{
  "_name_or_path": "/workspace/models-140/InternLM/internlm2_5-20b-chat",
  "architectures": [
    "InternLM2ForCausalLM"
  ],
  "attn_implementation": "eager",
  "auto_map": {
    "AutoConfig": "configuration_internlm2.InternLM2Config",
    "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
    "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
    "AutoModelForSequenceClassification": "modeling_internlm2.InternLM2ForSequenceClassification"
  },
  "bias": false,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 6144,
  "initializer_range": 0.02,
  "intermediate_size": 16384,
  "max_position_embeddings": 32768,
  "model_type": "internlm2",
  "num_attention_heads": 48,
  "num_hidden_layers": 48,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 4,
    "damp_percent": 0.01,
    "desc_act": false,
    "group_size": 128,
    "is_marlin_format": false,
    "model_file_base_name": null,
    "model_name_or_path": null,
    "quant_method": "gptq",
    "static_groups": false,
    "sym": true,
    "true_sequential": true
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 2.5,
    "type": "dynamic"
  },
  "rope_theta": 50000000,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.44.2",
  "use_cache": true,
  "vocab_size": 92544
}