{
  "_name_or_path": "/data03/dragon_proj/ChatLaw-MoE/models/moe_chatlaw_4experts-7b",
  "architectures": [
    "InternLM2ForCausalLM"
  ],
  "attn_implementation": "flash_attention_2",
  "auto_map": {
    "AutoConfig": "configuration_internlm.InternLM2Config",
    "AutoModel": "modeling_internlm.InternLM2ForCausalLM",
    "AutoModelForCausalLM": "modeling_internlm.InternLM2ForCausalLM"
  },
  "bias": false,
  "bos_token_id": 1,
  "cor_loss_coef": 0,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "internlm2",
  "num_attention_heads": 32,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "num_local_experts": 4,
  "output_expert_opinion": false,
  "output_router_logits": false,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 2.0,
    "type": "dynamic"
  },
  "rope_theta": 1000000,
  "router_aux_loss_coef": 0.001,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.37.2",
  "use_cache": true,
  "vocab_size": 92544
}