe0f": 34.42, + "ARC": 30.72, + "HellaSwag": 53.49, + "MMLU": 24.73, + "TruthfulQA": 39.03, + "Winogrande": 57.77, + "GSM8K": 0.76, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "c85efce322a0f6d93d64f7b9096525753da6913e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "gpt2-xl", + "Average \u2b06\ufe0f": 34.38, + "ARC": 30.29, + "HellaSwag": 51.36, + "MMLU": 26.54, + "TruthfulQA": 38.54, + "Winogrande": 58.25, + "GSM8K": 1.29, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "33cdb5c0db5423c1879b1b9f16c352988e8754a8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "PY007\/TinyLlama-1.1B-intermediate-step-480k-1T", + "Average \u2b06\ufe0f": 34.37, + "ARC": 30.89, + "HellaSwag": 52.97, + "MMLU": 25.0, + "TruthfulQA": 39.55, + "Winogrande": 57.3, + "GSM8K": 0.53, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "098830e58452a0a08f90eb0189ec5925803fd48b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/EverythingLM-13B-16K-GPTQ", + "Average \u2b06\ufe0f": 34.37, + "ARC": 29.27, + "HellaSwag": 26.24, + "MMLU": 25.4, + "TruthfulQA": 48.58, + "Winogrande": 71.35, + "GSM8K": 5.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 16.23, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "f14d3df05577f3e1ac35e2c4ec32ce0d39b97508", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "stabilityai\/stablelm-base-alpha-7b", + "Average \u2b06\ufe0f": 34.37, + "ARC": 32.0, + "HellaSwag": 51.78, + "MMLU": 26.21, + "TruthfulQA": 40.19, + "Winogrande": 55.41, + "GSM8K": 0.61, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 210.0, + "Available on the hub": true, + "Model sha": "38366357b5a45e002af2d254ff3d559444ec2147", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "h2oai\/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt", + "Average \u2b06\ufe0f": 34.32, + "ARC": 34.04, + "HellaSwag": 50.51, + "MMLU": 24.66, + "TruthfulQA": 41.8, + "Winogrande": 54.93, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "754e0c90ed5d9241fdfd5a188572b3ea2152eaa7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/xglm-4.5B", + "Average \u2b06\ufe0f": 34.31, + "ARC": 31.48, + "HellaSwag": 57.95, + "MMLU": 25.43, + "TruthfulQA": 35.84, + "Winogrande": 54.93, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 5.08, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "dc6a67fac06c8bca7860b84656a0cb736293a7a8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AI-Sweden-Models\/gpt-sw3-1.3b", + "Average \u2b06\ufe0f": 34.31, + "ARC": 30.38, + "HellaSwag": 50.4, + "MMLU": 26.14, + "TruthfulQA": 39.97, + "Winogrande": 58.88, + "GSM8K": 0.08, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.44, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "b0d9545a27cfaf9a937adac72ed6953f2dc597de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "winglian\/llama-2-4b", + "Average \u2b06\ufe0f": 34.23, + "ARC": 31.23, + "HellaSwag": 53.29, + "MMLU": 24.22, + "TruthfulQA": 38.72, + "Winogrande": 57.46, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 4.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "fbba77f9894cf738ad8d7d08fc6874856fb42507", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "L-R\/LLmRa-1.3B_V2", + "Average \u2b06\ufe0f": 34.21, + "ARC": 30.46, + "HellaSwag": 53.03, + "MMLU": 26.06, + "TruthfulQA": 36.46, + "Winogrande": 59.27, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a760ebda8f736988eafea879173c5be468ea68d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/dlite-v2-1_5b", + "Average \u2b06\ufe0f": 34.2, + "ARC": 32.59, + "HellaSwag": 53.98, + "MMLU": 24.93, + "TruthfulQA": 38.77, + "Winogrande": 54.7, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 5.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "97440ff1b6ef749423758e3495cdce1b5e68ee92", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LoupGarou\/WizardCoder-Guanaco-15B-V1.1", + "Average \u2b06\ufe0f": 34.19, + "ARC": 32.59, + "HellaSwag": 45.42, + "MMLU": 25.88, + "TruthfulQA": 42.33, + "Winogrande": 56.04, + "GSM8K": 2.88, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": [ + "apache-2.0" + ], + "#Params (B)": 15.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "979531c84ec0b4e1712d6a5cec6907126a21e605", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "0x7194633\/fialka-13B-v4", + "Average \u2b06\ufe0f": 34.18, + "ARC": 29.69, + "HellaSwag": 47.37, + "MMLU": 25.09, + "TruthfulQA": 43.65, + "Winogrande": 58.88, + "GSM8K": 0.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ca8208bc78cdce0be47f8726926b242961fd0c07", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "GeorgiaTechResearchInstitute\/starcoder-gpteacher-code-instruct", + "Average \u2b06\ufe0f": 34.15, + "ARC": 32.68, + "HellaSwag": 47.6, + "MMLU": 28.63, + "TruthfulQA": 40.41, + "Winogrande": 55.56, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 77.0, + "Available on the hub": true, + "Model sha": "d866b68daa719239dc44979dbf39a608ed6f7bce", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/gpt2-xl_lima", + "Average \u2b06\ufe0f": 34.12, + "ARC": 31.14, + "HellaSwag": 51.28, + "MMLU": 25.43, + "TruthfulQA": 38.74, + "Winogrande": 57.22, + "GSM8K": 0.91, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.56, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f7db5b1db521abd7578b95138e737637e0037ca5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "0x7194633\/fialka-13B-v3.1", + "Average \u2b06\ufe0f": 34.11, + "ARC": 29.95, + "HellaSwag": 47.28, + "MMLU": 25.41, + "TruthfulQA": 43.03, + "Winogrande": 58.48, + "GSM8K": 0.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5d7ce7a375b6641a133485c47542d522d7096f2e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/Walter-Falcon-1B", + "Average \u2b06\ufe0f": 34.07, + "ARC": 31.06, + "HellaSwag": 54.92, + "MMLU": 24.58, + "TruthfulQA": 38.47, + "Winogrande": 55.41, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "9cc302810282152eea488e8649e45dbc332313e3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "habanoz\/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1", + "Average \u2b06\ufe0f": 34.04, + "ARC": 30.55, + "HellaSwag": 53.7, + "MMLU": 26.07, + "TruthfulQA": 35.85, + "Winogrande": 58.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "152436a0dd6ca1603b3993bbf08a227ea131f85d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "stabilityai\/stablelm-tuned-alpha-7b", + "Average \u2b06\ufe0f": 34.04, + "ARC": 31.91, + "HellaSwag": 53.59, + "MMLU": 24.41, + "TruthfulQA": 40.37, + "Winogrande": 53.12, + "GSM8K": 0.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 357.0, + "Available on the hub": true, + "Model sha": "25071b093c15c0d1cb2b2876c6deb621b764fcf5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/TinyLlama-3T-Cinder-v1.1", + "Average \u2b06\ufe0f": 34.03, + "ARC": 34.04, + "HellaSwag": 50.4, + "MMLU": 25.75, + "TruthfulQA": 37.57, + "Winogrande": 56.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1f1bc965140150b7c7a5012abe1e0e0fcce93d68", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Deathsquad10\/TinyLlama-Remix", + "Average \u2b06\ufe0f": 34.0, + "ARC": 31.14, + "HellaSwag": 49.5, + "MMLU": 27.34, + "TruthfulQA": 40.53, + "Winogrande": 55.41, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e5ba81a66f14d23a72053b2d6bdcd31c111d81ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "jzjiao\/opt-1.3b-rlhf", + "Average \u2b06\ufe0f": 33.99, + "ARC": 28.92, + "HellaSwag": 52.77, + "MMLU": 25.39, + "TruthfulQA": 37.44, + "Winogrande": 58.96, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5b12df71b21b6b7d76ca9d56de6751f25022e854", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "bigscience\/bloom-1b7", + "Average \u2b06\ufe0f": 33.98, + "ARC": 30.63, + "HellaSwag": 47.6, + "MMLU": 27.48, + "TruthfulQA": 41.31, + "Winogrande": 56.04, + "GSM8K": 0.83, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 1.72, + "Hub \u2764\ufe0f": 105.0, + "Available on the hub": true, + "Model sha": "cc72a88036c2fb937d65efeacc57a0c2ef5d6fe5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PygmalionAI\/pygmalion-2.7b", + "Average \u2b06\ufe0f": 33.98, + "ARC": 32.76, + "HellaSwag": 54.13, + "MMLU": 23.28, + "TruthfulQA": 37.17, + "Winogrande": 56.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "creativeml-openrail-m", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 50.0, + "Available on the hub": true, + "Model sha": "9533805293bc48e8ddfe9dc1940d8cbc5662113e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LoupGarou\/WizardCoder-Guanaco-15B-V1.0", + "Average \u2b06\ufe0f": 33.96, + "ARC": 30.46, + "HellaSwag": 45.59, + "MMLU": 26.79, + "TruthfulQA": 46.39, + "Winogrande": 53.12, + "GSM8K": 1.44, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": [ + "apache-2.0" + ], + "#Params (B)": 15.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "ab5ea678d63eb2324658dcc8cfae267eabc366ef", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "golaxy\/gogpt-3b-bloom", + "Average \u2b06\ufe0f": 33.96, + "ARC": 31.91, + "HellaSwag": 50.32, + "MMLU": 25.2, + "TruthfulQA": 41.79, + "Winogrande": 54.38, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "fe942d5d0faca8156eaf456ecdf569993eab8062", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/gpt-2-xl_camel-ai-physics", + "Average \u2b06\ufe0f": 33.96, + "ARC": 29.52, + "HellaSwag": 50.62, + "MMLU": 26.79, + "TruthfulQA": 39.12, + "Winogrande": 57.54, + "GSM8K": 0.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.56, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e20cf5a8c89441f4dc15fd2af12dbe72b7df8e60", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt1.3b_10e5", + "Average \u2b06\ufe0f": 33.8, + "ARC": 29.52, + "HellaSwag": 52.81, + "MMLU": 25.61, + "TruthfulQA": 38.18, + "Winogrande": 56.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "58d5814c99392194b9d7a5ef7c2c4023eb75934e", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-GPTQ", + "Average \u2b06\ufe0f": 33.78, + "ARC": 28.41, + "HellaSwag": 26.05, + "MMLU": 24.71, + "TruthfulQA": 49.54, + "Winogrande": 68.67, + "GSM8K": 5.31, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 35.58, + "Hub \u2764\ufe0f": 78.0, + "Available on the hub": true, + "Model sha": "cd07cc7c55b46524f61214012653c25226d24c0d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigcode\/starcoderbase-7b", + "Average \u2b06\ufe0f": 33.75, + "ARC": 29.86, + "HellaSwag": 43.87, + "MMLU": 28.45, + "TruthfulQA": 40.46, + "Winogrande": 54.38, + "GSM8K": 5.46, + "Type": "pretrained", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 28.0, + "Available on the hub": true, + "Model sha": "4ab631381edb607557cbb04b6e9a225bad16807c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "PY007\/TinyLlama-1.1B-intermediate-step-240k-503b", + "Average \u2b06\ufe0f": 33.72, + "ARC": 29.27, + "HellaSwag": 49.71, + "MMLU": 26.26, + "TruthfulQA": 40.17, + "Winogrande": 56.59, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "213ebf60d7fdd3258fa5574840b06c97a7e8cf5d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/gpt-neo-1.3B", + "Average \u2b06\ufe0f": 33.58, + "ARC": 31.23, + "HellaSwag": 48.47, + "MMLU": 24.82, + "TruthfulQA": 39.63, + "Winogrande": 56.91, + "GSM8K": 0.45, + "Type": "pretrained", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.37, + "Hub \u2764\ufe0f": 227.0, + "Available on the hub": true, + "Model sha": "8282180b53cba30a1575e49de1530019e5931739", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_opt1.3b_10e5", + "Average \u2b06\ufe0f": 33.57, + "ARC": 29.44, + "HellaSwag": 51.7, + "MMLU": 25.38, + "TruthfulQA": 36.87, + "Winogrande": 58.01, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9aeaed5981224761a1cf0840da1761948881f8cb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "RWKV\/rwkv-raven-1b5", + "Average \u2b06\ufe0f": 33.56, + "ARC": 31.83, + "HellaSwag": 52.6, + "MMLU": 25.96, + "TruthfulQA": 37.09, + "Winogrande": 53.91, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": false, + "Model sha": "571a3bd891ce33f2ee3fc6de09218178edb0dae2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "lxe\/Cerebras-GPT-2.7B-Alpaca-SP", + "Average \u2b06\ufe0f": 33.5, + "ARC": 30.8, + "HellaSwag": 48.88, + "MMLU": 25.12, + "TruthfulQA": 40.24, + "Winogrande": 55.41, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "ae7f22e90cb968b0a73355aa2001d6bc7df28477", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "postbot\/gpt-neo-1.3B-emailgen", + "Average \u2b06\ufe0f": 33.47, + "ARC": 29.95, + "HellaSwag": 47.95, + "MMLU": 24.11, + "TruthfulQA": 42.55, + "Winogrande": 56.27, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "accdf0e43c0d1b313bc6d1fb307d67f1921ef3ca", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/TinyLlama-3T-Cinder-v1", + "Average \u2b06\ufe0f": 33.47, + "ARC": 33.53, + "HellaSwag": 46.36, + "MMLU": 26.03, + "TruthfulQA": 38.32, + "Winogrande": 56.59, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "52ccb7253aaa88f675ff117917d541ec7e49d56d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BEE-spoke-data\/TinyLlama-1.1bee", + "Average \u2b06\ufe0f": 33.38, + "ARC": 30.55, + "HellaSwag": 51.8, + "MMLU": 24.25, + "TruthfulQA": 39.01, + "Winogrande": 54.46, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5889ec467cf80a83c4092b55686f8121e81bf001", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "l3utterfly\/llama2-3b-distilled-layla-v1", + "Average \u2b06\ufe0f": 33.36, + "ARC": 30.46, + "HellaSwag": 46.05, + "MMLU": 23.91, + "TruthfulQA": 42.14, + "Winogrande": 57.38, + "GSM8K": 0.23, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1ba0a65e5262bc134dbc562a9faf80865b0a72f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/dlite-v1-1_5b", + "Average \u2b06\ufe0f": 33.35, + "ARC": 31.66, + "HellaSwag": 49.69, + "MMLU": 25.62, + "TruthfulQA": 37.08, + "Winogrande": 55.96, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 5.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4ac21faec255e3544e96aeb3591c27bdee5ebf45", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/polyglot-ko-12.8b", + "Average \u2b06\ufe0f": 33.33, + "ARC": 27.05, + "HellaSwag": 51.68, + "MMLU": 26.64, + "TruthfulQA": 34.69, + "Winogrande": 59.75, + "GSM8K": 0.15, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.06, + "Hub \u2764\ufe0f": 73.0, + "Available on the hub": true, + "Model sha": "09dfc839067bf44e7f52976eca8adbc17f04e1b0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MrNJK\/gpt2-xl-sft", + "Average \u2b06\ufe0f": 33.31, + "ARC": 30.03, + "HellaSwag": 49.17, + "MMLU": 25.56, + "TruthfulQA": 38.78, + "Winogrande": 55.56, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "53250831436460254b7ee9afc4014d4d3156b372", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Corianas\/Quokka_2.7b", + "Average \u2b06\ufe0f": 33.26, + "ARC": 31.06, + "HellaSwag": 47.72, + "MMLU": 24.8, + "TruthfulQA": 40.14, + "Winogrande": 55.49, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.79, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "abe5e0f574d32f3234035b6e8c5d68bbb201e03c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cerebras\/Cerebras-GPT-2.7B", + "Average \u2b06\ufe0f": 33.25, + "ARC": 29.1, + "HellaSwag": 49.29, + "MMLU": 25.17, + "TruthfulQA": 41.37, + "Winogrande": 54.14, + "GSM8K": 0.45, + "Type": "pretrained", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.7, + "Hub \u2764\ufe0f": 41.0, + "Available on the hub": true, + "Model sha": "4383dfd80aafdbcfd0876419d246de51e6cbf7c1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "RWKV\/rwkv-4-1b5-pile", + "Average \u2b06\ufe0f": 33.25, + "ARC": 31.83, + "HellaSwag": 52.25, + "MMLU": 25.77, + "TruthfulQA": 35.8, + "Winogrande": 53.83, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "643585471eaf5821d94dfcb498ab5b94a36b42cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shaohang\/Sparse0.5_OPT-1.3", + "Average \u2b06\ufe0f": 33.19, + "ARC": 27.13, + "HellaSwag": 48.69, + "MMLU": 25.6, + "TruthfulQA": 39.11, + "Winogrande": 58.56, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "06249d582b0cfefac537dd6bee2e578002ffff00", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "shaohang\/SparseOPT-1.3B", + "Average \u2b06\ufe0f": 33.19, + "ARC": 27.13, + "HellaSwag": 48.69, + "MMLU": 25.6, + "TruthfulQA": 39.11, + "Winogrande": 58.56, + "GSM8K": 0.08, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06249d582b0cfefac537dd6bee2e578002ffff00", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "health360\/Healix-1.1B-V1-Chat-dDPO", + "Average \u2b06\ufe0f": 33.0, + "ARC": 30.55, + "HellaSwag": 44.78, + "MMLU": 24.64, + "TruthfulQA": 41.55, + "Winogrande": 56.51, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "07dd0532fda09df289f6617e1135b09fb705080d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "TurkuNLP\/gpt3-finnish-13B", + "Average \u2b06\ufe0f": 32.95, + "ARC": 24.66, + "HellaSwag": 46.76, + "MMLU": 23.49, + "TruthfulQA": 44.47, + "Winogrande": 58.01, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "BloomModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "ade35fd78ac2c29f7a56ffd3087321d297bb97a9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/dlite-v2-774m", + "Average \u2b06\ufe0f": 32.86, + "ARC": 30.12, + "HellaSwag": 47.68, + "MMLU": 25.37, + "TruthfulQA": 40.0, + "Winogrande": 53.99, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "0ea894a33e491912cd1a65dde47b4af03f03c4f2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DatPySci\/pythia-1b-spin-iter1", + "Average \u2b06\ufe0f": 32.85, + "ARC": 30.55, + "HellaSwag": 49.26, + "MMLU": 24.46, + "TruthfulQA": 36.89, + "Winogrande": 53.59, + "GSM8K": 2.35, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4c80730b5c7fea5e02941c1845f172dc1f022623", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DatPySci\/pythia-1b-sft-50k", + "Average \u2b06\ufe0f": 32.85, + "ARC": 30.29, + "HellaSwag": 49.21, + "MMLU": 24.64, + "TruthfulQA": 37.07, + "Winogrande": 53.99, + "GSM8K": 1.9, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0fc973e8a9960f21d057681be7d2af7c8c10f43d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-1b-deduped", + "Average \u2b06\ufe0f": 32.78, + "ARC": 29.1, + "HellaSwag": 49.65, + "MMLU": 24.27, + "TruthfulQA": 38.94, + "Winogrande": 53.59, + "GSM8K": 1.14, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.08, + "Hub \u2764\ufe0f": 15.0, + "Available on the hub": true, + "Model sha": "7199d8fc61a6d565cd1f3c62bf11525b563e13b2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DatPySci\/pythia-1b-dpo", + "Average \u2b06\ufe0f": 32.76, + "ARC": 30.12, + "HellaSwag": 49.24, + "MMLU": 24.24, + "TruthfulQA": 37.2, + "Winogrande": 54.06, + "GSM8K": 1.67, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "65412d0e910fadcb54513624759417f8f805f75e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KnutJaegersberg\/RWKV-4-PilePlus-1B5-20230520-2942-486Gtokens-ctx4096", + "Average \u2b06\ufe0f": 32.68, + "ARC": 30.63, + "HellaSwag": 52.63, + "MMLU": 25.04, + "TruthfulQA": 34.96, + "Winogrande": 52.8, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.41, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "657e40fe890c2baa1705b45084a93a70b98842eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DatPySci\/pythia-1b-sft-50k", + "Average \u2b06\ufe0f": 32.66, + "ARC": 30.03, + "HellaSwag": 49.1, + "MMLU": 24.03, + "TruthfulQA": 37.01, + "Winogrande": 54.06, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "0fc973e8a9960f21d057681be7d2af7c8c10f43d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "w601sxs\/b1ade-1b", + "Average \u2b06\ufe0f": 32.59, + "ARC": 28.58, + "HellaSwag": 46.08, + "MMLU": 25.11, + "TruthfulQA": 41.34, + "Winogrande": 53.83, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b4b0fd71589e6590089e1ec14a840ecab10894ae", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TFLai\/gpt-neo-1.3B-4bit-alpaca", + "Average \u2b06\ufe0f": 32.58, + "ARC": 28.24, + "HellaSwag": 46.35, + "MMLU": 25.19, + "TruthfulQA": 39.26, + "Winogrande": 56.2, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "4bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "137d483d1dc757c81c59bd190016f7c5df01f978", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "DatPySci\/pythia-1b-dpo-full", + "Average \u2b06\ufe0f": 32.55, + "ARC": 29.44, + "HellaSwag": 49.03, + "MMLU": 24.13, + "TruthfulQA": 37.27, + "Winogrande": 53.43, + "GSM8K": 1.97, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 1.