{
  "_name_or_path": "/cpfs01/user/chenmengzhao/efficientqat_repo/EfficientQAT/output/block_ap_models/Mistral-Large-Instruct-2407-w2g64-wlr2e-6-qlr3e-5",
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 12288,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "model_type": "mistral",
  "num_attention_heads": 96,
  "num_hidden_layers": 88,
  "num_key_value_heads": 8,
  "quantization_config": {
    "bits": 2,
    "checkpoint_format": "gptq_v2",
    "damp_percent": 0.01,
    "desc_act": false,
    "group_size": 64,
    "lm_head": false,
    "meta": {
      "quantizer": "gptqmodel:0.9.9-dev0"
    },
    "model_file_base_name": null,
    "model_name_or_path": "/cpfs01/user/chenmengzhao/efficientqat_repo/EfficientQAT/output/block_ap_models/Mistral-Large-Instruct-2407-w2g64-wlr2e-6-qlr3e-5",
    "quant_method": "gptq",
    "static_groups": false,
    "sym": false,
    "true_sequential": true
  },
  "rms_norm_eps": 1e-05,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.40.0",
  "use_cache": true,
  "vocab_size": 32768
}