{
  "_name_or_path": "local_pretrained_llm/Meta-Llama-3.1-8B-Instruct",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "mm_projector_lr": null,
  "mm_seq_hidden_size": 1280,
  "mm_seq_no_pooling": true,
  "mm_seq_projector_type": "linear",
  "mm_seq_select_feature": "cls",
  "mm_seq_select_layer": -1,
  "mm_seq_tower": "ESM",
  "mm_str_hidden_size": 512,
  "mm_str_select_feature": "residue",
  "mm_str_select_layer": -1,
  "mm_struc_projector_type": "linear",
  "mm_struc_tower": "ESMIF",
  "mm_use_seq_start_end": false,
  "mm_use_str_start_end": false,
  "model_type": "pannot_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3",
    "type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.1",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_seq_proj": true,
  "use_mm_str_proj": true,
  "vocab_size": 128256
}