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fe1ac6dd06014f44404f2007103414b21d5dc2f5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "DatPySci\/pythia-1b-sft-full", + "Average \u2b06\ufe0f": 32.52, + "ARC": 29.52, + "HellaSwag": 48.91, + "MMLU": 23.95, + "TruthfulQA": 37.08, + "Winogrande": 53.67, + "GSM8K": 1.97, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.01, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "83ef084c876204aa4e3f5f33e23056f551fc58cf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/Alpaca_spin_gpt2_e1_se0", + "Average \u2b06\ufe0f": 32.5, + "ARC": 27.99, + "HellaSwag": 45.74, + "MMLU": 26.68, + "TruthfulQA": 39.06, + "Winogrande": 55.56, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2fb0e1fbba1275c78915cbe6c293c7ed67af9245", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "bigscience\/bloom-1b1", + "Average \u2b06\ufe0f": 32.47, + "ARC": 28.33, + "HellaSwag": 42.78, + "MMLU": 26.7, + "TruthfulQA": 41.8, + "Winogrande": 55.01, + "GSM8K": 0.23, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 1.06, + "Hub \u2764\ufe0f": 50.0, + "Available on the hub": true, + "Model sha": "6f4195539db0eef1c9d010289f32e0645d9a2354", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rinna\/bilingual-gpt-neox-4b-instruction-sft", + "Average \u2b06\ufe0f": 32.46, + "ARC": 28.07, + "HellaSwag": 47.5, + "MMLU": 23.12, + "TruthfulQA": 43.76, + "Winogrande": 52.33, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 3.8, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "c20e42bd49a3b1b0d0a07151899a322c4760e871", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/Alpaca_spin_tuned_gpt2_large", + "Average \u2b06\ufe0f": 32.46, + "ARC": 27.9, + "HellaSwag": 45.12, + "MMLU": 27.08, + "TruthfulQA": 39.43, + "Winogrande": 54.62, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "044c10b7d54fbf685e0cd0ac958b6d8cad67f18d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Kunhao\/pile-7b-250b-tokens", + "Average \u2b06\ufe0f": 32.44, + "ARC": 29.27, + "HellaSwag": 46.29, + "MMLU": 25.25, + "TruthfulQA": 40.49, + "Winogrande": 52.8, + "GSM8K": 0.53, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "caefdf7a7c177905b0b16fbe9d4c7ba08def97c2", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "MBZUAI\/LaMini-GPT-774M", + "Average \u2b06\ufe0f": 32.43, + "ARC": 27.65, + "HellaSwag": 43.81, + "MMLU": 26.3, + "TruthfulQA": 40.26, + "Winogrande": 56.59, + "GSM8K": 0.0, + "Type": "", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "4f3bd4b37d249e6aa335be677afd39f417e05b5d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Salesforce\/codegen-6B-multi", + "Average \u2b06\ufe0f": 32.43, + "ARC": 27.22, + "HellaSwag": 41.11, + "MMLU": 25.71, + "TruthfulQA": 45.65, + "Winogrande": 53.91, + "GSM8K": 0.99, + "Type": "pretrained", + "Architecture": "CodeGenForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bsd-3-clause", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "2d58b1e73791e8f0be7ea59c2720dccb6f4d0f06", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "FabbriSimo01\/Bloom_1b_Quantized", + "Average \u2b06\ufe0f": 32.41, + "ARC": 27.73, + "HellaSwag": 42.83, + "MMLU": 26.28, + "TruthfulQA": 41.82, + "Winogrande": 55.64, + "GSM8K": 0.15, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f31188966c6735bd894edacfee8371a6eaf7dbc7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "deepseek-ai\/deepseek-coder-1.3b-instruct", + "Average \u2b06\ufe0f": 32.4, + "ARC": 28.58, + "HellaSwag": 39.87, + "MMLU": 28.47, + "TruthfulQA": 44.02, + "Winogrande": 52.41, + "GSM8K": 1.06, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 56.0, + "Available on the hub": true, + "Model sha": "e04e04028d6345ab3225644cd615e2573ffb9b8c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/Alpaca_spin_gpt2_e0_se1", + "Average \u2b06\ufe0f": 32.4, + "ARC": 27.99, + "HellaSwag": 45.84, + "MMLU": 26.44, + "TruthfulQA": 38.88, + "Winogrande": 55.17, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "60f08e79339d6c6c02521fd8d3cd5fc16a0fd108", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/Alpaca_refine_gpt2_e0_se1", + "Average \u2b06\ufe0f": 32.39, + "ARC": 29.18, + "HellaSwag": 45.35, + "MMLU": 26.91, + "TruthfulQA": 37.89, + "Winogrande": 54.3, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fbb41cbdfc6662cfff26e0aec950df6e8d9dc8c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/gpt2-large-conversational", + "Average \u2b06\ufe0f": 32.33, + "ARC": 26.96, + "HellaSwag": 44.98, + "MMLU": 26.33, + "TruthfulQA": 39.6, + "Winogrande": 56.04, + "GSM8K": 0.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "6674ad1ed9f518054561b866172eb88b7a769413", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "xaviviro\/FLOR-1.3B-xat", + "Average \u2b06\ufe0f": 32.27, + "ARC": 26.79, + "HellaSwag": 41.63, + "MMLU": 26.65, + "TruthfulQA": 44.38, + "Winogrande": 53.43, + "GSM8K": 0.76, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "35cdda0d2b7ade43fd39f3fb4ffad25f0c2730ea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "rinna\/bilingual-gpt-neox-4b-8k", + "Average \u2b06\ufe0f": 32.23, + "ARC": 28.58, + "HellaSwag": 43.94, + "MMLU": 25.38, + "TruthfulQA": 47.48, + "Winogrande": 47.99, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 25.0, + "Available on the hub": true, + "Model sha": "ad56d7fc86db4ad5a7036bc9f80e11cd6f435a60", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Rachneet\/gpt2-xl-alpaca", + "Average \u2b06\ufe0f": 32.21, + "ARC": 26.79, + "HellaSwag": 43.85, + "MMLU": 26.31, + "TruthfulQA": 39.4, + "Winogrande": 56.91, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 1.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a1a19acc0ef161bfa35f460c15ed3015595714d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Devio\/test-3b", + "Average \u2b06\ufe0f": 32.2, + "ARC": 27.65, + "HellaSwag": 44.79, + "MMLU": 23.53, + "TruthfulQA": 41.42, + "Winogrande": 55.49, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 3.5, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b81c038ee2fa2addd285acde08b1a7ca3cb2854d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/Alpaca_refine_tuned_gpt2_large", + "Average \u2b06\ufe0f": 32.19, + "ARC": 27.56, + "HellaSwag": 45.09, + "MMLU": 26.91, + "TruthfulQA": 37.91, + "Winogrande": 54.93, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "312b55480d2c551b92edc66054d3bb7acf96876f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "rinna\/bilingual-gpt-neox-4b", + "Average \u2b06\ufe0f": 32.14, + "ARC": 29.18, + "HellaSwag": 43.73, + "MMLU": 23.1, + "TruthfulQA": 45.0, + "Winogrande": 51.85, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 3.95, + "Hub \u2764\ufe0f": 26.0, + "Available on the hub": true, + "Model sha": "f02f6f3c8da0093f3c1ce59220409bc2fa9fbb17", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "stabilityai\/stablelm-tuned-alpha-3b", + "Average \u2b06\ufe0f": 32.14, + "ARC": 27.82, + "HellaSwag": 44.06, + "MMLU": 23.08, + "TruthfulQA": 42.33, + "Winogrande": 55.01, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": [ + "cc-by-nc-sa-4.0" + ], + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 112.0, + "Available on the hub": true, + "Model sha": "d1c03d2114451d562416b9efe4281d319ceff99e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mohammed-Altaf\/Medical-ChatBot", + "Average \u2b06\ufe0f": 32.13, + "ARC": 30.55, + "HellaSwag": 38.63, + "MMLU": 25.98, + "TruthfulQA": 41.25, + "Winogrande": 55.41, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "9e2d5d7a6189762164690a2fe714b00ce497b253", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/Alpaca_refine_gpt2_e1_se0", + "Average \u2b06\ufe0f": 32.06, + "ARC": 27.3, + "HellaSwag": 45.39, + "MMLU": 26.51, + "TruthfulQA": 37.28, + "Winogrande": 55.88, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d1c9d3e02d5eed70032df54898ea11e51a7b41b2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/Alpaca-tuned-gpt2", + "Average \u2b06\ufe0f": 32.02, + "ARC": 26.54, + "HellaSwag": 44.79, + "MMLU": 27.22, + "TruthfulQA": 37.65, + "Winogrande": 55.09, + "GSM8K": 0.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d34098965369d0ddb41c44d19671429440490859", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mohammed-Altaf\/Medical-ChatBot", + "Average \u2b06\ufe0f": 31.98, + "ARC": 30.46, + "HellaSwag": 38.6, + "MMLU": 25.96, + "TruthfulQA": 41.04, + "Winogrande": 54.85, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "9e2d5d7a6189762164690a2fe714b00ce497b253", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/SSH_355M", + "Average \u2b06\ufe0f": 31.92, + "ARC": 26.96, + "HellaSwag": 38.98, + "MMLU": 27.59, + "TruthfulQA": 44.15, + "Winogrande": 53.83, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "11bdb293dc0bfd2afc406fc26c765aac7f06cbb7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mohammed-Altaf\/Medical-ChatBot", + "Average \u2b06\ufe0f": 31.87, + "ARC": 30.46, + "HellaSwag": 38.55, + "MMLU": 25.91, + "TruthfulQA": 41.02, + "Winogrande": 54.22, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "9e2d5d7a6189762164690a2fe714b00ce497b253", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hyunjae\/polyglot-ko-3.8b-total", + "Average \u2b06\ufe0f": 31.87, + "ARC": 25.34, + "HellaSwag": 39.69, + "MMLU": 29.16, + "TruthfulQA": 43.67, + "Winogrande": 53.35, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 3.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "658a043415467ca5286f3348493db10aa8b94f2c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "PY007\/TinyLlama-1.1B-step-50K-105b", + "Average \u2b06\ufe0f": 31.86, + "ARC": 25.85, + "HellaSwag": 44.1, + "MMLU": 26.78, + "TruthfulQA": 39.51, + "Winogrande": 54.38, + "GSM8K": 0.53, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c1f1ef67c12e4bb85fe0bdf1747c645a202cc118", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIGym\/deepseek-coder-1.3b-chat-and-function-calling", + "Average \u2b06\ufe0f": 31.82, + "ARC": 26.28, + "HellaSwag": 39.27, + "MMLU": 26.92, + "TruthfulQA": 43.37, + "Winogrande": 51.7, + "GSM8K": 3.41, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.35, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c0a37346bb1c3fac3b345106b3b691f3460e445e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mikivis\/gpt2-large-lora-sft", + "Average \u2b06\ufe0f": 31.82, + "ARC": 26.79, + "HellaSwag": 44.15, + "MMLU": 25.82, + "TruthfulQA": 39.06, + "Winogrande": 55.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1c0c5a686f3c83692e033416197155557e4d3a0d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "YeungNLP\/firefly-bloom-2b6-v2", + "Average \u2b06\ufe0f": 31.82, + "ARC": 27.65, + "HellaSwag": 39.23, + "MMLU": 25.24, + "TruthfulQA": 42.27, + "Winogrande": 54.78, + "GSM8K": 1.74, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 2.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": false, + "Model sha": "8334b22c39937c0404e09dd22a867e2e2a6fc9e0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/Instruct_GPT_v1", + "Average \u2b06\ufe0f": 31.77, + "ARC": 28.07, + "HellaSwag": 38.98, + "MMLU": 26.55, + "TruthfulQA": 42.22, + "Winogrande": 54.06, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1eea8e13be8b2616cc4a4bedb796f61ea894751c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "llm-jp\/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0", + "Average \u2b06\ufe0f": 31.77, + "ARC": 26.88, + "HellaSwag": 44.78, + "MMLU": 23.12, + "TruthfulQA": 45.19, + "Winogrande": 50.67, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "68282fe744c69ea2e4420a4a6833c0b9168215eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/SSH_300M", + "Average \u2b06\ufe0f": 31.75, + "ARC": 28.24, + "HellaSwag": 38.74, + "MMLU": 27.03, + "TruthfulQA": 42.51, + "Winogrande": 53.67, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d531d193cfb1e645e8afb89203983450b6655967", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIGym\/deepseek-coder-1.3b-chat", + "Average \u2b06\ufe0f": 31.74, + "ARC": 25.85, + "HellaSwag": 39.59, + "MMLU": 26.36, + "TruthfulQA": 43.92, + "Winogrande": 51.7, + "GSM8K": 3.03, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.35, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1e167cd95fc142008b7ea37a1d59a12f972b8c96", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/orca_mini_13B-GPTQ", + "Average \u2b06\ufe0f": 31.73, + "ARC": 27.3, + "HellaSwag": 25.85, + "MMLU": 25.31, + "TruthfulQA": 48.06, + "Winogrande": 63.77, + "GSM8K": 0.08, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 45.0, + "Available on the hub": true, + "Model sha": "8ec18e5c597da86fa123c08b6e6bef7da6ec7440", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/spin_gpt2_medium_alpaca_e2", + "Average \u2b06\ufe0f": 31.71, + "ARC": 28.07, + "HellaSwag": 39.88, + "MMLU": 26.99, + "TruthfulQA": 41.52, + "Winogrande": 53.67, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f269152bdb88c649e38afa72677cc810cdd46c07", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt1.3b_10e6", + "Average \u2b06\ufe0f": 31.7, + "ARC": 25.77, + "HellaSwag": 41.67, + "MMLU": 25.9, + "TruthfulQA": 42.72, + "Winogrande": 54.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d467863c8401c4ccb740b7c05fc8d5d6bbed0e0c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "llm-jp\/llm-jp-13b-instruct-full-jaster-v1.0", + "Average \u2b06\ufe0f": 31.63, + "ARC": 27.22, + "HellaSwag": 44.7, + "MMLU": 23.12, + "TruthfulQA": 44.69, + "Winogrande": 50.04, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 14.0, + "Available on the hub": true, + "Model sha": "b44eac954eac7ddbceba4f510325fd710c977eab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BarraHome\/PequeLLaMa-1B-Instruct-v0.1-16bit", + "Average \u2b06\ufe0f": 31.59, + "ARC": 27.99, + "HellaSwag": 43.03, + "MMLU": 24.73, + "TruthfulQA": 41.1, + "Winogrande": 52.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3ab3fcbf9b4a057c38bb4e50290e23a0fb23e049", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/fairseq-dense-355M", + "Average \u2b06\ufe0f": 31.58, + "ARC": 25.43, + "HellaSwag": 46.67, + "MMLU": 25.3, + "TruthfulQA": 39.19, + "Winogrande": 52.88, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.4, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "24da1ea670f0638c2df911596e95c764bcd5fb44", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "AIGym\/deepseek-coder-1.3b-chat", + "Average \u2b06\ufe0f": 31.57, + "ARC": 25.6, + "HellaSwag": 39.69, + "MMLU": 25.54, + "TruthfulQA": 43.94, + "Winogrande": 51.46, + "GSM8K": 3.18, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.35, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1e167cd95fc142008b7ea37a1d59a12f972b8c96", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-410m", + "Average \u2b06\ufe0f": 31.55, + "ARC": 26.19, + "HellaSwag": 40.85, + "MMLU": 27.25, + "TruthfulQA": 41.22, + "Winogrande": 53.12, + "GSM8K": 0.68, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.51, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "9879c9b5f8bea9051dcb0e68dff21493d67e9d4f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yukang\/Llama-2-13b-chat-longlora-32k-sft", + "Average \u2b06\ufe0f": 31.54, + "ARC": 26.54, + "HellaSwag": 26.1, + "MMLU": 23.12, + "TruthfulQA": 49.16, + "Winogrande": 64.33, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": false, + "Model sha": "6f2924e354c3ab035aa2ff7c7e28d0e5327e2667", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/latent_gpt2_medium_alpaca_e3", + "Average \u2b06\ufe0f": 31.53, + "ARC": 28.75, + "HellaSwag": 37.78, + "MMLU": 26.35, + "TruthfulQA": 44.74, + "Winogrande": 51.54, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f8eee4693c4efb77cc3694484ca8af68e64938a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/dlite-v1-774m", + "Average \u2b06\ufe0f": 31.51, + "ARC": 28.07, + "HellaSwag": 44.35, + "MMLU": 25.91, + "TruthfulQA": 36.11, + "Winogrande": 54.62, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d3f5401d07965fb13c2cb8b458ffaed9a5a79c2d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mikivis\/gpt2-large-lora-stf4", + "Average \u2b06\ufe0f": 31.5, + "ARC": 26.88, + "HellaSwag": 42.17, + "MMLU": 25.53, + "TruthfulQA": 40.84, + "Winogrande": 53.59, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "82eff3a62116fd589ad7319c9d75ff6b12f42f72", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "stabilityai\/stablelm-base-alpha-3b", + "Average \u2b06\ufe0f": 31.5, + "ARC": 26.45, + "HellaSwag": 42.24, + "MMLU": 25.43, + "TruthfulQA": 40.5, + "Winogrande": 53.91, + "GSM8K": 0.45, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": [ + "cc-by-sa-4.0" + ], + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 83.0, + "Available on the hub": true, + "Model sha": "99567ccfe45fabe467c71393aa6716106edb83c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/Instruct_GPT", + "Average \u2b06\ufe0f": 31.46, + "ARC": 28.24, + "HellaSwag": 39.33, + "MMLU": 26.84, + "TruthfulQA": 39.72, + "Winogrande": 54.3, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fa52bd3a8909f0b69844280d3bb5da1070d49979", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yukang\/Llama-2-13b-chat-longlora-32k-sft", + "Average \u2b06\ufe0f": 31.43, + "ARC": 26.11, + "HellaSwag": 26.17, + "MMLU": 23.12, + "TruthfulQA": 49.07, + "Winogrande": 64.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": false, + "Model sha": "6f2924e354c3ab035aa2ff7c7e28d0e5327e2667", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "facebook\/xglm-1.7B", + "Average \u2b06\ufe0f": 31.42, + "ARC": 25.85, + "HellaSwag": 45.68, + "MMLU": 25.1, + "TruthfulQA": 37.21, + "Winogrande": 53.91, + "GSM8K": 0.76, + "Type": "", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.7, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "d23a5e8e2164af31a84a26756b9b17f925143050", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-coder-ds-1.3b", + "Average \u2b06\ufe0f": 31.4, + "ARC": 26.54, + "HellaSwag": 39.49, + "MMLU": 24.85, + "TruthfulQA": 42.12, + "Winogrande": 53.04, + "GSM8K": 2.35, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8045ddf0d93e582dd6ed80c9f62fd0b6c7d8f806", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigcode\/starcoderbase-3b", + "Average \u2b06\ufe0f": 31.38, + "ARC": 25.85, + "HellaSwag": 39.11, + "MMLU": 27.35, + "TruthfulQA": 43.05, + "Winogrande": 51.14, + "GSM8K": 1.74, + "Type": "pretrained", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "e1c5ef4ebb97afa0db09ec3e520f0487ca350bbe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/latent_gpt2_medium_alpaca_e2", + "Average \u2b06\ufe0f": 31.37, + "ARC": 26.96, + "HellaSwag": 39.72, + "MMLU": 26.93, + "TruthfulQA": 41.01, + "Winogrande": 53.2, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d2d04c16c047a048c3addcd2480bd61ac04e359d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mikivis\/gpt2-large-lora-sft2", + "Average \u2b06\ufe0f": 31.33, + "ARC": 26.62, + "HellaSwag": 42.68, + "MMLU": 24.72, + "TruthfulQA": 40.31, + "Winogrande": 53.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1244efb5d20765beb54f6b4a4e1426cf6d5daf44", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "nicholasKluge\/Aira-2-774M", + "Average \u2b06\ufe0f": 31.33, + "ARC": 28.75, + "HellaSwag": 40.8, + "MMLU": 25.1, + "TruthfulQA": 41.33, + "Winogrande": 52.01, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "f43044cfe7bf0827a176f0d319c63251c2b29373", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KnutJaegersberg\/gpt-2-xl-EvolInstruct", + "Average \u2b06\ufe0f": 31.32, + "ARC": 27.39, + "HellaSwag": 38.46, + "MMLU": 25.67, + "TruthfulQA": 42.76, + "Winogrande": 53.51, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 1.61, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3e68735b9bfbca5c2e6a8e4367f003ab3d3c1512", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "FabbriSimo01\/Cerebras_1.3b_Quantized", + "Average \u2b06\ufe0f": 31.31, + "ARC": 25.94, + "HellaSwag": 38.56, + "MMLU": 26.79, + "TruthfulQA": 42.67, + "Winogrande": 53.51, + "GSM8K": 0.38, + "Type": "", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e2126a42a1c8a938553dd513e4adafec41cb793e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cerebras\/Cerebras-GPT-1.3B", + "Average \u2b06\ufe0f": 31.3, + "ARC": 26.28, + "HellaSwag": 38.54, + "MMLU": 26.59, + "TruthfulQA": 42.7, + "Winogrande": 53.43, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 45.0, + "Available on the hub": true, + "Model sha": "5b95400ee8d1e3cc9f79f0dec7182ed9c1009c34", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-410m-deduped", + "Average \u2b06\ufe0f": 31.29, + "ARC": 24.83, + "HellaSwag": 41.29, + "MMLU": 25.99, + "TruthfulQA": 40.95, + "Winogrande": 54.38, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.51, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "c4fc8d586d62df497f1f9b69d66d3ca419992d3e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/dlite-v2-355m", + "Average \u2b06\ufe0f": 31.2, + "ARC": 28.33, + "HellaSwag": 40.54, + "MMLU": 26.77, + "TruthfulQA": 38.76, + "Winogrande": 52.8, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "f51d310aebc16a9fe0d999d2a437b5faff635716", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "winglian\/basilisk-4b", + "Average \u2b06\ufe0f": 31.15, + "ARC": 25.85, + "HellaSwag": 39.6, + "MMLU": 24.61, + "TruthfulQA": 43.74, + "Winogrande": 53.12, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 4.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "b91c2e5389f4f0ce2d6042fdce5927343d8dcb06", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PygmalionAI\/pygmalion-1.3b", + "Average \u2b06\ufe0f": 31.14, + "ARC": 28.07, + "HellaSwag": 46.96, + "MMLU": 24.12, + "TruthfulQA": 37.64, + "Winogrande": 50.04, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "agpl-3.0", + "#Params (B)": 1.52, + "Hub \u2764\ufe0f": 59.0, + "Available on the hub": true, + "Model sha": "bef2c90128c00ff6f16c0f397463423b7d988e17", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/spin_gpt2_medium_alpaca_e3", + "Average \u2b06\ufe0f": 31.14, + "ARC": 27.82, + "HellaSwag": 38.82, + "MMLU": 26.92, + "TruthfulQA": 42.2, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3e1df48210c5ef275174a7dc0d7f27e3436a90d5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Mikivis\/gpt2-large-lora-sft1", + "Average \u2b06\ufe0f": 31.01, + "ARC": 24.66, + "HellaSwag": 42.67, + "MMLU": 24.89, + "TruthfulQA": 39.37, + "Winogrande": 54.46, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.77, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8e26a8d2dc1661d87a8652c75f00b805d63e7330", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "nicholasKluge\/Aira-2-355M", + "Average \u2b06\ufe0f": 31.0, + "ARC": 27.56, + "HellaSwag": 38.92, + "MMLU": 27.26, + "TruthfulQA": 38.53, + "Winogrande": 53.75, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2479f5b1bb62251ec88e60182ba81390a4c19cf9", + "Flagged": false, + "MoE": false + }, + { + "T": null, + "Model": "baseline", + "Average \u2b06\ufe0f": 31.0, + "ARC": 25.0, + "HellaSwag": 25.0, + "MMLU": 25.0, + "TruthfulQA": 25.0, + "Winogrande": 50.0, + "GSM8K": 0.21, + "Type": "", + "Architecture": null, + "Weight type": null, + "Precision": null, + "Merged": false, + "Hub License": null, + "#Params (B)": null, + "Hub \u2764\ufe0f": null, + "Available on the hub": null, + "Model sha": "N\/A", + "Flagged": false, + "MoE": null + }, + { + "T": "\ud83d\udcac", + "Model": "SummerSigh\/GPTNeo350M-Instruct-SFT", + "Average \u2b06\ufe0f": 31.0, + "ARC": 25.94, + "HellaSwag": 38.55, + "MMLU": 25.76, + "TruthfulQA": 45.25, + "Winogrande": 50.2, + "GSM8K": 0.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5e41660ced3edf13c47e933112efd280b710b977", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/bloom-1b1_10e6", + "Average \u2b06\ufe0f": 30.98, + "ARC": 25.43, + "HellaSwag": 37.12, + "MMLU": 25.43, + "TruthfulQA": 44.4, + "Winogrande": 53.