{
  "_name_or_path": "/mnt/petrelfs/lvying/LLM/OPUS-BioLLM/model/Meta-Llama-3-8B/",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "device": "cuda",
  "eos_token_id": 128001,
  "freeze_switch_adapter": false,
  "has_protein_encoder": true,
  "has_switch_projector": true,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "opus_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "switch_projector_lr": 1e-05,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 256,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "tune_switch_projector": false,
  "use_cache": true,
  "vocab_size": 128256
}