| { | |
| "_name_or_path": "/leonardo_work/EUHPC_D19_097/mllm/checkpoints/whisper-large-v3_Llama-Krikri-8B-Base_injec=21_frozenWhisper=True_inputMasking=False_full=True/checkpoint-3000", | |
| "add_lora": true, | |
| "architectures": [ | |
| "SLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_implementation": null, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "frozen_whisper": true, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "injection_layer": 21, | |
| "intermediate_size": 11008, | |
| "llm_lora_config": { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "ilsp/Llama-Krikri-8B-Base", | |
| "bias": "none", | |
| "eva_config": null, | |
| "exclude_modules": null, | |
| "fan_in_fan_out": false, | |
| "inference_mode": false, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 16, | |
| "lora_bias": "none", | |
| "lora_dropout": 0.1, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 8, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": "layers\\.\\d+\\.(self_attn\\.(q_proj|k_proj|v_proj|o_proj)|mlp\\.(gate_proj|up_proj|down_proj))", | |
| "task_type": null, | |
| "use_dora": false, | |
| "use_rslora": false | |
| }, | |
| "llm_path": "ilsp/Llama-Krikri-8B-Base", | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "streaming": false, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.50.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 149248, | |
| "whisper_generation_config": null, | |
| "whisper_is_multilingual": false, | |
| "whisper_language": "el", | |
| "whisper_lora_config": { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": null, | |
| "bias": "none", | |
| "eva_config": null, | |
| "exclude_modules": null, | |
| "fan_in_fan_out": false, | |
| "inference_mode": false, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 16, | |
| "lora_bias": "none", | |
| "lora_dropout": 0.1, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 8, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": "model\\.decoder\\.layers\\.\\d+\\.(self_attn|encoder_attn)\\.(q_proj|k_proj|v_proj|out_proj)|model\\.decoder\\.layers\\.\\d+\\.(fc1|fc2)", | |
| "task_type": null, | |
| "use_dora": false, | |
| "use_rslora": false | |
| }, | |
| "whisper_path": "openai/whisper-large-v3", | |
| "whisper_task": "transcribe", | |
| "whisper_temperature": 0.0 | |
| } | |