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "37d0d3582e88a382e22c7958dd908081553babb6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KaeriJenti\/Kaori-34b-v2", + "Average \u2b06\ufe0f": 30.97, + "ARC": 23.89, + "HellaSwag": 28.97, + "MMLU": 25.59, + "TruthfulQA": 49.46, + "Winogrande": 57.22, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e28a7b27201045a0ca9b1504c5bae53428f2c0ba", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KaeriJenti\/kaori-34b-v4", + "Average \u2b06\ufe0f": 30.97, + "ARC": 23.89, + "HellaSwag": 28.97, + "MMLU": 25.59, + "TruthfulQA": 49.46, + "Winogrande": 57.22, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 34.39, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "94628cc31b1acac36a464edbfea09949bca139b7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "postbot\/emailgen-pythia-410m-deduped", + "Average \u2b06\ufe0f": 30.93, + "ARC": 27.9, + "HellaSwag": 40.04, + "MMLU": 27.35, + "TruthfulQA": 38.2, + "Winogrande": 52.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.51, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e0208b02990c49138350da791f0b6fcb8a65e738", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "AI-Sweden-Models\/gpt-sw3-356m-instruct", + "Average \u2b06\ufe0f": 30.93, + "ARC": 26.96, + "HellaSwag": 38.01, + "MMLU": 25.53, + "TruthfulQA": 40.74, + "Winogrande": 52.57, + "GSM8K": 1.74, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.47, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "85615b7c700ca7f38c32db8c7efabfa97668f1c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Corianas\/Quokka_1.3b", + "Average \u2b06\ufe0f": 30.86, + "ARC": 27.73, + "HellaSwag": 37.91, + "MMLU": 26.66, + "TruthfulQA": 40.14, + "Winogrande": 52.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8a8d738e841a524d658897d89b9e39e7b9272ed8", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Corianas\/1.3b", + "Average \u2b06\ufe0f": 30.76, + "ARC": 27.3, + "HellaSwag": 38.3, + "MMLU": 26.77, + "TruthfulQA": 39.02, + "Winogrande": 53.04, + "GSM8K": 0.15, + "Type": "", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 1.42, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9831f95df82155ef95ff46a505506bf6194b131a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/Mediquad-4x7b", + "Average \u2b06\ufe0f": 30.74, + "ARC": 27.47, + "HellaSwag": 28.21, + "MMLU": 28.66, + "TruthfulQA": 49.56, + "Winogrande": 50.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 19.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "91cd7ebc2a1ec9f88073842ce9cbd92a6943fd55", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "cmarkea\/bloomz-560m-sft-chat", + "Average \u2b06\ufe0f": 30.72, + "ARC": 27.47, + "HellaSwag": 37.05, + "MMLU": 23.93, + "TruthfulQA": 42.35, + "Winogrande": 53.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 0.56, + "Hub \u2764\ufe0f": 10.0, + "Available on the hub": true, + "Model sha": "e2bbcbdd534c7d75b7d2f9408e74f6682cf3a05e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "player1537\/dolphinette", + "Average \u2b06\ufe0f": 30.65, + "ARC": 24.91, + "HellaSwag": 37.33, + "MMLU": 25.37, + "TruthfulQA": 42.08, + "Winogrande": 54.22, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.56, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "20529d47b0a82343014727edd1639a9a6a6b09e6", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "bigscience\/bloomz-560m", + "Average \u2b06\ufe0f": 30.63, + "ARC": 23.55, + "HellaSwag": 36.31, + "MMLU": 25.1, + "TruthfulQA": 45.69, + "Winogrande": 53.12, + "GSM8K": 0.0, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 0.56, + "Hub \u2764\ufe0f": 90.0, + "Available on the hub": true, + "Model sha": "a2845d7e13dd12efae154a9f1c63fcc2e0cc4b05", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/medalpaca-13B-GPTQ-4bit", + "Average \u2b06\ufe0f": 30.62, + "ARC": 29.35, + "HellaSwag": 26.32, + "MMLU": 25.44, + "TruthfulQA": 49.51, + "Winogrande": 53.12, + "GSM8K": 0.0, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 16.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "12190f743a19e91dfe1f5c77abc0c1bf486073dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/dlite-v1-355m", + "Average \u2b06\ufe0f": 30.54, + "ARC": 27.13, + "HellaSwag": 39.07, + "MMLU": 27.12, + "TruthfulQA": 37.13, + "Winogrande": 52.8, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "c5f4b5a61e6a66a5c7613164d99a70db5bf7e9a2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "xhyi\/PT_GPTNEO350_ATG", + "Average \u2b06\ufe0f": 30.46, + "ARC": 25.43, + "HellaSwag": 37.59, + "MMLU": 24.79, + "TruthfulQA": 43.05, + "Winogrande": 51.46, + "GSM8K": 0.45, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": false, + "Model sha": "56ab08aaa6802d0f830d42c352d5d536be72811d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TehVenom\/DiffMerge-DollyGPT-Pygmalion", + "Average \u2b06\ufe0f": 30.45, + "ARC": 23.63, + "HellaSwag": 34.38, + "MMLU": 24.41, + "TruthfulQA": 46.48, + "Winogrande": 53.83, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "6a00b371146d4bd2903890814485ee1b775162e7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "RWKV\/rwkv-4-430m-pile", + "Average \u2b06\ufe0f": 30.45, + "ARC": 26.71, + "HellaSwag": 40.01, + "MMLU": 24.85, + "TruthfulQA": 39.58, + "Winogrande": 51.14, + "GSM8K": 0.38, + "Type": "pretrained", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.43, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": false, + "Model sha": "a4f6ec80438d4262d1bbc8f385feb2ef1a4a9d6b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "LordNoah\/latent_gpt2_medium_alpaca_e4", + "Average \u2b06\ufe0f": 30.44, + "ARC": 29.1, + "HellaSwag": 39.8, + "MMLU": 25.52, + "TruthfulQA": 35.23, + "Winogrande": 52.41, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a2da5e4fbd6a50110a0106ef4f046deb56e5d7a6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TheTravellingEngineer\/bloom-560m-RLHF-v2", + "Average \u2b06\ufe0f": 30.43, + "ARC": 26.45, + "HellaSwag": 37.67, + "MMLU": 23.95, + "TruthfulQA": 43.51, + "Winogrande": 50.91, + "GSM8K": 0.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.56, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "7128cbfcdaf67f1eff27e45d875c35e7b47618db", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/mistral-inst-v02-dpo", + "Average \u2b06\ufe0f": 30.43, + "ARC": 27.9, + "HellaSwag": 26.08, + "MMLU": 27.02, + "TruthfulQA": 50.8, + "Winogrande": 50.75, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d907e70ac8d48e22b85f57b4fb715dfef9f4cfc8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AI-Sweden-Models\/gpt-sw3-356m", + "Average \u2b06\ufe0f": 30.41, + "ARC": 23.63, + "HellaSwag": 37.05, + "MMLU": 25.93, + "TruthfulQA": 42.55, + "Winogrande": 53.04, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.47, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "15ba8a812d3eb265342f62cb0ee9ab6a45fdbd89", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "robowaifudev\/megatron-gpt2-345m", + "Average \u2b06\ufe0f": 30.4, + "ARC": 24.23, + "HellaSwag": 39.18, + "MMLU": 24.32, + "TruthfulQA": 41.51, + "Winogrande": 52.96, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.38, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "b39f8d00fb9f33da4271be2035da848da896a23b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "uukuguy\/speechless-codellama-orca-airoboros-13b-0.10e", + "Average \u2b06\ufe0f": 30.36, + "ARC": 29.44, + "HellaSwag": 25.71, + "MMLU": 25.43, + "TruthfulQA": 49.64, + "Winogrande": 51.93, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dbd1d1f7ad7b6b359f8246141650b25ca0bb8cbb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "KnutJaegersberg\/megatron-gpt2-345m-evol_instruct_v2", + "Average \u2b06\ufe0f": 30.31, + "ARC": 26.37, + "HellaSwag": 38.39, + "MMLU": 23.6, + "TruthfulQA": 41.19, + "Winogrande": 52.33, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.36, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "2866eeaaf62014a7a6e939d18b6e27f44df48428", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vicgalle\/Miqu-6B-truthy", + "Average \u2b06\ufe0f": 30.28, + "ARC": 27.65, + "HellaSwag": 26.71, + "MMLU": 27.04, + "TruthfulQA": 50.63, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "179b531fff0959893bb486df30f1f374a2c42b90", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Felladrin\/Llama-160M-Chat-v1", + "Average \u2b06\ufe0f": 30.27, + "ARC": 24.74, + "HellaSwag": 35.29, + "MMLU": 26.13, + "TruthfulQA": 44.16, + "Winogrande": 51.3, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.16, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "06b255f112080b26c62e72404331421ffcb95293", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AkiGogikar\/KnowledgeNinja-LiteLlama-460Mx6MoE-1T", + "Average \u2b06\ufe0f": 30.23, + "ARC": 25.17, + "HellaSwag": 38.45, + "MMLU": 26.16, + "TruthfulQA": 41.57, + "Winogrande": 50.04, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 1.97, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "04c91b4a7759f67dc236e8d61846f0cf756da9fa", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "porkorbeef\/Llama-2-13b-sf", + "Average \u2b06\ufe0f": 30.22, + "ARC": 29.52, + "HellaSwag": 26.49, + "MMLU": 25.98, + "TruthfulQA": 48.97, + "Winogrande": 50.36, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06253ee259e6b205c4734ab6ec3fa850737b2110", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-codellama-orca-airoboros-13b-0.10e", + "Average \u2b06\ufe0f": 30.22, + "ARC": 29.27, + "HellaSwag": 25.74, + "MMLU": 25.69, + "TruthfulQA": 49.61, + "Winogrande": 50.99, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "dbd1d1f7ad7b6b359f8246141650b25ca0bb8cbb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "yec019\/fbopt-350m-8bit", + "Average \u2b06\ufe0f": 30.21, + "ARC": 23.55, + "HellaSwag": 36.6, + "MMLU": 26.22, + "TruthfulQA": 40.97, + "Winogrande": 52.64, + "GSM8K": 1.29, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 0.33, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "305f804054d75a406a85a568ea99dca17cfc998d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kevin009\/flyingllama-v2", + "Average \u2b06\ufe0f": 30.19, + "ARC": 24.74, + "HellaSwag": 38.44, + "MMLU": 26.37, + "TruthfulQA": 41.3, + "Winogrande": 50.28, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a1c0d260967efd02b197d525ce2802d42a3fb694", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KnutJaegersberg\/RWKV-4-PilePlus-430M-20230520-6162-1018Gtokens-ctx4098", + "Average \u2b06\ufe0f": 30.18, + "ARC": 26.02, + "HellaSwag": 40.39, + "MMLU": 24.45, + "TruthfulQA": 37.57, + "Winogrande": 52.41, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.38, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e31777c9d3b8c5c9f803b23f49550c009cbdcf6d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "ahxt\/llama2_xs_460M_experimental", + "Average \u2b06\ufe0f": 30.17, + "ARC": 24.91, + "HellaSwag": 38.47, + "MMLU": 26.17, + "TruthfulQA": 41.59, + "Winogrande": 49.88, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": false, + "Model sha": "c8db281477559f5c969a9be794ce236f8a99e1a0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "ahxt\/LiteLlama-460M-1T", + "Average \u2b06\ufe0f": 30.16, + "ARC": 24.83, + "HellaSwag": 38.39, + "MMLU": 25.96, + "TruthfulQA": 41.59, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 145.0, + "Available on the hub": true, + "Model sha": "77b8a976440e7d1ea5a890eaf1e0175b1cac0078", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kevin009\/flyingllama", + "Average \u2b06\ufe0f": 30.16, + "ARC": 24.74, + "HellaSwag": 38.35, + "MMLU": 26.14, + "TruthfulQA": 41.6, + "Winogrande": 50.12, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.46, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "57297d80cdbd91415b76b2ef58d272262a627a98", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "uukuguy\/Orca-2-7b-f16", + "Average \u2b06\ufe0f": 30.15, + "ARC": 29.61, + "HellaSwag": 25.62, + "MMLU": 26.7, + "TruthfulQA": 48.36, + "Winogrande": 50.59, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f6b2f717467dc12b2b19cad90ed4362153863ad9", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-350M-Erebus", + "Average \u2b06\ufe0f": 30.14, + "ARC": 23.81, + "HellaSwag": 34.35, + "MMLU": 26.23, + "TruthfulQA": 43.58, + "Winogrande": 52.57, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.33, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "83ce2f4e78d308968cf7ecd03d86a1f64aea8336", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TheTravellingEngineer\/bloom-1b1-RLHF", + "Average \u2b06\ufe0f": 30.14, + "ARC": 27.99, + "HellaSwag": 26.19, + "MMLU": 26.86, + "TruthfulQA": 48.88, + "Winogrande": 50.91, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "65bd72580520a1d4a0c19fcb23f68c1f28464e1b", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "bigscience\/bloom-560m", + "Average \u2b06\ufe0f": 30.13, + "ARC": 24.74, + "HellaSwag": 37.15, + "MMLU": 24.22, + "TruthfulQA": 42.44, + "Winogrande": 51.93, + "GSM8K": 0.3, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 0.56, + "Hub \u2764\ufe0f": 312.0, + "Available on the hub": true, + "Model sha": "4f42c91d806a19ae1a46af6c3fb5f4990d884cd6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yhyhy3\/med-orca-instruct-33b", + "Average \u2b06\ufe0f": 30.12, + "ARC": 28.84, + "HellaSwag": 25.63, + "MMLU": 26.5, + "TruthfulQA": 49.26, + "Winogrande": 50.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": null, + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1d636881854338e571825226c712180da06be72c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "porkorbeef\/Llama-2-13b", + "Average \u2b06\ufe0f": 30.11, + "ARC": 29.35, + "HellaSwag": 26.35, + "MMLU": 24.94, + "TruthfulQA": 48.32, + "Winogrande": 51.7, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "06253ee259e6b205c4734ab6ec3fa850737b2110", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "health360\/Healix-410M", + "Average \u2b06\ufe0f": 30.1, + "ARC": 25.09, + "HellaSwag": 32.02, + "MMLU": 24.94, + "TruthfulQA": 44.42, + "Winogrande": 54.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.41, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "df5a3cec54a0bdd22e1644bfe576c7b58eca6bfd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt350m_10e5", + "Average \u2b06\ufe0f": 30.09, + "ARC": 24.15, + "HellaSwag": 36.53, + "MMLU": 26.0, + "TruthfulQA": 42.17, + "Winogrande": 51.7, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.33, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9351bd3b7ded60bcf170d81fd3a6040ea431a8de", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "marcchew\/Marcoroni-7B-LaMini-80K", + "Average \u2b06\ufe0f": 30.09, + "ARC": 28.75, + "HellaSwag": 26.13, + "MMLU": 24.46, + "TruthfulQA": 49.71, + "Winogrande": 51.46, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ea7a283403ec1a40570bfc25f2c4b8fcb089b6bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "222gate\/TinyMistral-248Mx4-MOE", + "Average \u2b06\ufe0f": 30.08, + "ARC": 29.52, + "HellaSwag": 25.71, + "MMLU": 24.82, + "TruthfulQA": 48.66, + "Winogrande": 51.78, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4610e3fb0c4f541835bedf9be5a8fd6955827e3b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "doas\/test5", + "Average \u2b06\ufe0f": 30.06, + "ARC": 28.41, + "HellaSwag": 26.63, + "MMLU": 25.36, + "TruthfulQA": 47.34, + "Winogrande": 52.64, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b0dae937b7137790d8946794375e1affd51c760a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigcode\/starcoderbase-1b", + "Average \u2b06\ufe0f": 30.06, + "ARC": 22.7, + "HellaSwag": 34.31, + "MMLU": 26.67, + "TruthfulQA": 45.79, + "Winogrande": 49.96, + "GSM8K": 0.91, + "Type": "pretrained", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 1.14, + "Hub \u2764\ufe0f": 47.0, + "Available on the hub": true, + "Model sha": "182f0165fdf8da9c9935901eec65c94337f01c11", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MBZUAI\/lamini-cerebras-1.3b", + "Average \u2b06\ufe0f": 30.05, + "ARC": 26.88, + "HellaSwag": 37.96, + "MMLU": 28.43, + "TruthfulQA": 36.45, + "Winogrande": 50.59, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "502e70081df53edc8a9156acf5a26a11a9dad8fb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KnutJaegersberg\/megatron-GPT-2-345m-EvolInstruct", + "Average \u2b06\ufe0f": 30.01, + "ARC": 24.06, + "HellaSwag": 35.12, + "MMLU": 24.48, + "TruthfulQA": 41.25, + "Winogrande": 54.78, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.38, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "dc95fda9f1e51d94870e28751e35410c66563d18", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/opt-350m", + "Average \u2b06\ufe0f": 30.01, + "ARC": 23.55, + "HellaSwag": 36.73, + "MMLU": 26.02, + "TruthfulQA": 40.83, + "Winogrande": 52.64, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.35, + "Hub \u2764\ufe0f": 104.0, + "Available on the hub": true, + "Model sha": "cb32f77e905cccbca1d970436fb0f5e6b58ee3c5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shitshow123\/mistral7b_sft_dpo", + "Average \u2b06\ufe0f": 30.0, + "ARC": 27.56, + "HellaSwag": 25.53, + "MMLU": 24.05, + "TruthfulQA": 49.68, + "Winogrande": 53.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "0191ecaf158b047b4c2f87edfcbe5c144c509d38", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yeen214\/test_llama2_ko_7b", + "Average \u2b06\ufe0f": 29.99, + "ARC": 29.95, + "HellaSwag": 26.94, + "MMLU": 25.62, + "TruthfulQA": 49.03, + "Winogrande": 48.38, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "45901e1d6ccb22f5ed8aec3f9dd366823fdd1c33", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vikp\/phi2", + "Average \u2b06\ufe0f": 29.98, + "ARC": 22.87, + "HellaSwag": 30.7, + "MMLU": 27.55, + "TruthfulQA": 46.1, + "Winogrande": 52.01, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9fd01ce09da870fc66af88616d43e53db642ef46", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-codellama-orca-platypus-13b-0.10e", + "Average \u2b06\ufe0f": 29.96, + "ARC": 28.92, + "HellaSwag": 25.76, + "MMLU": 25.28, + "TruthfulQA": 49.22, + "Winogrande": 50.59, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "119abfc73f9ce541a40779f167fe21e95faed4e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "IDEA-CCNL\/Ziya-LLaMA-13B-Pretrain-v1", + "Average \u2b06\ufe0f": 29.96, + "ARC": 27.99, + "HellaSwag": 26.0, + "MMLU": 27.04, + "TruthfulQA": 48.59, + "Winogrande": 50.12, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "826e83e411df32f358893ab21f5eae680499ae9a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "PygmalionAI\/pygmalion-350m", + "Average \u2b06\ufe0f": 29.95, + "ARC": 25.0, + "HellaSwag": 37.8, + "MMLU": 25.68, + "TruthfulQA": 40.41, + "Winogrande": 50.28, + "GSM8K": 0.53, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.35, + "Hub \u2764\ufe0f": 52.0, + "Available on the hub": false, + "Model sha": "d65832d913f6b396e2ffb64c373d9383c9da9303", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "senseable\/moe-x33", + "Average \u2b06\ufe0f": 29.95, + "ARC": 26.19, + "HellaSwag": 26.44, + "MMLU": 24.93, + "TruthfulQA": 51.14, + "Winogrande": 50.99, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 58.94, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2ce4ba7ce76392721be10c3c05b63853be98b686", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "hoskinson-center\/proofGPT-v0.1", + "Average \u2b06\ufe0f": 29.94, + "ARC": 22.87, + "HellaSwag": 28.66, + "MMLU": 25.96, + "TruthfulQA": 51.64, + "Winogrande": 50.43, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1e4dd330ca90c0ef6d77ca71bd49cbe3d71f26b8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shitshow123\/TinyLlama-1.1B-ChatStrong-DPO-PPO", + "Average \u2b06\ufe0f": 29.93, + "ARC": 30.38, + "HellaSwag": 25.75, + "MMLU": 24.17, + "TruthfulQA": 48.87, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8bf7ba0c5552fd7377c75e0ad8e6030a16234f86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fionazhang\/mistral-environment-adapter", + "Average \u2b06\ufe0f": 29.93, + "ARC": 29.18, + "HellaSwag": 25.81, + "MMLU": 25.38, + "TruthfulQA": 48.75, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "28910193dcfc67b615e918c6cd90162b9ef12446", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "marcchew\/LaMini-40k-Platypus2-7B", + "Average \u2b06\ufe0f": 29.91, + "ARC": 28.5, + "HellaSwag": 26.32, + "MMLU": 27.04, + "TruthfulQA": 47.39, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e8c03e43eab479a216b5f4f182a711c3624f38bd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/OPT-350M-Nerys-v2", + "Average \u2b06\ufe0f": 29.9, + "ARC": 23.63, + "HellaSwag": 35.49, + "MMLU": 25.91, + "TruthfulQA": 42.08, + "Winogrande": 51.62, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.35, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "59b1019c35ab17a7d77ea1ad32b45a8375ba6e89", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "postbot\/gpt2-medium-emailgen", + "Average \u2b06\ufe0f": 29.87, + "ARC": 26.45, + "HellaSwag": 34.31, + "MMLU": 24.1, + "TruthfulQA": 43.96, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": [ + "apache-2.0" + ], + "#Params (B)": 0.38, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1b9b03d00b2b300d3c04c37fe3782c180ef51a27", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "rishiraj\/cutie", + "Average \u2b06\ufe0f": 29.87, + "ARC": 26.96, + "HellaSwag": 27.02, + "MMLU": 24.17, + "TruthfulQA": 48.42, + "Winogrande": 52.64, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eab22794d6cf39c945f7dc326c9785a5abf88ddd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "doas\/test2", + "Average \u2b06\ufe0f": 29.87, + "ARC": 29.61, + "HellaSwag": 26.65, + "MMLU": 24.34, + "TruthfulQA": 48.49, + "Winogrande": 50.12, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f08d224deae510ebf1408ce38bc2610b1e4c77eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TheTravellingEngineer\/bloom-560m-RLHF", + "Average \u2b06\ufe0f": 29.86, + "ARC": 24.4, + "HellaSwag": 36.96, + "MMLU": 23.63, + "TruthfulQA": 40.76, + "Winogrande": 53.12, + "GSM8K": 0.3, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.56, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "b1769e92f325d8a28e7db1c21f133e6c85b84e78", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "TheBloke\/WizardLM-7B-uncensored-GPTQ", + "Average \u2b06\ufe0f": 29.86, + "ARC": 28.5, + "HellaSwag": 25.37, + "MMLU": 24.85, + "TruthfulQA": 50.86, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 9.04, + "Hub \u2764\ufe0f": 177.0, + "Available on the hub": true, + "Model sha": "cc30c031fd795ee3d3a50312ab4549415bfbdb46", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/santa1.1b_10e6", + "Average \u2b06\ufe0f": 29.84, + "ARC": 27.65, + "HellaSwag": 26.39, + "MMLU": 25.42, + "TruthfulQA": 49.4, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadCustomModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.23, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a27e0cf68c590772c74b981c8bd69ce6a559e776", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e6_run1", + "Average \u2b06\ufe0f": 29.84, + "ARC": 23.98, + "HellaSwag": 29.79, + "MMLU": 24.49, + "TruthfulQA": 48.59, + "Winogrande": 52.17, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "452e86748d96bab00fa5b7a576c49e3bc66fca6c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e5_30ep", + "Average \u2b06\ufe0f": 29.84, + "ARC": 25.6, + "HellaSwag": 30.3, + "MMLU": 23.9, + "TruthfulQA": 47.22, + "Winogrande": 52.01, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6b007a3eaf31ad1c1186b937704986882f473dbe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "uukuguy\/speechless-codellama-orca-platypus-13b-0.10e", + "Average \u2b06\ufe0f": 29.83, + "ARC": 28.75, + "HellaSwag": 25.88, + "MMLU": 25.36, + "TruthfulQA": 49.27, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "119abfc73f9ce541a40779f167fe21e95faed4e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "IDEA-CCNL\/Ziya-LLaMA-13B-v1", + "Average \u2b06\ufe0f": 29.82, + "ARC": 27.73, + "HellaSwag": 25.96, + "MMLU": 27.04, + "TruthfulQA": 48.65, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "gpl-3.