Upload folder using huggingface_hub

config.json

@@ -1,24 +1,29 @@
 {
-    "_name_or_path": "/covalent/.cache/models/tmp00g6emey4etxozmw",
+    "_name_or_path": "/covalent/.cache/models/tmpafjf_1dky4w60szd",
+    "_num_labels": 1,
+    "activation_function": "gelu_new",
     "architectures": [
-        "LlamaForCausalLM"
+        "GPT2LMHeadModel"
     ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bos_token_id": 128000,
-    "eos_token_id": 128001,
-    "head_dim": 64,
-    "hidden_act": "silu",
-    "hidden_size": 2048,
+    "attn_pdrop": 0.1,
+    "bos_token_id": 50256,
+    "embd_pdrop": 0.1,
+    "eos_token_id": 50256,
+    "id2label": {
+        "0": "LABEL_0"
+    },
     "initializer_range": 0.02,
-    "intermediate_size": 8192,
-    "max_position_embeddings": 131072,
-    "mlp_bias": false,
-    "model_type": "llama",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 16,
-    "num_key_value_heads": 8,
-    "pretraining_tp": 1,
+    "label2id": {
+        "LABEL_0": 0
+    },
+    "layer_norm_epsilon": 1e-05,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 6,
+    "n_positions": 1024,
     "quantization_config": {
         "_load_in_4bit": false,
         "_load_in_8bit": true,
@@ -36,19 +41,24 @@
         "load_in_8bit": true,
         "quant_method": "bitsandbytes"
     },
-    "rms_norm_eps": 1e-05,
-    "rope_scaling": {
-        "factor": 32.0,
-        "high_freq_factor": 4.0,
-        "low_freq_factor": 1.0,
-        "original_max_position_embeddings": 8192,
-        "rope_type": "llama3"
+    "reorder_and_upcast_attn": false,
+    "resid_pdrop": 0.1,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "task_specific_params": {
+        "text-generation": {
+            "do_sample": true,
+            "max_length": 50
+        }
     },
-    "rope_theta": 500000.0,
-    "tie_word_embeddings": true,
     "torch_dtype": "float16",
     "transformers_version": "4.46.2",
     "use_cache": true,
-    "vocab_size": 128256,
+    "vocab_size": 50257,
     "api_key": null
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89982eab1669267b2b88a04814a2b133f36faaeb277352724796f6707a9f545
-size 1500097784
+oid sha256:e0827ca788d423a524c1b82cabbdb96fa2cc1b59a95ddded09689a7273d69b8c
+size 121535904

smash_config.json

@@ -28,7 +28,7 @@
     "quant_llm-int8_weight_bits": 8,
     "max_batch_size": 1,
     "device": "cuda",
-    "cache_dir": "/covalent/.cache/models/tmp00g6emey",
+    "cache_dir": "/covalent/.cache/models/tmpafjf_1dk",
     "task": "",
     "save_load_fn": "bitsandbytes",
     "save_load_fn_args": {}