{
  "_name_or_path": "/workspace/enc_sllm/custom_awq_Qwen2.5-72B-Instruct",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 29568,
  "max_position_embeddings": 32768,
  "max_window_layers": 70,
  "model_type": "qwen2",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "quantization_config": {
    "backend": "autoawq",
    "bits": 4,
    "do_fuse": false,
    "exllama_config": null,
    "fuse_max_seq_len": null,
    "group_size": 128,
    "modules_to_fuse": null,
    "modules_to_not_convert": null,
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.45.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}