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 262.0, + "Available on the hub": true, + "Model sha": "fccf34387d2c9f2f95ff59ae380e6de3718e41ff", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Panchovix\/WizardLM-33B-V1.0-Uncensored-SuperHOT-8k", + "Average \u2b06\ufe0f": 29.81, + "ARC": 25.43, + "HellaSwag": 31.97, + "MMLU": 23.43, + "TruthfulQA": 47.0, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "b6d0002b10d43ab48aa14e365d9e7b40655ec160", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vihangd\/neuralfalcon-1b-v1", + "Average \u2b06\ufe0f": 29.8, + "ARC": 26.37, + "HellaSwag": 26.56, + "MMLU": 25.93, + "TruthfulQA": 49.03, + "Winogrande": 50.75, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f788af66f22a933ad60e732ebaede3dfb5679bd4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "marcchew\/Marcoroni-7B-LaMini-40K", + "Average \u2b06\ufe0f": 29.78, + "ARC": 27.65, + "HellaSwag": 26.23, + "MMLU": 26.92, + "TruthfulQA": 47.4, + "Winogrande": 50.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "27868e4faed5d68d059c8c57dbd3e24e4933ca28", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MayaPH\/FinOPT-Franklin", + "Average \u2b06\ufe0f": 29.78, + "ARC": 27.73, + "HellaSwag": 24.91, + "MMLU": 23.12, + "TruthfulQA": 52.4, + "Winogrande": 50.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 1.32, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "1b13331834190bfe49a176f1661ba4d8309a5051", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "NEU-HAI\/mental-alpaca", + "Average \u2b06\ufe0f": 29.77, + "ARC": 28.58, + "HellaSwag": 26.02, + "MMLU": 27.04, + "TruthfulQA": 48.61, + "Winogrande": 48.38, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "f5f24d4a11ed52b4a224f365b6a694cf4e27c1bc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BreadAi\/PM_modelV2", + "Average \u2b06\ufe0f": 29.77, + "ARC": 25.09, + "HellaSwag": 26.45, + "MMLU": 26.14, + "TruthfulQA": 51.36, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4edde209eea33af491206f8651c0c47e70e08289", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "NobodyExistsOnTheInternet\/clown-SUV-4x70b", + "Average \u2b06\ufe0f": 29.76, + "ARC": 24.74, + "HellaSwag": 28.29, + "MMLU": 24.2, + "TruthfulQA": 48.81, + "Winogrande": 52.49, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 238.09, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "323a18e2bc3c2fada3daefe71befe616354fd6eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e5_10ep", + "Average \u2b06\ufe0f": 29.75, + "ARC": 23.98, + "HellaSwag": 31.24, + "MMLU": 24.79, + "TruthfulQA": 46.22, + "Winogrande": 52.25, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "af26f29ed2520cfe4bbb213457b956491ec68d6a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/TinyLlama-748M-Reason-With-Cinder-Test-2", + "Average \u2b06\ufe0f": 29.73, + "ARC": 24.66, + "HellaSwag": 34.5, + "MMLU": 25.15, + "TruthfulQA": 42.76, + "Winogrande": 50.51, + "GSM8K": 0.83, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.75, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ed18e6755a8d925d18a5d23d0005c600b7edf326", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt350m_10e6", + "Average \u2b06\ufe0f": 29.73, + "ARC": 23.98, + "HellaSwag": 32.36, + "MMLU": 24.96, + "TruthfulQA": 46.71, + "Winogrande": 50.36, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.33, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d1cba6a82e52f551953e1d47bdaca262a2989f9d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "hoskinson-center\/proofGPT-v0.1-6.7B", + "Average \u2b06\ufe0f": 29.72, + "ARC": 23.29, + "HellaSwag": 28.45, + "MMLU": 24.57, + "TruthfulQA": 50.87, + "Winogrande": 51.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "02f405f08ca0e5b1aaa90a7c3b11303b5f245102", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/Llama-68M-Chat-v1", + "Average \u2b06\ufe0f": 29.72, + "ARC": 23.29, + "HellaSwag": 28.27, + "MMLU": 25.18, + "TruthfulQA": 47.27, + "Winogrande": 54.3, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.07, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "f60895b5cf4e4f2c9387c6c851a4f6691c40ce95", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vihangd\/neuralfalcon-1b-v1", + "Average \u2b06\ufe0f": 29.72, + "ARC": 26.79, + "HellaSwag": 26.56, + "MMLU": 26.22, + "TruthfulQA": 48.93, + "Winogrande": 49.57, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f788af66f22a933ad60e732ebaede3dfb5679bd4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "danielpark\/gorani-100k-llama2-13b-instruct", + "Average \u2b06\ufe0f": 29.69, + "ARC": 28.07, + "HellaSwag": 26.3, + "MMLU": 25.17, + "TruthfulQA": 48.96, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "f7d38ee654e505ad7a454f192d5e3d85cb60b3b8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alnrg2arg\/test2", + "Average \u2b06\ufe0f": 29.69, + "ARC": 27.22, + "HellaSwag": 26.25, + "MMLU": 24.64, + "TruthfulQA": 50.14, + "Winogrande": 49.88, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Delta", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "6310110a31918d27d42116942bc2ba3941784ae9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TFLai\/gpt2-turkish-uncased", + "Average \u2b06\ufe0f": 29.68, + "ARC": 24.49, + "HellaSwag": 25.08, + "MMLU": 26.59, + "TruthfulQA": 52.3, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4807e7df1dfb9d60c6d98e3cfeff62cb6b9a1579", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "porkorbeef\/Llama-2-13b-12_153950", + "Average \u2b06\ufe0f": 29.68, + "ARC": 28.58, + "HellaSwag": 26.58, + "MMLU": 20.79, + "TruthfulQA": 49.03, + "Winogrande": 53.12, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ee9b0cf26f521b5cb2322d743880e8b6bfadb0b7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e5_40ep", + "Average \u2b06\ufe0f": 29.66, + "ARC": 24.23, + "HellaSwag": 29.9, + "MMLU": 23.75, + "TruthfulQA": 49.02, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "ba153179184a0d951ce8a9434d84b3a6a091f644", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Technoculture\/mtor", + "Average \u2b06\ufe0f": 29.65, + "ARC": 27.3, + "HellaSwag": 26.22, + "MMLU": 24.28, + "TruthfulQA": 49.68, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 11.6, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "2164456a751d3ba578b17df0a4b097d4e3ad8df1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "marcchew\/Platypus-2-7B-LaMini-14K", + "Average \u2b06\ufe0f": 29.64, + "ARC": 29.52, + "HellaSwag": 26.15, + "MMLU": 23.13, + "TruthfulQA": 48.29, + "Winogrande": 50.75, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "50199ba51c4d002cc86cf3fb2ac921ec52bf4828", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e5", + "Average \u2b06\ufe0f": 29.62, + "ARC": 24.66, + "HellaSwag": 31.23, + "MMLU": 26.45, + "TruthfulQA": 43.92, + "Winogrande": 51.46, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b1cc44b598222a3657b96be755cc35c1d541549f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vikash06\/doctorMistralLLM10k", + "Average \u2b06\ufe0f": 29.61, + "ARC": 27.22, + "HellaSwag": 27.45, + "MMLU": 25.95, + "TruthfulQA": 48.28, + "Winogrande": 48.78, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a0af93b8550a5eb5424cda986e6c91b603cebfe9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openbmb\/UltraRM-13b", + "Average \u2b06\ufe0f": 29.58, + "ARC": 28.16, + "HellaSwag": 26.13, + "MMLU": 25.96, + "TruthfulQA": 47.91, + "Winogrande": 49.33, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4b231ae58c15244e6e15f0d2f4e26ec37b846229", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vicgalle\/alpaca-7b", + "Average \u2b06\ufe0f": 29.57, + "ARC": 28.07, + "HellaSwag": 25.83, + "MMLU": 25.31, + "TruthfulQA": 48.49, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "7f22882125208d1f54765c21abf84fd162aa454a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mavihsrr\/GetCode-slerp", + "Average \u2b06\ufe0f": 29.57, + "ARC": 26.54, + "HellaSwag": 26.2, + "MMLU": 23.12, + "TruthfulQA": 49.78, + "Winogrande": 51.78, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.74, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c4e9a5c09be34872e7a1db125d851ae1210d15ff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SebastianSchramm\/Cerebras-GPT-111M-instruction", + "Average \u2b06\ufe0f": 29.57, + "ARC": 24.4, + "HellaSwag": 26.05, + "MMLU": 25.87, + "TruthfulQA": 49.46, + "Winogrande": 51.62, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.11, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "09f1ec782ae2243fc605b24eb13ec8d5e4fd2734", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "golaxy\/gogpt-560m", + "Average \u2b06\ufe0f": 29.56, + "ARC": 26.37, + "HellaSwag": 31.86, + "MMLU": 25.29, + "TruthfulQA": 43.12, + "Winogrande": 50.75, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.56, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "82bd8b88b95068eee614a35b790388c5d2415705", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HWERI\/pythia-70m-deduped-cleansharegpt", + "Average \u2b06\ufe0f": 29.56, + "ARC": 25.68, + "HellaSwag": 25.4, + "MMLU": 23.12, + "TruthfulQA": 51.15, + "Winogrande": 52.01, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.07, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6ea42abd94cb0017918f6fe5e71d78bcb7c75548", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/xglm-564M", + "Average \u2b06\ufe0f": 29.55, + "ARC": 24.57, + "HellaSwag": 34.64, + "MMLU": 25.18, + "TruthfulQA": 40.43, + "Winogrande": 52.25, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.56, + "Hub \u2764\ufe0f": 38.0, + "Available on the hub": true, + "Model sha": "f3059f01b98ccc877c673149e0178c0e957660f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/tinyllama-730M-test", + "Average \u2b06\ufe0f": 29.55, + "ARC": 25.09, + "HellaSwag": 33.82, + "MMLU": 24.43, + "TruthfulQA": 42.9, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.75, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "29b2c22fd13f0fb6e903f33998ba0866750854f8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Abe13\/juniper-certificate-Llama-2-7b-chat-hf", + "Average \u2b06\ufe0f": 29.55, + "ARC": 29.1, + "HellaSwag": 27.63, + "MMLU": 24.02, + "TruthfulQA": 48.23, + "Winogrande": 48.3, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "90ed388e5503c02f5e6ba8dbc7286687a85ce1c1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "NobodyExistsOnTheInternet\/code-llama-70b-python-instruct", + "Average \u2b06\ufe0f": 29.55, + "ARC": 29.61, + "HellaSwag": 25.66, + "MMLU": 23.5, + "TruthfulQA": 49.26, + "Winogrande": 49.25, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 68.98, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "b11a209df4f27f9db7464677dbb14fba4baf1c3c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/Medtulu-4x7B", + "Average \u2b06\ufe0f": 29.54, + "ARC": 28.75, + "HellaSwag": 25.74, + "MMLU": 24.41, + "TruthfulQA": 47.91, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 19.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b9b38d1b9039038d7d4e5177884bb35300f2fdf1", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e5_20ep", + "Average \u2b06\ufe0f": 29.54, + "ARC": 25.43, + "HellaSwag": 30.84, + "MMLU": 23.39, + "TruthfulQA": 46.49, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "5c4954bb2595cce1256f496d2374d2dee4f79e93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "winglian\/Llama-2-3b-hf", + "Average \u2b06\ufe0f": 29.53, + "ARC": 26.96, + "HellaSwag": 26.52, + "MMLU": 23.33, + "TruthfulQA": 50.71, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "293f071b223efd7959f9e1fac66285369aaa959d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ai-forever\/rugpt3large_based_on_gpt2", + "Average \u2b06\ufe0f": 29.53, + "ARC": 22.61, + "HellaSwag": 32.84, + "MMLU": 24.9, + "TruthfulQA": 43.39, + "Winogrande": 53.12, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 64.0, + "Available on the hub": false, + "Model sha": "8201db0de8deb68f25e7309db04d163b71970494", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "bigcode\/santacoder", + "Average \u2b06\ufe0f": 29.51, + "ARC": 26.28, + "HellaSwag": 25.6, + "MMLU": 25.89, + "TruthfulQA": 51.24, + "Winogrande": 48.07, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadCustomModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 319.0, + "Available on the hub": true, + "Model sha": "132eb6b6cedaf579c2f333f1ecd78a16d7e45978", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Cartinoe5930\/iDUS", + "Average \u2b06\ufe0f": 29.51, + "ARC": 27.73, + "HellaSwag": 26.65, + "MMLU": 24.91, + "TruthfulQA": 48.58, + "Winogrande": 49.17, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "680101b4b43110627f526cd4d05856cf624a6ce2", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "WangZeJun\/bloom-820m-chat", + "Average \u2b06\ufe0f": 29.5, + "ARC": 23.38, + "HellaSwag": 34.16, + "MMLU": 25.98, + "TruthfulQA": 40.32, + "Winogrande": 53.2, + "GSM8K": 0.0, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 0.75, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "f98b1f9c1bd358dd837d05d443d992c495497606", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "janhq\/supermario-v1", + "Average \u2b06\ufe0f": 29.49, + "ARC": 27.73, + "HellaSwag": 25.83, + "MMLU": 27.04, + "TruthfulQA": 47.27, + "Winogrande": 49.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "22a88e62529dc2cc95991478cd87e6c588237258", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "huggingtweets\/bladeecity-jerma985", + "Average \u2b06\ufe0f": 29.49, + "ARC": 22.87, + "HellaSwag": 30.53, + "MMLU": 26.56, + "TruthfulQA": 44.99, + "Winogrande": 52.01, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9bf3a0db7f6bc960c51f2c0dc6fb66ed982b0180", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "abhinand\/mistral7b-test001", + "Average \u2b06\ufe0f": 29.49, + "ARC": 24.66, + "HellaSwag": 26.78, + "MMLU": 23.12, + "TruthfulQA": 50.07, + "Winogrande": 52.33, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.58, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "52d285a1d9bdd52e50a4cd10b9de43f2f4332517", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Panchovix\/airoboros-33b-gpt4-1.2-SuperHOT-8k", + "Average \u2b06\ufe0f": 29.48, + "ARC": 24.66, + "HellaSwag": 31.23, + "MMLU": 23.13, + "TruthfulQA": 47.44, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "47c14f699cbbc9bd24458edd86eb70d87552b623", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "marcchew\/test1", + "Average \u2b06\ufe0f": 29.48, + "ARC": 27.65, + "HellaSwag": 26.17, + "MMLU": 24.55, + "TruthfulQA": 48.33, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7444355ad764584ef05805f58ccf174bb03e0f46", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "codeparrot\/codeparrot", + "Average \u2b06\ufe0f": 29.48, + "ARC": 21.67, + "HellaSwag": 28.34, + "MMLU": 25.55, + "TruthfulQA": 50.87, + "Winogrande": 50.2, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 94.0, + "Available on the hub": false, + "Model sha": "065248a99f051da363b1c2cbf05da943c8b6211b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "kz919\/mistral-7b-dpo-open-orca-flan-50k-synthetic-5-models", + "Average \u2b06\ufe0f": 29.48, + "ARC": 25.51, + "HellaSwag": 25.52, + "MMLU": 26.82, + "TruthfulQA": 48.81, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "abe276881262a4571412e6b1bf545c3d61c9e49e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/gpt-neo-125m", + "Average \u2b06\ufe0f": 29.47, + "ARC": 22.95, + "HellaSwag": 30.26, + "MMLU": 25.97, + "TruthfulQA": 45.58, + "Winogrande": 51.78, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.15, + "Hub \u2764\ufe0f": 151.0, + "Available on the hub": true, + "Model sha": "6cb0d322a3a484e99667e7cb240e22f1ac036b99", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "SilverCoder66\/Mistral-7B-Instruct-adapt-vbh", + "Average \u2b06\ufe0f": 29.47, + "ARC": 27.56, + "HellaSwag": 25.73, + "MMLU": 25.38, + "TruthfulQA": 47.95, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "76f61fe15cb9a1ac129d3e2980a91c9c7aaeec61", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "beomi\/KoAlpaca-Polyglot-5.8B", + "Average \u2b06\ufe0f": 29.46, + "ARC": 27.65, + "HellaSwag": 35.58, + "MMLU": 24.72, + "TruthfulQA": 39.74, + "Winogrande": 49.01, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.0, + "Hub \u2764\ufe0f": 53.0, + "Available on the hub": true, + "Model sha": "1051dacf82ca9fba0ba4a4ff67f1d98a81ef7a2e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BreadAi\/MusePy-1-2", + "Average \u2b06\ufe0f": 29.46, + "ARC": 25.77, + "HellaSwag": 25.94, + "MMLU": 25.22, + "TruthfulQA": 49.33, + "Winogrande": 50.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6c1725158a74a41a10f21696a48510d45b4b425b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "porkorbeef\/Llama-2-13b-public", + "Average \u2b06\ufe0f": 29.45, + "ARC": 29.95, + "HellaSwag": 26.65, + "MMLU": 22.74, + "TruthfulQA": 49.01, + "Winogrande": 48.38, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e1b32a8fcfc0f37fd5f50cf765151897574c73c7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "openbmb\/UltraLM-13b", + "Average \u2b06\ufe0f": 29.45, + "ARC": 29.44, + "HellaSwag": 25.99, + "MMLU": 23.12, + "TruthfulQA": 48.61, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 70.0, + "Available on the hub": false, + "Model sha": "2c732c2899fc329036d97e5c6f0a61eaff19d97d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "BEE-spoke-data\/smol_llama-220M-GQA", + "Average \u2b06\ufe0f": 29.44, + "ARC": 24.83, + "HellaSwag": 29.76, + "MMLU": 25.85, + "TruthfulQA": 44.55, + "Winogrande": 50.99, + "GSM8K": 0.68, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.22, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "2d144b9a69b3620110e8a14790d383076ac87925", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MBZUAI\/lamini-neo-125m", + "Average \u2b06\ufe0f": 29.44, + "ARC": 24.57, + "HellaSwag": 30.22, + "MMLU": 26.74, + "TruthfulQA": 42.85, + "Winogrande": 52.25, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f01e73ba67da96f6645be3067158cc493b0cbbcb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KoboldAI\/fairseq-dense-125M", + "Average \u2b06\ufe0f": 29.41, + "ARC": 24.06, + "HellaSwag": 34.14, + "MMLU": 23.98, + "TruthfulQA": 43.72, + "Winogrande": 50.59, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "XGLMForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.16, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "c8fb975220512b34e7b4a9fc570ca333ddcaf9b5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigcode\/tiny_starcoder_py", + "Average \u2b06\ufe0f": 29.41, + "ARC": 20.99, + "HellaSwag": 28.77, + "MMLU": 26.79, + "TruthfulQA": 47.68, + "Winogrande": 51.22, + "GSM8K": 0.99, + "Type": "pretrained", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigcode-openrail-m", + "#Params (B)": 0.16, + "Hub \u2764\ufe0f": 67.0, + "Available on the hub": true, + "Model sha": "8547527bef0bc927268c1653cce6948c5c242dd1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cerebras\/Cerebras-GPT-256M", + "Average \u2b06\ufe0f": 29.38, + "ARC": 22.01, + "HellaSwag": 28.99, + "MMLU": 26.83, + "TruthfulQA": 45.98, + "Winogrande": 52.49, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.26, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "d77812ac95aece1f1edef6745ae2a1b325ad01a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-160m-deduped", + "Average \u2b06\ufe0f": 29.38, + "ARC": 24.06, + "HellaSwag": 31.39, + "MMLU": 24.86, + "TruthfulQA": 44.34, + "Winogrande": 51.38, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.21, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "582159a2dfe3e712a8d47ae83dec95ae3bde8e7e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "breadlicker45\/dough-instruct-base-001", + "Average \u2b06\ufe0f": 29.37, + "ARC": 23.89, + "HellaSwag": 24.76, + "MMLU": 23.13, + "TruthfulQA": 53.4, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3e1b0bf0a887feeb342982eee4f6d8041772a7dd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "breadlicker45\/dough-base-001", + "Average \u2b06\ufe0f": 29.37, + "ARC": 23.89, + "HellaSwag": 24.76, + "MMLU": 23.13, + "TruthfulQA": 53.4, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e42b65191f97d786eadaba450f1d34baea470734", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Deci\/DeciCoder-1b", + "Average \u2b06\ufe0f": 29.37, + "ARC": 21.16, + "HellaSwag": 31.09, + "MMLU": 24.34, + "TruthfulQA": 47.05, + "Winogrande": 50.83, + "GSM8K": 1.74, + "Type": "pretrained", + "Architecture": "DeciCoderForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.11, + "Hub \u2764\ufe0f": 243.0, + "Available on the hub": true, + "Model sha": "af2ef45ef8cbe82eb7eb4074f260412bc14c7b11", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "amazingvince\/zephyr-smol_llama-100m-dpo-full", + "Average \u2b06\ufe0f": 29.37, + "ARC": 25.0, + "HellaSwag": 28.54, + "MMLU": 25.18, + "TruthfulQA": 45.75, + "Winogrande": 51.07, + "GSM8K": 0.68, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.1, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "be3400c89d66ed66f0aa96f1b8131604c118b67b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/lora_opt125m_10e5", + "Average \u2b06\ufe0f": 29.37, + "ARC": 22.78, + "HellaSwag": 31.22, + "MMLU": 25.18, + "TruthfulQA": 45.26, + "Winogrande": 51.78, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "?", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b9b45183b73c2ce10092d55e710e1e31b8463620", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e5_50ep", + "Average \u2b06\ufe0f": 29.37, + "ARC": 23.89, + "HellaSwag": 28.98, + "MMLU": 23.74, + "TruthfulQA": 48.3, + "Winogrande": 51.3, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "93dec43baa7693b669be5ddb24ce8909ffcad21d", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "yhyhy3\/med-orca-instruct-33b", + "Average \u2b06\ufe0f": 29.36, + "ARC": 27.39, + "HellaSwag": 25.89, + "MMLU": 25.37, + "TruthfulQA": 49.6, + "Winogrande": 47.91, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LlamaModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 33.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1d636881854338e571825226c712180da06be72c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "chargoddard\/SmolLlamix-8x101M-take2", + "Average \u2b06\ufe0f": 29.35, + "ARC": 23.98, + "HellaSwag": 28.43, + "MMLU": 25.07, + "TruthfulQA": 45.87, + "Winogrande": 52.25, + "GSM8K": 0.53, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.4, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c9f73e5f63546ca506bbae944ab546a8d8e42d24", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Technoculture\/PMCorca-2x13b", + "Average \u2b06\ufe0f": 29.35, + "ARC": 27.22, + "HellaSwag": 25.94, + "MMLU": 23.12, + "TruthfulQA": 49.72, + "Winogrande": 50.12, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 21.51, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3e32f163db0a5d25d00f9d1c8aff0a3666f2b25e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e2", + "Average \u2b06\ufe0f": 29.35, + "ARC": 23.21, + "HellaSwag": 31.41, + "MMLU": 26.55, + "TruthfulQA": 42.59, + "Winogrande": 52.17, + "GSM8K": 0.15, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8b738dcf7a2e38fc2e014dfc1c50f5ca30acccbf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/Mediquad-orca-20B", + "Average \u2b06\ufe0f": 29.35, + "ARC": 29.35, + "HellaSwag": 25.72, + "MMLU": 24.28, + "TruthfulQA": 48.42, + "Winogrande": 48.3, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 19.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6a5a811206e5c255dff8128334c06924347ae324", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Technoculture\/Medorca-4x7b", + "Average \u2b06\ufe0f": 29.35, + "ARC": 29.35, + "HellaSwag": 25.72, + "MMLU": 24.28, + "TruthfulQA": 48.42, + "Winogrande": 48.3, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 19.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "70fa312cca9f7d966c37ccb52f0ce6a2aa2fd3a0", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "FINDA-FIT\/llama-r", + "Average \u2b06\ufe0f": 29.34, + "ARC": 21.59, + "HellaSwag": 30.18, + "MMLU": 26.13, + "TruthfulQA": 45.38, + "Winogrande": 52.17, + "GSM8K": 0.61, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6bdde9a227da60c2db803024d5b2e3a53a41cf0b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "BEE-spoke-data\/smol_llama-220M-openhermes", + "Average \u2b06\ufe0f": 29.34, + "ARC": 25.17, + "HellaSwag": 28.98, + "MMLU": 26.17, + "TruthfulQA": 43.08, + "Winogrande": 52.01, + "GSM8K": 0.61, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.22, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "356848c3ced75332f875abf0896e0157a33abd8e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "BEE-spoke-data\/zephyr-220m-dpo-full", + "Average \u2b06\ufe0f": 29.33, + "ARC": 25.43, + "HellaSwag": 29.15, + "MMLU": 26.43, + "TruthfulQA": 43.44, + "Winogrande": 50.99, + "GSM8K": 0.53, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.22, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "58b624e62557ea56b525ead061b6bd92dae37970", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shahzebnaveed\/codeparrot-ds", + "Average \u2b06\ufe0f": 29.33, + "ARC": 25.26, + "HellaSwag": 25.75, + "MMLU": 23.11, + "TruthfulQA": 50.85, + "Winogrande": 50.99, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8b2a61c278488b60d12f574e3086d895c3635df6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "BEE-spoke-data\/zephyr-220m-sft-full", + "Average \u2b06\ufe0f": 29.33, + "ARC": 25.26, + "HellaSwag": 29.03, + "MMLU": 26.45, + "TruthfulQA": 43.23, + "Winogrande": 51.62, + "GSM8K": 0.38, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.22, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "49f3c45163e7eb65b9b9deb971f1f69424d5d261", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "nicholasKluge\/Aira-2-1B1", + "Average \u2b06\ufe0f": 29.32, + "ARC": 23.21, + "HellaSwag": 26.97, + "MMLU": 24.86, + "TruthfulQA": 50.63, + "Winogrande": 50.28, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "a53eb20b72ae86441566f99acc204d9bb527bf32", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "yyjjtt\/test-model", + "Average \u2b06\ufe0f": 29.31, + "ARC": 24.4, + "HellaSwag": 30.17, + "MMLU": 25.88, + "TruthfulQA": 44.59, + "Winogrande": 50.83, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3ea8330f61a47f16861415359f09ff0c6a210f27", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TaylorAI\/Flash-Llama-30M-20001", + "Average \u2b06\ufe0f": 29.31, + "ARC": 23.89, + "HellaSwag": 25.76, + "MMLU": 24.09, + "TruthfulQA": 51.29, + "Winogrande": 50.83, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "6ff84442217565875450bd7a0457121dcedf6b0b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Harshvir\/LaMini-Neo-1.3B-Mental-Health_lora", + "Average \u2b06\ufe0f": 29.3, + "ARC": 25.77, + "HellaSwag": 25.67, + "MMLU": 27.0, + "TruthfulQA": 48.21, + "Winogrande": 49.17, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "9f1c45d5ce88a8eaf7ec03b760a4adfb5fda07eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "klosax\/pythia-160m-deduped-step92k-193bt", + "Average \u2b06\ufe0f": 29.3, + "ARC": 24.23, + "HellaSwag": 32.33, + "MMLU": 24.54, + "TruthfulQA": 43.49, + "Winogrande": 50.83, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.16, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "9eac24dad1bd7194e38ce8083a0197cee456456c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bit-dny\/MindLLM", + "Average \u2b06\ufe0f": 29.28, + "ARC": 22.44, + "HellaSwag": 34.11, + "MMLU": 25.5, + "TruthfulQA": 43.48, + "Winogrande": 49.33, + "GSM8K": 0.83, + "Type": "pretrained", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "b3554c83555a098c94b626c3ab67247bfd024fb5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "bsp-albz\/llama2-13b-platypus-ckpt-1000", + "Average \u2b06\ufe0f": 29.28, + "ARC": 28.16, + "HellaSwag": 26.55, + "MMLU": 23.17, + "TruthfulQA": 48.79, + "Winogrande": 49.01, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d9f3e490df2134784afc3a86f5c617a9bab8db4d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "microsoft\/DialoGPT-large", + "Average \u2b06\ufe0f": 29.27, + "ARC": 23.38, + "HellaSwag": 25.77, + "MMLU": 23.81, + "TruthfulQA": 50.27, + "Winogrande": 52.41, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 242.0, + "Available on the hub": true, + "Model sha": "04e3e47b52dadbcf7688aa61a7ed0438ecf9184c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "voidful\/changpt-bart", + "Average \u2b06\ufe0f": 29.27, + "ARC": 28.67, + "HellaSwag": 26.41, + "MMLU": 23.12, + "TruthfulQA": 47.94, + "Winogrande": 49.49, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.18, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e3d26f736b8b47d5275421be6133b81bef84db7d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MayaPH\/FinOPT-Lincoln", + "Average \u2b06\ufe0f": 29.27, + "ARC": 26.71, + "HellaSwag": 25.6, + "MMLU": 23.0, + "TruthfulQA": 50.59, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 0.33, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7ddc381fa3968df22f72acb6cf03b75d3ac49661", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "victor123\/WizardLM-13B-1.0", + "Average \u2b06\ufe0f": 29.27, + "ARC": 28.5, + "HellaSwag": 25.97, + "MMLU": 23.12, + "TruthfulQA": 48.61, + "Winogrande": 49.41, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 12.85, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2ea86d3c02ca0c2abb086a2145e1e85eaea4a23e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "max-2022\/test_mistral2", + "Average \u2b06\ufe0f": 29.27, + "ARC": 27.9, + "HellaSwag": 25.32, + "MMLU": 24.74, + "TruthfulQA": 49.1, + "Winogrande": 48.54, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3c74c0654e9de8e19356c5c70eebf15dddd8840e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Isotonic\/smol_llama-4x220M-MoE", + "Average \u2b06\ufe0f": 29.25, + "ARC": 25.09, + "HellaSwag": 29.24, + "MMLU": 25.88, + "TruthfulQA": 43.92, + "Winogrande": 51.22, + "GSM8K": 0.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.6, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5d2a0bcaa25ae455a8111a385c95b3827c972e26", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "BEE-spoke-data\/NanoLlama-GQA-L10-A32_KV8-v13-KI", + "Average \u2b06\ufe0f": 29.23, + "ARC": 23.81, + "HellaSwag": 29.39, + "MMLU": 25.37, + "TruthfulQA": 44.77, + "Winogrande": 51.14, + "GSM8K": 0.91, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.22, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "29fc3a802ee639be914d2a54fa6d9f595036ecf2", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "FabbriSimo01\/GPT_Large_Quantized", + "Average \u2b06\ufe0f": 29.21, + "ARC": 27.05, + "HellaSwag": 26.29, + "MMLU": 24.12, + "TruthfulQA": 48.46, + "Winogrande": 49.33, + "GSM8K": 0.0, + "Type": "", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "unknown", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c2df1904aa18de22d03ba0fee925e831d8468898", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/gpt2-dolly", + "Average \u2b06\ufe0f": 29.21, + "ARC": 22.7, + "HellaSwag": 30.15, + "MMLU": 25.81, + "TruthfulQA": 44.97, + "Winogrande": 51.46, + "GSM8K": 0.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "7e75e6f4626437305e4d3e7b2aa36f617c517247", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "concedo\/Pythia-70M-ChatSalad", + "Average \u2b06\ufe0f": 29.2, + "ARC": 20.99, + "HellaSwag": 27.28, + "MMLU": 24.78, + "TruthfulQA": 49.74, + "Winogrande": 52.41, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.1, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "692289413c47c219cf83b1596783a8e9223541eb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yukang\/Llama-2-7b-longlora-32k-ft", + "Average \u2b06\ufe0f": 29.2, + "ARC": 27.9, + "HellaSwag": 25.61, + "MMLU": 23.08, + "TruthfulQA": 49.57, + "Winogrande": 49.01, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "ab48674ffc55568ffe2a1207ef0e711c2febbaaf", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "BEE-spoke-data\/smol_llama-220M-open_instruct", + "Average \u2b06\ufe0f": 29.19, + "ARC": 25.0, + "HellaSwag": 29.71, + "MMLU": 26.11, + "TruthfulQA": 44.06, + "Winogrande": 50.28, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.22, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6d4735f86c74c881857659efb7d981c5f50bee77", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "microsoft\/DialoGPT-small", + "Average \u2b06\ufe0f": 29.19, + "ARC": 25.77, + "HellaSwag": 25.79, + "MMLU": 25.81, + "TruthfulQA": 47.49, + "Winogrande": 50.28, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.18, + "Hub \u2764\ufe0f": 75.0, + "Available on the hub": true, + "Model sha": "97d0fec744c2cb4d48f5db51d17e3258e185858e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "Cartinoe5930\/DARE-Merging", + "Average \u2b06\ufe0f": 29.19, + "ARC": 25.26, + "HellaSwag": 26.11, + "MMLU": 23.68, + "TruthfulQA": 48.31, + "Winogrande": 51.7, + "GSM8K": 0.08, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bd5072000c2d7db7c72ec8286d79e00671188605", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "fionazhang\/mistral-environment-all", + "Average \u2b06\ufe0f": 29.18, + "ARC": 29.44, + "HellaSwag": 25.89, + "MMLU": 23.12, + "TruthfulQA": 47.92, + "Winogrande": 48.7, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ba2832b0dbd70860408d7786026549407c951a8a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "buildingthemoon\/testfinetunedmodel", + "Average \u2b06\ufe0f": 29.18, + "ARC": 25.85, + "HellaSwag": 31.4, + "MMLU": 26.07, + "TruthfulQA": 40.75, + "Winogrande": 50.99, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9efeae0561a9af68ea7f9b26c5184838760372bc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Facebook\/OPT-125M", + "Average \u2b06\ufe0f": 29.17, + "ARC": 22.87, + "HellaSwag": 31.44, + "MMLU": 26.01, + "TruthfulQA": 42.87, + "Winogrande": 51.62, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "27dcfa74d334bc871f3234de431e71c6eeba5dd6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yukang\/Llama-2-13b-longlora-16k-ft", + "Average \u2b06\ufe0f": 29.17, + "ARC": 25.85, + "HellaSwag": 27.6, + "MMLU": 23.1, + "TruthfulQA": 48.89, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "5f0cfdef590fc9bd7642042fb5f1ed9679260b93", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "microsoft\/CodeGPT-small-py", + "Average \u2b06\ufe0f": 29.17, + "ARC": 22.7, + "HellaSwag": 27.26, + "MMLU": 25.05, + "TruthfulQA": 51.23, + "Winogrande": 48.78, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 21.0, + "Available on the hub": false, + "Model sha": "e5f31df92bfb7b7a808ea8d1c7557488e1bdff7f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Dans-DiscountModels\/TinyMistral-v2.5-MiniPile-Guidelines-E1", + "Average \u2b06\ufe0f": 29.16, + "ARC": 26.54, + "HellaSwag": 25.65, + "MMLU": 23.44, + "TruthfulQA": 49.9, + "Winogrande": 49.41, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "11a6744bc71fa05bc14e0944001c7a5c318440f0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Dans-DiscountModels\/TinyMistral-v2.5-MiniPile-Guidelines-E1", + "Average \u2b06\ufe0f": 29.15, + "ARC": 26.45, + "HellaSwag": 25.68, + "MMLU": 23.53, + "TruthfulQA": 49.85, + "Winogrande": 49.41, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "11a6744bc71fa05bc14e0944001c7a5c318440f0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "pszemraj\/pythia-31m-KI_v1-2048-scratch", + "Average \u2b06\ufe0f": 29.15, + "ARC": 23.12, + "HellaSwag": 25.23, + "MMLU": 23.12, + "TruthfulQA": 51.67, + "Winogrande": 51.78, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b29a3229f8d5317adeabafeb20677ec7bea9d703", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MaziyarPanahi\/UNA-34Beagles-32K-bf16-v1-GPTQ", + "Average \u2b06\ufe0f": 29.15, + "ARC": 26.11, + "HellaSwag": 26.29, + "MMLU": 24.43, + "TruthfulQA": 47.27, + "Winogrande": 50.83, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 43.23, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7094ef1fc4e032cf2c03a2f43f3db5e814bce318", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "facebook\/opt-125m", + "Average \u2b06\ufe0f": 29.15, + "ARC": 22.87, + "HellaSwag": 31.47, + "MMLU": 26.02, + "TruthfulQA": 42.87, + "Winogrande": 51.62, + "GSM8K": 0.08, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 103.0, + "Available on the hub": true, + "Model sha": "3d2b5f275bdf882b8775f902e1bfdb790e2cfc32", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e3", + "Average \u2b06\ufe0f": 29.15, + "ARC": 22.87, + "HellaSwag": 31.01, + "MMLU": 26.66, + "TruthfulQA": 42.52, + "Winogrande": 51.85, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1b7a1e2cce264be61f67360011b4a85824e27caa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ogimgio\/gpt-neo-125m-neurallinguisticpioneers", + "Average \u2b06\ufe0f": 29.15, + "ARC": 22.44, + "HellaSwag": 30.36, + "MMLU": 25.14, + "TruthfulQA": 45.64, + "Winogrande": 51.22, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "515fd7753c5fecbf4a2951f7cebb2846d91324b3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "kodonho\/Momo-70b-DPO-mixed", + "Average \u2b06\ufe0f": 29.14, + "ARC": 26.28, + "HellaSwag": 24.98, + "MMLU": 23.06, + "TruthfulQA": 48.85, + "Winogrande": 51.7, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "mit", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7d93ee866df83b1924289512cc6c07c3d8800b43", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "cerebras\/Cerebras-GPT-590M", + "Average \u2b06\ufe0f": 29.14, + "ARC": 23.72, + "HellaSwag": 32.4, + "MMLU": 25.97, + "TruthfulQA": 44.15, + "Winogrande": 48.15, + "GSM8K": 0.45, + "Type": "", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.59, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "67a653304fd782a34906d59f3795a37f9e053397", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "roneneldan\/TinyStories-1M", + "Average \u2b06\ufe0f": 29.14, + "ARC": 23.46, + "HellaSwag": 25.23, + "MMLU": 24.57, + "TruthfulQA": 49.4, + "Winogrande": 52.17, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 27.0, + "Available on the hub": false, + "Model sha": "8cd14d5339178f1b285f55baee14a0deff7103ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TheBloke\/Llama-2-7b-Chat-AWQ", + "Average \u2b06\ufe0f": 29.14, + "ARC": 27.22, + "HellaSwag": 25.48, + "MMLU": 24.67, + "TruthfulQA": 49.95, + "Winogrande": 47.51, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 1.13, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a065961fd627aa3b3e6dde21e77fd5e20f712189", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "euclaise\/crow-1b", + "Average \u2b06\ufe0f": 29.12, + "ARC": 25.51, + "HellaSwag": 25.87, + "MMLU": 24.8, + "TruthfulQA": 48.28, + "Winogrande": 49.41, + "GSM8K": 0.83, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "dbbcb8892474ce1571297eb68b6c1ef971fa0cf8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yash21\/TinyYi-7B-Test", + "Average \u2b06\ufe0f": 29.11, + "ARC": 26.88, + "HellaSwag": 26.14, + "MMLU": 24.41, + "TruthfulQA": 46.35, + "Winogrande": 50.91, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e680a6b8244e9a4871aa419e2faca079d4f42381", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yash21\/TinyYi-7b-Test", + "Average \u2b06\ufe0f": 29.11, + "ARC": 26.88, + "HellaSwag": 26.14, + "MMLU": 24.41, + "TruthfulQA": 46.35, + "Winogrande": 50.91, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 6.06, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e680a6b8244e9a4871aa419e2faca079d4f42381", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Aspik101\/tulu-7b-instruct-pl-lora_unload", + "Average \u2b06\ufe0f": 29.11, + "ARC": 28.67, + "HellaSwag": 26.05, + "MMLU": 23.12, + "TruthfulQA": 48.61, + "Winogrande": 48.22, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "962d4e5d8da5a4ec0ec047b6f8f08f1bb9e509fe", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "TurkuNLP\/gpt3-finnish-large", + "Average \u2b06\ufe0f": 29.11, + "ARC": 21.76, + "HellaSwag": 32.88, + "MMLU": 24.11, + "TruthfulQA": 44.35, + "Winogrande": 51.54, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "BloomModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "b9a3dd97387fc70d07010d469888a918842d3449", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "euclaise\/gpt-neox-122m-minipile-digits", + "Average \u2b06\ufe0f": 29.1, + "ARC": 20.73, + "HellaSwag": 27.03, + "MMLU": 25.31, + "TruthfulQA": 49.19, + "Winogrande": 52.33, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc0-1.0", + "#Params (B)": 0.17, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "3e9187385d31234b04021ddc8b03cbd5cfef9fb4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/160M-TinyLLama-Mini-Cinder", + "Average \u2b06\ufe0f": 29.09, + "ARC": 24.66, + "HellaSwag": 28.16, + "MMLU": 25.09, + "TruthfulQA": 44.08, + "Winogrande": 52.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "a82c33fd5feadf6034e1df1e7dad4fc9993bf065", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yukang\/Llama-2-7b-longlora-100k-ft", + "Average \u2b06\ufe0f": 29.08, + "ARC": 28.16, + "HellaSwag": 25.43, + "MMLU": 23.48, + "TruthfulQA": 49.06, + "Winogrande": 48.38, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 50.0, + "Available on the hub": false, + "Model sha": "242c6469cab41b41d30826e850afa4687e422f24", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "KnutJaegersberg\/internlm-20b-llamafied", + "Average \u2b06\ufe0f": 29.08, + "ARC": 26.79, + "HellaSwag": 26.4, + "MMLU": 25.4, + "TruthfulQA": 48.06, + "Winogrande": 47.83, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "LlamaModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 19.56, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f859dfb710431ad6cd7d4e8389297d0f0b196278", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e5_1ep", + "Average \u2b06\ufe0f": 29.05, + "ARC": 23.46, + "HellaSwag": 30.9, + "MMLU": 26.73, + "TruthfulQA": 42.53, + "Winogrande": 50.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "fc31db73f21f8ca07e1a72ffab8684a00f99cfc8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "anas-awadalla\/mpt-1b-redpajama-200b", + "Average \u2b06\ufe0f": 29.05, + "ARC": 25.77, + "HellaSwag": 26.08, + "MMLU": 24.5, + "TruthfulQA": 47.57, + "Winogrande": 50.36, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MosaicGPT", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "fc98636655efb7c091bbe5d8014eb138ddfc5471", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BreadAi\/gpt-YA-1-1_160M", + "Average \u2b06\ufe0f": 29.03, + "ARC": 22.95, + "HellaSwag": 27.29, + "MMLU": 26.25, + "TruthfulQA": 47.02, + "Winogrande": 50.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.16, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "b9b3577df726f7984721e4d73741296db50fa782", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alibidaran\/medical_transcription_generator", + "Average \u2b06\ufe0f": 29.03, + "ARC": 22.78, + "HellaSwag": 30.6, + "MMLU": 23.84, + "TruthfulQA": 46.5, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "f622239151c89c2db0f1cef495d1b42afd16ce64", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-160m", + "Average \u2b06\ufe0f": 29.02, + "ARC": 22.78, + "HellaSwag": 30.34, + "MMLU": 24.95, + "TruthfulQA": 44.26, + "Winogrande": 51.54, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.21, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "50f5173d932e8e61f858120bcb800b97af589f46", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Locutusque\/gpt2-conversational-or-qa", + "Average \u2b06\ufe0f": 29.01, + "ARC": 21.42, + "HellaSwag": 27.61, + "MMLU": 26.51, + "TruthfulQA": 47.31, + "Winogrande": 51.14, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "f881c740c82ee9bc3191b886ad53f18d741960ea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhishek\/hepu-o4zf-ravz-7-0", + "Average \u2b06\ufe0f": 29.01, + "ARC": 24.49, + "HellaSwag": 25.36, + "MMLU": 23.27, + "TruthfulQA": 51.67, + "Winogrande": 49.25, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b73d869edfc259dea27c15d06cf65ee08ec3c2c7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "klosax\/pythia-70m-deduped-step44k-92bt", + "Average \u2b06\ufe0f": 29.0, + "ARC": 22.1, + "HellaSwag": 28.21, + "MMLU": 26.03, + "TruthfulQA": 46.12, + "Winogrande": 51.54, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.07, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "aac86fff08965d84d8bfc3e7c14559d48b8c4c99", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "chargoddard\/SmolLlamix-8x101M", + "Average \u2b06\ufe0f": 28.98, + "ARC": 22.7, + "HellaSwag": 28.5, + "MMLU": 24.69, + "TruthfulQA": 46.09, + "Winogrande": 51.3, + "GSM8K": 0.61, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.4, + "Hub \u2764\ufe0f": 11.0, + "Available on the hub": true, + "Model sha": "02909f5f76561cc02059b0802d4b894f4a8f9b5a", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "huggingtweets\/jerma985", + "Average \u2b06\ufe0f": 28.97, + "ARC": 21.67, + "HellaSwag": 30.91, + "MMLU": 26.57, + "TruthfulQA": 44.01, + "Winogrande": 50.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "816206ad02a397161be78dcb70eeda67e0c53132", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mzio\/hedgehog-mistral_7b-alpaca_clean-smd_lora_1e_3", + "Average \u2b06\ufe0f": 28.97, + "ARC": 23.29, + "HellaSwag": 25.47, + "MMLU": 23.5, + "TruthfulQA": 50.65, + "Winogrande": 50.91, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.28, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "43f7dc636fbd7811c93d6123c5637db9701a6bb5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "BEE-spoke-data\/smol_llama-101M-GQA", + "Average \u2b06\ufe0f": 28.97, + "ARC": 23.55, + "HellaSwag": 28.77, + "MMLU": 24.24, + "TruthfulQA": 45.76, + "Winogrande": 50.67, + "GSM8K": 0.83, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.1, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "cac68b3377fd0a1eb1aca92a2e661d81f59d8b08", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BEE-spoke-data\/smol_llama-101M-GQA", + "Average \u2b06\ufe0f": 28.96, + "ARC": 23.46, + "HellaSwag": 28.73, + "MMLU": 24.35, + "TruthfulQA": 45.8, + "Winogrande": 50.67, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.1, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "cac68b3377fd0a1eb1aca92a2e661d81f59d8b08", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "WizardLM\/WizardLM-30B-V1.0", + "Average \u2b06\ufe0f": 28.96, + "ARC": 27.39, + "HellaSwag": 25.94, + "MMLU": 23.12, + "TruthfulQA": 48.61, + "Winogrande": 48.7, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": false, + "Model sha": "815e2dd7daabe446c429f3c9f70ef01582528f81", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "concedo\/OPT-19M-ChatSalad", + "Average \u2b06\ufe0f": 28.96, + "ARC": 24.4, + "HellaSwag": 25.15, + "MMLU": 23.12, + "TruthfulQA": 51.36, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.02, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "3930ca6bf3976e9b603815403cb373398ae509e5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TW3PartnersLLM\/TW3-v1-AlpacaSmaug-30B", + "Average \u2b06\ufe0f": 28.95, + "ARC": 26.96, + "HellaSwag": 26.11, + "MMLU": 23.11, + "TruthfulQA": 48.45, + "Winogrande": 49.09, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 30.41, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "789045861027df1adf1c4d5ae5cde11f534de35e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "WizardLM\/WizardLM-30B-V1.0", + "Average \u2b06\ufe0f": 28.95, + "ARC": 27.39, + "HellaSwag": 25.94, + "MMLU": 23.12, + "TruthfulQA": 48.61, + "Winogrande": 48.62, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "", + "#Params (B)": 30.0, + "Hub \u2764\ufe0f": 74.0, + "Available on the hub": false, + "Model sha": "815e2dd7daabe446c429f3c9f70ef01582528f81", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BreadAi\/DiscordPy", + "Average \u2b06\ufe0f": 28.94, + "ARC": 23.29, + "HellaSwag": 26.15, + "MMLU": 25.04, + "TruthfulQA": 48.16, + "Winogrande": 50.99, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "a5405585aec0b60c5de7d942ccd58421fe9239be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-70m", + "Average \u2b06\ufe0f": 28.93, + "ARC": 21.59, + "HellaSwag": 27.29, + "MMLU": 25.9, + "TruthfulQA": 47.06, + "Winogrande": 51.46, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2ab25ed47af79376eed2baaf8bbb7a192a0c73ff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "xformAI\/opt-125m-gqa-ub-6-best-for-KV-cache", + "Average \u2b06\ufe0f": 28.93, + "ARC": 24.23, + "HellaSwag": 25.0, + "MMLU": 23.12, + "TruthfulQA": 49.53, + "Winogrande": 51.7, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "078bcddaf1abf77d8c44b05b8f2e1d1c0a82855d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "vilm\/Mixsmol-4x400M-v0.1-epoch2", + "Average \u2b06\ufe0f": 28.92, + "ARC": 23.55, + "HellaSwag": 32.6, + "MMLU": 25.26, + "TruthfulQA": 39.24, + "Winogrande": 52.64, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.77, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "3741dbdbb179f58d07ac9f2d082fb7a6cffe7613", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "anton-l\/gpt-j-tiny-random", + "Average \u2b06\ufe0f": 28.92, + "ARC": 26.37, + "HellaSwag": 25.76, + "MMLU": 24.46, + "TruthfulQA": 47.44, + "Winogrande": 49.49, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTJForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "feea91564dac0081f73aeb6744979c6cfe553fff", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Corianas\/590m", + "Average \u2b06\ufe0f": 28.88, + "ARC": 24.15, + "HellaSwag": 31.91, + "MMLU": 26.61, + "TruthfulQA": 42.19, + "Winogrande": 48.38, + "GSM8K": 0.08, + "Type": "", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.67, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ec721c97ef0e6ebfc578ab98b3ff6e2bd19b3e27", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BreadAi\/gpt-YA-1-1_70M", + "Average \u2b06\ufe0f": 28.88, + "ARC": 22.53, + "HellaSwag": 27.37, + "MMLU": 25.38, + "TruthfulQA": 47.09, + "Winogrande": 50.91, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.07, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "218e8da522cf6fb5566314f37624f27412ae2259", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cyberagent\/open-calm-large", + "Average \u2b06\ufe0f": 28.88, + "ARC": 20.73, + "HellaSwag": 29.56, + "MMLU": 25.23, + "TruthfulQA": 46.52, + "Winogrande": 51.14, + "GSM8K": 0.08, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "f9b7a3222967b15169a09bcc86b118ac68a1ad62", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "qblocks\/gpt2_137m_DolphinCoder", + "Average \u2b06\ufe0f": 28.87, + "ARC": 21.84, + "HellaSwag": 31.35, + "MMLU": 25.4, + "TruthfulQA": 41.58, + "Winogrande": 52.01, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "906d8a02bdb444159b189a153f1f5589071ed74e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Zangs3011\/gpt2_137m_DolphinCoder", + "Average \u2b06\ufe0f": 28.87, + "ARC": 21.84, + "HellaSwag": 31.35, + "MMLU": 25.4, + "TruthfulQA": 41.58, + "Winogrande": 52.01, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a558223f774bbd315d1a3890d93ab80dc720fbb1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "microsoft\/DialoGPT-medium", + "Average \u2b06\ufe0f": 28.86, + "ARC": 24.49, + "HellaSwag": 26.21, + "MMLU": 25.84, + "TruthfulQA": 47.06, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 283.0, + "Available on the hub": true, + "Model sha": "9d5c5fadcc072b693fb5a5e29416bbf3f503c26c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Quake24\/easyTermsSummerizer", + "Average \u2b06\ufe0f": 28.86, + "ARC": 25.77, + "HellaSwag": 25.81, + "MMLU": 23.12, + "TruthfulQA": 47.69, + "Winogrande": 50.75, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.41, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8df9f96cc14be8f681c40bd1672b3f3540b70e31", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BFauber\/opt125m_10e4", + "Average \u2b06\ufe0f": 28.85, + "ARC": 22.95, + "HellaSwag": 30.9, + "MMLU": 26.66, + "TruthfulQA": 42.88, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "502d29fa88d682b5cc0bbd44e5815c2d0c955f3f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MayaPH\/FinOPT-Washington", + "Average \u2b06\ufe0f": 28.85, + "ARC": 25.17, + "HellaSwag": 26.25, + "MMLU": 24.83, + "TruthfulQA": 45.8, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "cdd8a6cde7902de39757cf31d73af1f51df0d8e8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "pszemraj\/pythia-31m-goodwiki-deduped-2048-scratch", + "Average \u2b06\ufe0f": 28.85, + "ARC": 23.12, + "HellaSwag": 25.66, + "MMLU": 23.11, + "TruthfulQA": 51.32, + "Winogrande": 49.88, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "01a3cd918dd7c233bc0c3c0c948a9a462a5359d1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BreadAi\/StoryPy", + "Average \u2b06\ufe0f": 28.85, + "ARC": 22.35, + "HellaSwag": 26.19, + "MMLU": 24.37, + "TruthfulQA": 49.1, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.1, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "5c32081bd3bc1404c2f5b8dbb6f888048bcb7cd7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "postbot\/distilgpt2-emailgen", + "Average \u2b06\ufe0f": 28.84, + "ARC": 21.76, + "HellaSwag": 27.52, + "MMLU": 25.97, + "TruthfulQA": 46.17, + "Winogrande": 51.62, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.09, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "fe96d63cc2edcbd1ae444ada293cc59d1e01a6ad", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "saarvajanik\/facebook-opt-6.7b-gqa-ub-16-best-for-KV-cache", + "Average \u2b06\ufe0f": 28.84, + "ARC": 23.04, + "HellaSwag": 25.94, + "MMLU": 23.12, + "TruthfulQA": 48.99, + "Winogrande": 51.93, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4b01e3b68eadfeffec10ea017e6c1249c58a8d46", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "ethzanalytics\/pythia-31m", + "Average \u2b06\ufe0f": 28.81, + "ARC": 21.84, + "HellaSwag": 27.0, + "MMLU": 24.97, + "TruthfulQA": 49.1, + "Winogrande": 49.72, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "eeea0b6b80603d162fe7de4e80a5bf4a8e9c6207", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Yukang\/Llama-2-7b-longlora-16k-ft", + "Average \u2b06\ufe0f": 28.81, + "ARC": 26.37, + "HellaSwag": 26.37, + "MMLU": 23.75, + "TruthfulQA": 47.76, + "Winogrande": 48.62, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "c86de31b80866d047e680e08dbd3572e2965d4c5", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "ByteWave\/Yi-8B-Llama", + "Average \u2b06\ufe0f": 28.78, + "ARC": 25.68, + "HellaSwag": 26.79, + "MMLU": 24.14, + "TruthfulQA": 47.79, + "Winogrande": 48.3, + "GSM8K": 0.0, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 8.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4f3f4d73ff3962487d1c51702b02d795bf1f33a4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nthngdy\/pythia-owt2-70m-100k", + "Average \u2b06\ufe0f": 28.78, + "ARC": 20.9, + "HellaSwag": 28.34, + "MMLU": 25.02, + "TruthfulQA": 45.12, + "Winogrande": 53.28, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.07, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b288893319b6cdce499148f4482043c350116560", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Locutusque\/TinyMistral-248M-v2", + "Average \u2b06\ufe0f": 28.78, + "ARC": 21.25, + "HellaSwag": 26.56, + "MMLU": 23.39, + "TruthfulQA": 49.6, + "Winogrande": 51.85, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.25, + "Hub \u2764\ufe0f": 13.0, + "Available on the hub": true, + "Model sha": "937ed7abdec98b7a9868b95e3b8a0d757b902325", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Tincando\/fiction_story_generator", + "Average \u2b06\ufe0f": 28.77, + "ARC": 23.29, + "HellaSwag": 28.68, + "MMLU": 26.72, + "TruthfulQA": 43.79, + "Winogrande": 50.12, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": false, + "Model sha": "377b080cf96e10d50289aa3e1fd79c330265f45a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Corianas\/256_5epoch", + "Average \u2b06\ufe0f": 28.76, + "ARC": 22.27, + "HellaSwag": 28.99, + "MMLU": 26.62, + "TruthfulQA": 41.71, + "Winogrande": 52.72, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 0.32, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b1fe75844a07832acd405a4d989a26f6ab7b1c00", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "binbi\/SF-72B-V1.8.6-V1.2", + "Average \u2b06\ufe0f": 28.75, + "ARC": 26.28, + "HellaSwag": 24.87, + "MMLU": 23.03, + "TruthfulQA": 48.78, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f894446c80611e3fc174e4cf3af0e149a316b9bb", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "binbi\/SF-72B-V1", + "Average \u2b06\ufe0f": 28.75, + "ARC": 26.28, + "HellaSwag": 24.87, + "MMLU": 23.03, + "TruthfulQA": 48.78, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "39e00bb5cbebecb7b62f3b696423127e6ca5283b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Tensoic\/Qwixtral-4x1.8B-SFT", + "Average \u2b06\ufe0f": 28.75, + "ARC": 21.42, + "HellaSwag": 24.96, + "MMLU": 23.42, + "TruthfulQA": 50.15, + "Winogrande": 52.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 1.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "17b2e9b0d8fa62575e5192299dd3d9f05eb42765", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "abhiramtirumala\/DialoGPT-sarcastic-medium", + "Average \u2b06\ufe0f": 28.73, + "ARC": 23.29, + "HellaSwag": 25.93, + "MMLU": 23.76, + "TruthfulQA": 46.04, + "Winogrande": 53.35, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": false, + "Model sha": "292596e120591887383011c4520bc5b57e7e8993", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "TW3PartnersLLM\/TW3-v2-AlpacaSmaug-72B", + "Average \u2b06\ufe0f": 28.73, + "ARC": 25.77, + "HellaSwag": 25.23, + "MMLU": 23.0, + "TruthfulQA": 48.65, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "other", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d251bc926a483153b466beeced045dbdad699a2c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Felladrin\/Smol-Llama-101M-Chat-v1", + "Average \u2b06\ufe0f": 28.73, + "ARC": 22.87, + "HellaSwag": 28.69, + "MMLU": 24.93, + "TruthfulQA": 45.76, + "Winogrande": 50.04, + "GSM8K": 0.08, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.1, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "b7c10b0e04ef6f9811ac7f57b3a947546d288eea", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "nthngdy\/pythia-owt2-70m-50k", + "Average \u2b06\ufe0f": 28.71, + "ARC": 21.5, + "HellaSwag": 28.15, + "MMLU": 25.7, + "TruthfulQA": 44.5, + "Winogrande": 52.41, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.07, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9fce9b8252f7891dbd50299a8c3bd71cd25454db", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "distilgpt2", + "Average \u2b06\ufe0f": 28.71, + "ARC": 22.27, + "HellaSwag": 27.58, + "MMLU": 24.81, + "TruthfulQA": 44.49, + "Winogrande": 53.12, + "GSM8K": 0.0, + "Type": "", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.09, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "38cc92ec43315abd5136313225e95acc5986876c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "HWERI\/pythia-70m-deduped-cleansharegpt-en", + "Average \u2b06\ufe0f": 28.71, + "ARC": 21.16, + "HellaSwag": 27.16, + "MMLU": 25.24, + "TruthfulQA": 48.57, + "Winogrande": 50.12, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.07, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "a97ff56bc68a81a9f6147f1590e53511246d1040", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "BEE-spoke-data\/verysmol_llama-v11-KIx2", + "Average \u2b06\ufe0f": 28.7, + "ARC": 22.7, + "HellaSwag": 27.6, + "MMLU": 25.28, + "TruthfulQA": 44.75, + "Winogrande": 51.54, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.06, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "1cd271d3d62a9e1dc4b7c2978e54806d74705439", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "dfurman\/MoMoMerge-72B-v0.1", + "Average \u2b06\ufe0f": 28.69, + "ARC": 26.28, + "HellaSwag": 25.27, + "MMLU": 23.08, + "TruthfulQA": 48.73, + "Winogrande": 48.78, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 72.29, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "43aa890e6e85a40a1d0a967bca6f7f0c7fd409f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ibivibiv\/orthorus-125b-moe-v2", + "Average \u2b06\ufe0f": 28.68, + "ARC": 26.28, + "HellaSwag": 25.17, + "MMLU": 22.79, + "TruthfulQA": 48.49, + "Winogrande": 49.33, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 120.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "4e6706454e0db6b216ab81c7a9a918834e289f19", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Yash21\/SuperChat-7B", + "Average \u2b06\ufe0f": 28.67, + "ARC": 23.98, + "HellaSwag": 26.4, + "MMLU": 23.24, + "TruthfulQA": 47.21, + "Winogrande": 50.2, + "GSM8K": 0.99, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b416e3a17d1954d488c29bcc50841dd735527b52", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "xformAI\/facebook-opt-125m-qcqa-ub-6-best-for-KV-cache", + "Average \u2b06\ufe0f": 28.66, + "ARC": 24.23, + "HellaSwag": 25.0, + "MMLU": 23.12, + "TruthfulQA": 48.41, + "Winogrande": 51.22, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9bfbe90e1b638fe96534bf5085442ecde45f854d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "kenhktsui\/nano-phi-115M-v0.1", + "Average \u2b06\ufe0f": 28.66, + "ARC": 21.93, + "HellaSwag": 27.86, + "MMLU": 25.34, + "TruthfulQA": 46.0, + "Winogrande": 50.83, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "888a0d660e498daed51fdf69da70b075452b4bf9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "RWKV\/rwkv-4-169m-pile", + "Average \u2b06\ufe0f": 28.64, + "ARC": 23.63, + "HellaSwag": 31.74, + "MMLU": 23.18, + "TruthfulQA": 41.92, + "Winogrande": 50.91, + "GSM8K": 0.45, + "Type": "pretrained", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.17, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "46bdc280eb97b6141d5d51a935e0c4870ecaefcc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "postbot\/distilgpt2-emailgen-V2", + "Average \u2b06\ufe0f": 28.64, + "ARC": 20.99, + "HellaSwag": 26.78, + "MMLU": 25.53, + "TruthfulQA": 46.51, + "Winogrande": 52.01, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.09, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "9750ba00e79a02e1bf98d3faa3d49b8ae0f8ae63", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "TomGrc\/FN-OpenLLM_2x72B_MoE", + "Average \u2b06\ufe0f": 28.62, + "ARC": 25.51, + "HellaSwag": 25.23, + "MMLU": 22.8, + "TruthfulQA": 48.47, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 120.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "e1bf8cd6594a6ae363f07ab2ed3fe8ea2e718c81", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "pszemraj\/pythia-31m-simplewiki-scratch-bf16", + "Average \u2b06\ufe0f": 28.61, + "ARC": 22.78, + "HellaSwag": 25.61, + "MMLU": 23.12, + "TruthfulQA": 49.65, + "Winogrande": 50.51, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4eaec0542e7609fd3f364cb34491f05d7c61a3d0", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "pszemraj\/pythia-31m-simplepile-lite-2048-scratch-2e", + "Average \u2b06\ufe0f": 28.6, + "ARC": 21.59, + "HellaSwag": 25.79, + "MMLU": 24.99, + "TruthfulQA": 50.62, + "Winogrande": 48.62, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "91f011eb99502e667ebc2803f354ce5f5209ccf1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "saarvajanik\/facebook-opt-6.7b-qcqa-ub-16-best-for-KV-cache", + "Average \u2b06\ufe0f": 28.58, + "ARC": 23.81, + "HellaSwag": 27.05, + "MMLU": 23.12, + "TruthfulQA": 46.69, + "Winogrande": 50.83, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "42a63c805a12dda777f145ef3650202a55183a9f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/gpt2_open-platypus", + "Average \u2b06\ufe0f": 28.58, + "ARC": 22.18, + "HellaSwag": 31.29, + "MMLU": 26.19, + "TruthfulQA": 40.35, + "Winogrande": 51.3, + "GSM8K": 0.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "745c1864b752525789cad2b75166c519a327325e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "beomi\/KoAlpaca-KoRWKV-6B", + "Average \u2b06\ufe0f": 28.57, + "ARC": 23.46, + "HellaSwag": 31.65, + "MMLU": 24.89, + "TruthfulQA": 39.83, + "Winogrande": 51.62, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 6.53, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": true, + "Model sha": "427ee72c4350f26de1b287a0c07b842e7d168dbc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KnutJaegersberg\/RWKV-4-PilePlus-169M-20230520-done-ctx4096", + "Average \u2b06\ufe0f": 28.57, + "ARC": 23.98, + "HellaSwag": 32.25, + "MMLU": 23.37, + "TruthfulQA": 42.29, + "Winogrande": 49.17, + "GSM8K": 0.38, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.13, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1134d31db1aee9fc970d3e9dc4e7314fb8bba500", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "yeen214\/llama2_7b_small_tuning_v1", + "Average \u2b06\ufe0f": 28.56, + "ARC": 22.44, + "HellaSwag": 25.0, + "MMLU": 25.51, + "TruthfulQA": 48.7, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "3f9b43b4db2da4fe3785071dd52c9fc92aa0801d", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mzio\/hedgehog-alpaca_clean_mistral-mistral_7b_lk_esn_tqk_lora-lk_untied_head-lsc_1", + "Average \u2b06\ufe0f": 28.56, + "ARC": 21.25, + "HellaSwag": 28.74, + "MMLU": 25.15, + "TruthfulQA": 46.66, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.28, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d9ce8cc144f015d0b968beaec11d1ea6ba00e5b6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/chat_gpt2_dpo", + "Average \u2b06\ufe0f": 28.56, + "ARC": 23.98, + "HellaSwag": 31.22, + "MMLU": 24.95, + "TruthfulQA": 41.26, + "Winogrande": 49.96, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2c35dac9f97e3756137c175b9d49d72fdcf2d059", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aloobun\/falcon-1b-cot-t2", + "Average \u2b06\ufe0f": 28.56, + "ARC": 24.74, + "HellaSwag": 24.75, + "MMLU": 23.12, + "TruthfulQA": 48.38, + "Winogrande": 50.36, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "FalconForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "fed367016c8adcd499f18eab5e8a9eda71c5e647", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "qiyinmiss\/My_GPT2", + "Average \u2b06\ufe0f": 28.55, + "ARC": 21.93, + "HellaSwag": 31.59, + "MMLU": 25.84, + "TruthfulQA": 40.73, + "Winogrande": 50.51, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "4145e280b85ec619906dfc5a624e17cde8ffbea6", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "openai-community\/gpt2", + "Average \u2b06\ufe0f": 28.53, + "ARC": 22.01, + "HellaSwag": 31.53, + "MMLU": 25.83, + "TruthfulQA": 40.69, + "Winogrande": 50.43, + "GSM8K": 0.68, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 1695.0, + "Available on the hub": true, + "Model sha": "11c5a3d5811f50298f278a704980280950aedb10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "gpt2", + "Average \u2b06\ufe0f": 28.53, + "ARC": 22.01, + "HellaSwag": 31.53, + "MMLU": 25.83, + "TruthfulQA": 40.69, + "Winogrande": 50.43, + "GSM8K": 0.68, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "11c5a3d5811f50298f278a704980280950aedb10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Corianas\/Quokka_590m", + "Average \u2b06\ufe0f": 28.53, + "ARC": 24.4, + "HellaSwag": 31.61, + "MMLU": 25.36, + "TruthfulQA": 39.59, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.67, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ae0ac41e9be016f6dceac06821fbf6ebacc7edb9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/gpt2_guanaco-dolly-platypus", + "Average \u2b06\ufe0f": 28.52, + "ARC": 23.55, + "HellaSwag": 31.03, + "MMLU": 26.4, + "TruthfulQA": 40.02, + "Winogrande": 50.12, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6bf0a8146cf255c829ec2ad83926c8b80945b431", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/gpt2_platypus-dolly-guanaco", + "Average \u2b06\ufe0f": 28.51, + "ARC": 23.21, + "HellaSwag": 31.04, + "MMLU": 26.16, + "TruthfulQA": 40.31, + "Winogrande": 50.36, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bfa144d3eb087e54f1798fd2e2fb17e894cc39d3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/math_gpt2", + "Average \u2b06\ufe0f": 28.5, + "ARC": 24.23, + "HellaSwag": 30.88, + "MMLU": 25.38, + "TruthfulQA": 39.23, + "Winogrande": 51.07, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "57b7106f661d4874578a2ef48784d1afc0cccd8f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Josephgflowers\/distillgpt2Cinder", + "Average \u2b06\ufe0f": 28.5, + "ARC": 24.49, + "HellaSwag": 27.24, + "MMLU": 24.97, + "TruthfulQA": 43.96, + "Winogrande": 50.12, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.08, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "bc2bb342a2a239258e4862272ba3993c955e8289", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "bigcode\/gpt_bigcode-santacoder", + "Average \u2b06\ufe0f": 28.49, + "ARC": 21.16, + "HellaSwag": 30.84, + "MMLU": 24.97, + "TruthfulQA": 45.64, + "Winogrande": 47.83, + "GSM8K": 0.53, + "Type": "pretrained", + "Architecture": "GPTBigCodeForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "openrail", + "#Params (B)": 1.12, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "291931872cae83498cf984b16319f47f5e9e7a07", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MBZUAI\/lamini-cerebras-256m", + "Average \u2b06\ufe0f": 28.49, + "ARC": 21.76, + "HellaSwag": 28.7, + "MMLU": 26.66, + "TruthfulQA": 41.81, + "Winogrande": 52.01, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.26, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "72df0b6d62d64002575687ea2edbb0df05712678", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/code_gpt2_mini_model", + "Average \u2b06\ufe0f": 28.49, + "ARC": 23.72, + "HellaSwag": 31.25, + "MMLU": 24.96, + "TruthfulQA": 39.86, + "Winogrande": 51.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "97d249d37896a4c20485830862541373edeca49c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "AI-Sweden-Models\/gpt-sw3-126m", + "Average \u2b06\ufe0f": 28.49, + "ARC": 22.18, + "HellaSwag": 29.54, + "MMLU": 24.43, + "TruthfulQA": 44.03, + "Winogrande": 50.67, + "GSM8K": 0.08, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9272f5a996cf785b8ab706a27d1e7dff1228dc70", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "0x7194633\/nanoFialka-v1", + "Average \u2b06\ufe0f": 28.48, + "ARC": 22.01, + "HellaSwag": 28.12, + "MMLU": 25.03, + "TruthfulQA": 45.26, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "96023dad08cf1f9a300c95c8834e28631ca7167b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "blueapple8259\/TinyStories-Alpaca", + "Average \u2b06\ufe0f": 28.46, + "ARC": 23.98, + "HellaSwag": 24.92, + "MMLU": 23.35, + "TruthfulQA": 46.68, + "Winogrande": 51.85, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.07, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "18e0bde7e72e477757832f0624a0410efc066216", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BreadAi\/gpt-Youtube", + "Average \u2b06\ufe0f": 28.46, + "ARC": 23.29, + "HellaSwag": 26.34, + "MMLU": 23.54, + "TruthfulQA": 48.63, + "Winogrande": 48.93, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.21, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "de88554a0212c16fdfeda030afb58f831ebcd895", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "daekeun-ml\/phi-2-upscaled-4B-instruct-v0.1", + "Average \u2b06\ufe0f": 28.45, + "ARC": 22.95, + "HellaSwag": 28.68, + "MMLU": 26.8, + "TruthfulQA": 40.92, + "Winogrande": 50.59, + "GSM8K": 0.76, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "PhiForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 4.04, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "7647fcf7c3aa98a04a86a65e2f774ec670994b07", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "vilm\/Mixsmol-4x400M-v0.1-epoch1", + "Average \u2b06\ufe0f": 28.45, + "ARC": 22.87, + "HellaSwag": 30.57, + "MMLU": 25.28, + "TruthfulQA": 39.03, + "Winogrande": 52.8, + "GSM8K": 0.15, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.77, + "Hub \u2764\ufe0f": 12.0, + "Available on the hub": true, + "Model sha": "0389e88c0309b95c885bdfd7fd1a4d5a39b4bcc4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "BEE-spoke-data\/Mixtral-GQA-400m-v2", + "Average \u2b06\ufe0f": 28.45, + "ARC": 20.22, + "HellaSwag": 27.78, + "MMLU": 26.1, + "TruthfulQA": 46.55, + "Winogrande": 49.96, + "GSM8K": 0.08, + "Type": "pretrained", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.01, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6f8c51d1bf60da6f8e64ba7fb75fb747d9b124cf", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "AI-Sweden-Models\/gpt-sw3-126m", + "Average \u2b06\ufe0f": 28.45, + "ARC": 22.01, + "HellaSwag": 29.56, + "MMLU": 24.53, + "TruthfulQA": 44.07, + "Winogrande": 50.43, + "GSM8K": 0.08, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.19, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c9d5a2f3fe905557cf0acba496a903255a11907c", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Sayan01\/Llama-Flan-XL2base", + "Average \u2b06\ufe0f": 28.44, + "ARC": 20.65, + "HellaSwag": 25.33, + "MMLU": 23.19, + "TruthfulQA": 50.58, + "Winogrande": 50.91, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 2.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "5ffcaeaf5645d96c3f04ed632a820590d3f87c6c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "roneneldan\/TinyStories-28M", + "Average \u2b06\ufe0f": 28.44, + "ARC": 22.78, + "HellaSwag": 25.83, + "MMLU": 23.53, + "TruthfulQA": 48.08, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 7.0, + "Available on the hub": false, + "Model sha": "52dabea9997faf578489d619249616926e54ed18", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "EleutherAI\/pythia-70m-deduped", + "Average \u2b06\ufe0f": 28.44, + "ARC": 21.08, + "HellaSwag": 27.17, + "MMLU": 25.26, + "TruthfulQA": 47.51, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.1, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "e93a9faa9c77e5d09219f6c868bfc7a1bd65593c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "budecosystem\/boomer-1b", + "Average \u2b06\ufe0f": 28.44, + "ARC": 22.78, + "HellaSwag": 31.58, + "MMLU": 25.66, + "TruthfulQA": 39.17, + "Winogrande": 50.51, + "GSM8K": 0.91, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "f8f24b5480fa43f23d858f0eb8d1af1b7ad0af59", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Dans-DiscountModels\/TinyMistral-v2-Test1", + "Average \u2b06\ufe0f": 28.42, + "ARC": 21.5, + "HellaSwag": 26.79, + "MMLU": 23.36, + "TruthfulQA": 50.3, + "Winogrande": 48.54, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "c7f5b9b6915cb9942d47ab8bde32093bcc4a4374", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "roneneldan\/TinyStories-33M", + "Average \u2b06\ufe0f": 28.41, + "ARC": 24.23, + "HellaSwag": 25.69, + "MMLU": 23.82, + "TruthfulQA": 47.64, + "Winogrande": 49.09, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 79.0, + "Available on the hub": false, + "Model sha": "190d22e37cba4b12ddae57d6738a0c65f6ab1aa5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/gpt2_camel_physics-platypus", + "Average \u2b06\ufe0f": 28.41, + "ARC": 23.04, + "HellaSwag": 31.32, + "MMLU": 26.91, + "TruthfulQA": 39.56, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "66165ff32ed8de6c39f3524a810f5e97ba6d3347", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/gpt2_platypus-camel_physics", + "Average \u2b06\ufe0f": 28.41, + "ARC": 23.04, + "HellaSwag": 31.32, + "MMLU": 26.91, + "TruthfulQA": 39.56, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "66165ff32ed8de6c39f3524a810f5e97ba6d3347", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "SaylorTwift\/gpt2_test", + "Average \u2b06\ufe0f": 28.4, + "ARC": 21.84, + "HellaSwag": 31.6, + "MMLU": 25.86, + "TruthfulQA": 40.67, + "Winogrande": 50.12, + "GSM8K": 0.3, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ef61310a16ffda93bf8f6132e02658482ffc2bcc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dpv\/finetuned-gpt2-tiny", + "Average \u2b06\ufe0f": 28.4, + "ARC": 21.84, + "HellaSwag": 31.6, + "MMLU": 25.86, + "TruthfulQA": 40.67, + "Winogrande": 50.12, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "379e02101b4dccba48e7ae792708d2fe7f0bbca2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "behnamsh\/gpt2_platypus-camel_physics", + "Average \u2b06\ufe0f": 28.4, + "ARC": 22.78, + "HellaSwag": 31.24, + "MMLU": 25.87, + "TruthfulQA": 38.95, + "Winogrande": 51.54, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "cd4d700d13b3bc9371bf45616ef74ac20d165c3d", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "MBZUAI\/lamini-cerebras-590m", + "Average \u2b06\ufe0f": 28.38, + "ARC": 24.32, + "HellaSwag": 31.58, + "MMLU": 25.57, + "TruthfulQA": 40.72, + "Winogrande": 47.91, + "GSM8K": 0.15, + "Type": "", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.59, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "bab37eb7ba63f6ff9f0eb36a85727146b82ae5ed", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cloudyu\/Qwen-72Bx2-MoE-120B", + "Average \u2b06\ufe0f": 28.37, + "ARC": 25.94, + "HellaSwag": 24.91, + "MMLU": 23.27, + "TruthfulQA": 48.91, + "Winogrande": 47.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 120.61, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "8074fa7f9d97775efe3bcb8b11c04cdcbf3a9810", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "xformAI\/facebook-opt-125m-qcqa-ub-6-best-for-q-loss", + "Average \u2b06\ufe0f": 28.37, + "ARC": 23.29, + "HellaSwag": 25.57, + "MMLU": 23.15, + "TruthfulQA": 49.03, + "Winogrande": 49.17, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9e7a1dd66f1fe7b0808dcdb12a8ad5d166c67576", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "mncai\/SGPT-1.3B-insurance-epoch10", + "Average \u2b06\ufe0f": 28.37, + "ARC": 24.57, + "HellaSwag": 24.25, + "MMLU": 25.23, + "TruthfulQA": 45.24, + "Winogrande": 50.91, + "GSM8K": 0.0, + "Type": "", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "df685c0bbf838f0627383c28f48e577ee901ba68", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vicgalle\/gpt2-alpaca-gpt4", + "Average \u2b06\ufe0f": 28.34, + "ARC": 22.61, + "HellaSwag": 31.17, + "MMLU": 25.76, + "TruthfulQA": 38.04, + "Winogrande": 52.17, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 20.0, + "Available on the hub": true, + "Model sha": "282e9bd56f0cab5d48e6954793647eecaa0871d9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Corianas\/Quokka_256m", + "Average \u2b06\ufe0f": 28.32, + "ARC": 22.87, + "HellaSwag": 28.84, + "MMLU": 26.48, + "TruthfulQA": 39.47, + "Winogrande": 52.25, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.32, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "d4e69f714d360d39979eb7b8cbc9decdb7190c88", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "roneneldan\/TinyStories-8M", + "Average \u2b06\ufe0f": 28.31, + "ARC": 24.66, + "HellaSwag": 25.03, + "MMLU": 23.33, + "TruthfulQA": 46.54, + "Winogrande": 50.28, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.01, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": false, + "Model sha": "8612e3b15c66ffa94eaa6ee0de5c96edd2d630af", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/convo_bot_gpt_v1", + "Average \u2b06\ufe0f": 28.3, + "ARC": 22.35, + "HellaSwag": 31.07, + "MMLU": 26.12, + "TruthfulQA": 38.71, + "Winogrande": 51.54, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "29f955906543788e2f1de656637c9e068cf177f7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "xzuyn\/GPT-2-SlimOrcaDeduped-airoboros-3.1-MetaMathQA-SFT-124M", + "Average \u2b06\ufe0f": 28.3, + "ARC": 24.57, + "HellaSwag": 29.43, + "MMLU": 25.82, + "TruthfulQA": 38.84, + "Winogrande": 49.01, + "GSM8K": 2.12, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e12dbd27ee148ce4af6faf742aa936d38c26536f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "ethzanalytics\/pythia-31m", + "Average \u2b06\ufe0f": 28.3, + "ARC": 19.97, + "HellaSwag": 26.34, + "MMLU": 24.27, + "TruthfulQA": 50.12, + "Winogrande": 49.09, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8a3c2f1555de8a3c53d67d73b5d0d53a66a6c6c2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/dlite-v2-124m", + "Average \u2b06\ufe0f": 28.3, + "ARC": 23.98, + "HellaSwag": 31.1, + "MMLU": 25.29, + "TruthfulQA": 38.98, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 5.0, + "Available on the hub": true, + "Model sha": "bc719f990748ea72be4b6c270df34fc3d37291dc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "instructkr\/ko-wand-136M", + "Average \u2b06\ufe0f": 28.29, + "ARC": 21.33, + "HellaSwag": 25.0, + "MMLU": 23.58, + "TruthfulQA": 50.68, + "Winogrande": 49.17, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": [ + "apache-2.0" + ], + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "86cc9bf25c45c60cc16ea6002609121fdcd83609", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Locutusque\/TinyMistral-248M-v2.5", + "Average \u2b06\ufe0f": 28.29, + "ARC": 24.57, + "HellaSwag": 27.49, + "MMLU": 23.15, + "TruthfulQA": 46.72, + "Winogrande": 47.83, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.25, + "Hub \u2764\ufe0f": 19.0, + "Available on the hub": true, + "Model sha": "99c8efd7bc4aba7939e20b7e9e3a46b542cae713", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "huggingtweets\/gladosystem", + "Average \u2b06\ufe0f": 28.29, + "ARC": 24.4, + "HellaSwag": 29.71, + "MMLU": 23.18, + "TruthfulQA": 41.78, + "Winogrande": 50.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "02a1bbcee7b584ace743b2fe4885cc0eaf2179ac", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "namanpundir\/theus_concepttagger", + "Average \u2b06\ufe0f": 28.29, + "ARC": 24.57, + "HellaSwag": 25.5, + "MMLU": 23.12, + "TruthfulQA": 48.25, + "Winogrande": 48.3, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "BartForConditionalGeneration", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "54f816e4cc09d5e3615da5a0eedb67b2be529cd9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MBZUAI\/lamini-cerebras-111m", + "Average \u2b06\ufe0f": 28.29, + "ARC": 22.1, + "HellaSwag": 27.12, + "MMLU": 25.51, + "TruthfulQA": 43.79, + "Winogrande": 51.22, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "e8e347b02f9305e4bc144eb9be2821c518d43183", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "gpt2", + "Average \u2b06\ufe0f": 28.28, + "ARC": 21.59, + "HellaSwag": 31.58, + "MMLU": 25.4, + "TruthfulQA": 41.15, + "Winogrande": 49.57, + "GSM8K": 0.38, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "11c5a3d5811f50298f278a704980280950aedb10", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "pszemraj\/pythia-31m-simplewiki-2048", + "Average \u2b06\ufe0f": 28.27, + "ARC": 22.18, + "HellaSwag": 25.55, + "MMLU": 23.12, + "TruthfulQA": 49.37, + "Winogrande": 49.41, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "95d47818055661250b55144c7d9beaf05dc126d8", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "saarvajanik\/facebook-opt-6.7b-qcqa-ub-16-best-for-q-loss", + "Average \u2b06\ufe0f": 28.25, + "ARC": 21.67, + "HellaSwag": 26.65, + "MMLU": 23.15, + "TruthfulQA": 46.81, + "Winogrande": 51.22, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2e3897dc86f781538f316fbf27072ae45d0779ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "cyberagent\/open-calm-7b", + "Average \u2b06\ufe0f": 28.21, + "ARC": 20.48, + "HellaSwag": 30.65, + "MMLU": 25.22, + "TruthfulQA": 44.15, + "Winogrande": 48.54, + "GSM8K": 0.23, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-sa-4.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 199.0, + "Available on the hub": true, + "Model sha": "276a5fb67510554e11ef191a2da44c919acccdf5", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "crumb\/gpt2023", + "Average \u2b06\ufe0f": 28.2, + "ARC": 21.93, + "HellaSwag": 31.11, + "MMLU": 25.05, + "TruthfulQA": 40.71, + "Winogrande": 50.12, + "GSM8K": 0.3, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 17.0, + "Available on the hub": true, + "Model sha": "e3620b53d164529575db66d9d4f4382311dd713c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "AI-Sweden-Models\/gpt-sw3-126m-instruct", + "Average \u2b06\ufe0f": 28.2, + "ARC": 23.38, + "HellaSwag": 29.88, + "MMLU": 23.78, + "TruthfulQA": 42.65, + "Winogrande": 48.54, + "GSM8K": 0.99, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.19, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5f353e1eb1b579ef62e10302b7c0bb843ee8eba9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/TinyMistral-248M-SFT-v4", + "Average \u2b06\ufe0f": 28.2, + "ARC": 24.91, + "HellaSwag": 28.15, + "MMLU": 26.04, + "TruthfulQA": 39.56, + "Winogrande": 50.51, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.25, + "Hub \u2764\ufe0f": 23.0, + "Available on the hub": true, + "Model sha": "ec0ff201527cd9b50eb9b4fc754d6c08f1242ea1", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "beomi\/KoRWKV-6B", + "Average \u2b06\ufe0f": 28.19, + "ARC": 22.1, + "HellaSwag": 32.18, + "MMLU": 24.69, + "TruthfulQA": 39.05, + "Winogrande": 51.14, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "RwkvForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 6.53, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "541600070459baf0f1be9560181d5ceb77794085", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "roneneldan\/TinyStories-3M", + "Average \u2b06\ufe0f": 28.19, + "ARC": 22.01, + "HellaSwag": 25.58, + "MMLU": 24.99, + "TruthfulQA": 47.33, + "Winogrande": 49.25, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPTNeoForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": false, + "Model sha": "cfaf26ec85ecdfc1bd7c2638104cce55cb67f894", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/code_gpt2", + "Average \u2b06\ufe0f": 28.19, + "ARC": 23.29, + "HellaSwag": 30.99, + "MMLU": 25.03, + "TruthfulQA": 40.6, + "Winogrande": 49.25, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fd12ea93faeecbe4d1f4bc2b1d1c3bce0521d182", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/TinyMistral-248M-Instruct", + "Average \u2b06\ufe0f": 28.19, + "ARC": 24.32, + "HellaSwag": 27.52, + "MMLU": 25.18, + "TruthfulQA": 41.94, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.25, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": true, + "Model sha": "32a9317176bd8562bbb6497eef43a95f2c0261c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "pszemraj\/distilgpt2-HC3", + "Average \u2b06\ufe0f": 28.18, + "ARC": 24.66, + "HellaSwag": 27.99, + "MMLU": 23.95, + "TruthfulQA": 42.1, + "Winogrande": 50.36, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.09, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "6f9ad473a3793d0271df34a55882ad30846a6788", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "lgaalves\/gpt2-dolly", + "Average \u2b06\ufe0f": 28.18, + "ARC": 21.76, + "HellaSwag": 30.77, + "MMLU": 24.66, + "TruthfulQA": 42.22, + "Winogrande": 49.57, + "GSM8K": 0.08, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "52fcf61a8eef255a981be6efde187481086e1a48", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "BEE-spoke-data\/smol_llama-81M-tied", + "Average \u2b06\ufe0f": 28.17, + "ARC": 22.18, + "HellaSwag": 29.33, + "MMLU": 24.06, + "TruthfulQA": 43.97, + "Winogrande": 49.25, + "GSM8K": 0.23, + "Type": "pretrained", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.08, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "096e543bd36d067a819ea867c66f14d946849053", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/math_gpt2_sft", + "Average \u2b06\ufe0f": 28.03, + "ARC": 22.87, + "HellaSwag": 30.41, + "MMLU": 25.06, + "TruthfulQA": 37.62, + "Winogrande": 51.54, + "GSM8K": 0.68, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "3ed7a2e8ff3b47cca5428d8870434251a0353a53", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/Med_GPT2", + "Average \u2b06\ufe0f": 28.02, + "ARC": 23.38, + "HellaSwag": 30.99, + "MMLU": 24.0, + "TruthfulQA": 38.95, + "Winogrande": 49.72, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "46fa8704ddb8c2b84a66f9ec0adbd84f3f0f0337", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "MBZUAI\/LaMini-GPT-124M", + "Average \u2b06\ufe0f": 28.01, + "ARC": 24.32, + "HellaSwag": 30.82, + "MMLU": 24.99, + "TruthfulQA": 36.57, + "Winogrande": 51.38, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 16.0, + "Available on the hub": true, + "Model sha": "5c67c8c03c08e82d6138ce2a1eddf5317fac3a6b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Sharathhebbar24\/chat_gpt2", + "Average \u2b06\ufe0f": 27.99, + "ARC": 23.04, + "HellaSwag": 30.76, + "MMLU": 24.39, + "TruthfulQA": 39.81, + "Winogrande": 49.96, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "4acb2db0b75f98219114bcd96d1e6be8c6b86010", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Locutusque\/LocutusqueXFelladrin-TinyMistral248M-Instruct", + "Average \u2b06\ufe0f": 27.98, + "ARC": 24.74, + "HellaSwag": 27.79, + "MMLU": 26.12, + "TruthfulQA": 40.12, + "Winogrande": 49.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.25, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "646fc1eaf46fcd7f1f9141da8a259715ff7528be", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shitshow123\/tinylamma-20000", + "Average \u2b06\ufe0f": 27.95, + "ARC": 23.81, + "HellaSwag": 32.45, + "MMLU": 25.37, + "TruthfulQA": 34.87, + "Winogrande": 51.22, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.1, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "51b5eea5679f69d00571d94fb87ee12496cb8104", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "TurkuNLP\/gpt3-finnish-small", + "Average \u2b06\ufe0f": 27.95, + "ARC": 20.48, + "HellaSwag": 28.09, + "MMLU": 24.47, + "TruthfulQA": 46.47, + "Winogrande": 48.22, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "BloomModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "20a19af481bf59f38610a2977b2b513e9df51e3a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "M4-ai\/TinyMistral-6x248M-Instruct", + "Average \u2b06\ufe0f": 27.89, + "ARC": 22.44, + "HellaSwag": 27.02, + "MMLU": 24.13, + "TruthfulQA": 43.16, + "Winogrande": 50.59, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 6.0, + "Available on the hub": true, + "Model sha": "6004505aa44f0101f69c6e1bf29722c863858c7b", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "Mikivis\/xuanxuan", + "Average \u2b06\ufe0f": 27.88, + "ARC": 23.46, + "HellaSwag": 31.12, + "MMLU": 26.27, + "TruthfulQA": 35.97, + "Winogrande": 50.43, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "ba6ae2b347bc613ae38980e059ec8c5ec8b26038", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "vicgalle\/gpt2-alpaca", + "Average \u2b06\ufe0f": 27.86, + "ARC": 22.87, + "HellaSwag": 31.14, + "MMLU": 26.26, + "TruthfulQA": 36.22, + "Winogrande": 50.67, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 0.14, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "e06875a588f7b3386c18a6efdc8cc7583d95b21b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aisquared\/dlite-v1-124m", + "Average \u2b06\ufe0f": 27.86, + "ARC": 24.32, + "HellaSwag": 31.16, + "MMLU": 25.08, + "TruthfulQA": 36.38, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "f6fd5f3960f31881e6cee23f5a872ecc80b40283", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "psyche\/kogpt", + "Average \u2b06\ufe0f": 27.83, + "ARC": 21.16, + "HellaSwag": 28.11, + "MMLU": 26.56, + "TruthfulQA": 42.06, + "Winogrande": 49.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.39, + "Hub \u2764\ufe0f": 4.0, + "Available on the hub": true, + "Model sha": "4c02d48f548103ba53a5e481b8aa81bf7a259287", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "cerebras\/Cerebras-GPT-111M", + "Average \u2b06\ufe0f": 27.75, + "ARC": 20.22, + "HellaSwag": 26.73, + "MMLU": 25.51, + "TruthfulQA": 46.31, + "Winogrande": 47.75, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "?", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.11, + "Hub \u2764\ufe0f": 69.0, + "Available on the hub": true, + "Model sha": "d2b54d7af419055f204690fe0385959616a1723e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "Locutusque\/TinyMistral-248m", + "Average \u2b06\ufe0f": 27.73, + "ARC": 22.87, + "HellaSwag": 28.02, + "MMLU": 23.15, + "TruthfulQA": 42.52, + "Winogrande": 49.8, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.25, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "8f03f72bca0542aa164c29ba41f02cba6f9d7748", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Locutusque\/TinyMistral-248M-v2.5-Instruct", + "Average \u2b06\ufe0f": 27.7, + "ARC": 22.27, + "HellaSwag": 27.6, + "MMLU": 23.9, + "TruthfulQA": 44.21, + "Winogrande": 48.22, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.25, + "Hub \u2764\ufe0f": 9.0, + "Available on the hub": true, + "Model sha": "0490a521f39dfdf3e50a500773cd1772322b66a9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "ai-forever\/mGPT", + "Average \u2b06\ufe0f": 27.61, + "ARC": 23.81, + "HellaSwag": 26.37, + "MMLU": 25.17, + "TruthfulQA": 39.62, + "Winogrande": 50.67, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 211.0, + "Available on the hub": true, + "Model sha": "40897bd7c8b47a76802c411108ca6220438b8b40", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "huashiyiqike\/testmodel", + "Average \u2b06\ufe0f": 27.6, + "ARC": 19.71, + "HellaSwag": 26.68, + "MMLU": 25.28, + "TruthfulQA": 43.72, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 0.15, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "1ac5d244402e2433b6abfcff1fe65e84af15766b", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Corianas\/111m", + "Average \u2b06\ufe0f": 27.6, + "ARC": 19.71, + "HellaSwag": 26.68, + "MMLU": 25.28, + "TruthfulQA": 43.72, + "Winogrande": 50.2, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-sa-4.0", + "#Params (B)": 0.15, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "ee58d79e27f8b9e3984aab29235c5851d2be01d4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/TinyMistral-248M-SFT-v3", + "Average \u2b06\ufe0f": 27.45, + "ARC": 21.93, + "HellaSwag": 28.26, + "MMLU": 22.91, + "TruthfulQA": 40.03, + "Winogrande": 51.54, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 0.25, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "7a4787dfed21a432924d24575e6c65a97e1dd98a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "OpenBuddy\/openbuddy-mixtral-7bx8-v17.2-32k", + "Average \u2b06\ufe0f": 23.07, + "ARC": 33.53, + "HellaSwag": 31.36, + "MMLU": 17.8, + "TruthfulQA": 0.0, + "Winogrande": 55.72, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.74, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "d61589d9e263af809f20f452af68749ff85d0163", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "databricks\/dolly-v2-3b", + "Average \u2b06\ufe0f": 22.83, + "ARC": 25.26, + "HellaSwag": 26.55, + "MMLU": 24.7, + "TruthfulQA": 0.0, + "Winogrande": 59.43, + "GSM8K": 1.06, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 3.0, + "Hub \u2764\ufe0f": 262.0, + "Available on the hub": true, + "Model sha": "f6c9be08f16fe4d3a719bee0a4a7c7415b5c65df", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "v1olet\/v1olet_marcoroni-go-bruins-7B", + "Average \u2b06\ufe0f": 22.43, + "ARC": 29.1, + "HellaSwag": 28.3, + "MMLU": 25.09, + "TruthfulQA": 0.0, + "Winogrande": 52.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "05868b30f81600b703a1029c4806683f7f5a89fc", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "v1olet\/v1olet_mistral_7B", + "Average \u2b06\ufe0f": 22.16, + "ARC": 29.18, + "HellaSwag": 28.13, + "MMLU": 26.24, + "TruthfulQA": 0.0, + "Winogrande": 49.41, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "aaf2184ac642ce0171d2703bdb3db8fde855e4c9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "FelixChao\/Magician-MoE-4x7B", + "Average \u2b06\ufe0f": 22.14, + "ARC": 28.24, + "HellaSwag": 30.06, + "MMLU": 24.67, + "TruthfulQA": 0.0, + "Winogrande": 49.88, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 19.73, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "3770b16a9cab8fa835a5d18c4d3fafe4bac7246f", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udfe2", + "Model": "FabbriSimo01\/Facebook_opt_1.3b_Quantized", + "Average \u2b06\ufe0f": 21.78, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 59.67, + "GSM8K": 0.15, + "Type": "pretrained", + "Architecture": "OPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "mit", + "#Params (B)": 1.3, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "7ef72ccee9d91d06967809e4e63ffbef62a9ad4a", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "KevinNi\/mistral-class-bio-tutor", + "Average \u2b06\ufe0f": 21.59, + "ARC": 28.07, + "HellaSwag": 28.02, + "MMLU": 23.79, + "TruthfulQA": 0.0, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.11, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c0e782c571209e1238e3a3170dcd187f9a436df2", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "maximuslee07\/llama-2-13b-rockwellautomation", + "Average \u2b06\ufe0f": 21.48, + "ARC": 28.16, + "HellaSwag": 25.77, + "MMLU": 25.14, + "TruthfulQA": 0.0, + "Winogrande": 49.8, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Delta", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2bec12a875dd8cb22550c02082ae81e138018ebe", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "jslin09\/bloom-560m-finetuned-fraud", + "Average \u2b06\ufe0f": 21.37, + "ARC": 26.96, + "HellaSwag": 28.87, + "MMLU": 24.03, + "TruthfulQA": 0.0, + "Winogrande": 48.38, + "GSM8K": 0.0, + "Type": "", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "bigscience-bloom-rail-1.0", + "#Params (B)": 0.56, + "Hub \u2764\ufe0f": 2.0, + "Available on the hub": true, + "Model sha": "5571f87f557b909e863005c6e3870bc2e77341a7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ahnyeonchan\/OpenOrca-AYT-13B", + "Average \u2b06\ufe0f": 21.35, + "ARC": 27.22, + "HellaSwag": 26.03, + "MMLU": 25.11, + "TruthfulQA": 0.0, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Delta", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "llama2", + "#Params (B)": 13.02, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "1357abceda30e8389007a023907824cc3a11e397", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/alignment-handbook-zephyr-7b_ppostep_100", + "Average \u2b06\ufe0f": 21.3, + "ARC": 29.27, + "HellaSwag": 25.87, + "MMLU": 23.76, + "TruthfulQA": 0.0, + "Winogrande": 48.93, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "61d68e300e0887dd431bd3a24ab94a36cd56b03d", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Andron00e\/YetAnother_Open-Llama-3B-LoRA", + "Average \u2b06\ufe0f": 21.29, + "ARC": 25.94, + "HellaSwag": 25.76, + "MMLU": 24.65, + "TruthfulQA": 0.0, + "Winogrande": 51.38, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LlamaForCausalLM", + "Weight type": "Delta", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "52c5cb0178831908ed0571f1750fcb0f0fb125f9", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "Andron00e\/YetAnother_Open-Llama-3B-LoRA-OpenOrca", + "Average \u2b06\ufe0f": 21.2, + "ARC": 25.94, + "HellaSwag": 25.76, + "MMLU": 24.65, + "TruthfulQA": 0.0, + "Winogrande": 50.83, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 3.43, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "07d9d32cd091148295d4e13802ba63486599aff4", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Dampish\/Dante-2.8B", + "Average \u2b06\ufe0f": 21.12, + "ARC": 25.09, + "HellaSwag": 26.05, + "MMLU": 24.51, + "TruthfulQA": 0.0, + "Winogrande": 51.07, + "GSM8K": 0.0, + "Type": "", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Delta", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 2.8, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "fb2a8f95c0286f957c830af640fd5c989081e8e4", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "BreadAi\/MuseCan", + "Average \u2b06\ufe0f": 21.06, + "ARC": 28.07, + "HellaSwag": 25.0, + "MMLU": 24.19, + "TruthfulQA": 0.0, + "Winogrande": 49.09, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPT2LMHeadModel", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": null, + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "f441866d78feaead3dede6efd9e23990bb74c21e", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "team-lucid\/mptk-1b", + "Average \u2b06\ufe0f": 20.84, + "ARC": 22.7, + "HellaSwag": 25.48, + "MMLU": 27.11, + "TruthfulQA": 0.0, + "Winogrande": 49.72, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MptForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 1.31, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "aea467410ae0cead4fded6b98a3575e92b22862f", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mindy-labs\/mindy-7b", + "Average \u2b06\ufe0f": 20.52, + "ARC": 23.63, + "HellaSwag": 25.82, + "MMLU": 24.15, + "TruthfulQA": 0.0, + "Winogrande": 49.49, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Delta", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "b859eae30d69b065060e268b4e918601dabcc36c", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alnrg2arg\/test", + "Average \u2b06\ufe0f": 20.45, + "ARC": 23.04, + "HellaSwag": 25.23, + "MMLU": 23.28, + "TruthfulQA": 0.0, + "Winogrande": 51.14, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Delta", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "9750a39173e3052074bf940c1e41badf993ee960", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "amu\/zen", + "Average \u2b06\ufe0f": 20.33, + "ARC": 23.98, + "HellaSwag": 25.08, + "MMLU": 23.26, + "TruthfulQA": 0.0, + "Winogrande": 49.64, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Delta", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2d41f336037eadddf1dcd75d622813ab8e956067", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "alnrg2arg\/test_wanda_240109", + "Average \u2b06\ufe0f": 20.24, + "ARC": 22.95, + "HellaSwag": 25.26, + "MMLU": 23.32, + "TruthfulQA": 0.0, + "Winogrande": 49.88, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Delta", + "Precision": "float16", + "Merged": false, + "Hub License": "cc-by-nc-4.0", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "1c11cdf3b6aa1e175dc76609affbaec7da4494ab", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "ewqr2130\/mistral-moe-scratch", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "efda3aed6b33db48bde86d2d3a7200895350e490", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83e\udd1d", + "Model": "RatanRohith\/NeuralPizza-Valor-7B-Merge-slerp", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.92, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "fca24d608a5196ee6661e1b293466f95089776ff", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "mathurinache\/Odysseas-11B", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c3a5944eb94bb9d2e8fd8b9c8d45791b4e8cf982", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "clibrain\/Llama-2-ft-instruct-es", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 18.0, + "Available on the hub": true, + "Model sha": "42f07d6a86fac5574febb7b8fa13c3b1e14fcebd", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "APMIC\/caigun-lora-model-33B", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "8bit", + "Merged": false, + "Hub License": "cc-by-nc-nd-4.0", + "#Params (B)": 18.25, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "43789c7afafa495cbcb75185c8f48b11488c0408", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "shitshow123\/moe_scratch", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 46.7, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "86bd0f657bfc81b8c42bcc2c958949e21258f97e", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udd36", + "Model": "shitshow123\/stablelm_sft_dpo", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.87, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c8c9b1fb2217a2b659de4f9396feeca5d15f53ee", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "rizla\/rizla-11", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "cc-by-nc-2.0", + "#Params (B)": 9.42, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "499b64d8272ea64e1247f9ff1eef33d7138b6c34", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "TheTravellingEngineer\/bloom-1b1-RLHF-v2", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "BloomForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "", + "#Params (B)": 1.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "05f7f0fd82fb3a5798d4bb284b6c10dd9d380f22", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "mathurinache\/Odysseas-11B", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.48, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "c3a5944eb94bb9d2e8fd8b9c8d45791b4e8cf982", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udfe2", + "Model": "wtang06\/mpt-125m-c4", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "pretrained", + "Architecture": "MPTForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.12, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "55f8f1874aa8bf4fc28c0abc92c7fbd1271ff7d7", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "RatanRohith\/NeuralPizza-7B-Merge-Slerp", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 0.92, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "535fd5f9f28bfbd5a46f5f80a1f0c83633ed142b", + "Flagged": false, + "MoE": false + }, + { + "T": "?", + "Model": "Rardilit\/Panther_v1", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "", + "Architecture": "LLaMAForCausalLM", + "Weight type": "Delta", + "Precision": "float16", + "Merged": false, + "Hub License": "other", + "#Params (B)": 0.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "antiven0m\/brugle-rp", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "unknown", + "#Params (B)": 7.24, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": false, + "Model sha": "02096a89cfa76a0bb9aa331a771edd703674b0c3", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "aiplanet\/panda-coder-13B", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "LlamaForCausalLM", + "Weight type": "Original", + "Precision": "4bit", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 8.0, + "Available on the hub": false, + "Model sha": "823a8320224cdac88e927aee00338ffa79395faa", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "kihoonlee\/Merge-13B-v1-test", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 11.54, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "2af514940b5c353502ee1e4f918aae5c516c9680", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "dfurman\/llama-2-13b-dolphin-peft", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "Unknown", + "Weight type": "Adapter", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 13.0, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "5d17f6b5f394f0745bd4377c8a1290c68051e351", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83e\udd1d", + "Model": "AbacusResearch\/jaLLAbi", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "base merges and moerges", + "Architecture": "MixtralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": true, + "Hub License": "apache-2.0", + "#Params (B)": 14.36, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "d5c3d2f5365073d173557ee78764d018d0a0ce86", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udd36", + "Model": "uukuguy\/speechless-mistral-six-in-one-7b-orth-1.0", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "fine-tuned on domain-specific datasets", + "Architecture": "MistralForCausalLM", + "Weight type": "Original", + "Precision": "bfloat16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 7.0, + "Hub \u2764\ufe0f": 1.0, + "Available on the hub": true, + "Model sha": "e500285ba420cb3865d72aa0cc3b1fb9cc0bfee8", + "Flagged": false, + "MoE": true + }, + { + "T": "\ud83d\udcac", + "Model": "kyujinpy\/Sakura-SOLAR-Instruct-DPO-v1", + "Average \u2b06\ufe0f": 20.07, + "ARC": 22.7, + "HellaSwag": 25.04, + "MMLU": 23.12, + "TruthfulQA": 0.0, + "Winogrande": 49.57, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "Unknown", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "?", + "#Params (B)": 10.73, + "Hub \u2764\ufe0f": 0.0, + "Available on the hub": true, + "Model sha": "56cd9f8992e05fa799b33db83e967d1b5f0d5724", + "Flagged": false, + "MoE": false + }, + { + "T": "\ud83d\udcac", + "Model": "Felladrin\/Pythia-31M-Chat-v1", + "Average \u2b06\ufe0f": 19.92, + "ARC": 22.7, + "HellaSwag": 25.6, + "MMLU": 23.24, + "TruthfulQA": 0.0, + "Winogrande": 47.99, + "GSM8K": 0.0, + "Type": "chat models (RLHF, DPO, IFT, ...)", + "Architecture": "GPTNeoXForCausalLM", + "Weight type": "Original", + "Precision": "float16", + "Merged": false, + "Hub License": "apache-2.0", + "#Params (B)": 0.03, + "Hub \u2764\ufe0f": 3.0, + "Available on the hub": true, + "Model sha": "e6a52e4ac98e20c7f9e39aaba9368dd6faacdad9", + "Flagged": false, + "MoE": false + } +] \ No newline at end of file