{
  "_name_or_path": "/data5/models/QwQ-32B-Preview",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 27648,
  "max_position_embeddings": 32768,
  "max_window_layers": 64,
  "model_type": "qwen2",
  "num_attention_heads": 40,
  "num_hidden_layers": 64,
  "num_key_value_heads": 8,
  "quantization_config": {
    "amp": true,
    "autoround_version": "0.4.1",
    "backend": "auto_round:gptq:exllamav2",
    "batch_size": 8,
    "bits": 4,
    "data_type": "int",
    "dataset": "NeelNanda/pile-10k",
    "enable_minmax_tuning": true,
    "enable_norm_bias_tuning": false,
    "enable_quanted_input": true,
    "extra_config": {
      "model.layers.5.mlp.down_proj": {
        "bits": 16,
        "data_type": "float"
      },
      "model.layers.5.mlp.gate_proj": {
        "bits": 16,
        "data_type": "float"
      },
      "model.layers.5.mlp.up_proj": {
        "bits": 16,
        "data_type": "float"
      }
    },
    "gradient_accumulate_steps": 1,
    "group_size": 128,
    "iters": 200,
    "low_gpu_mem_usage": false,
    "lr": 0.005,
    "minmax_lr": 0.005,
    "nsamples": 128,
    "quant_method": "intel/auto-round",
    "scale_dtype": "torch.float16",
    "seqlen": 2048,
    "sym": true,
    "to_quant_block_names": [
      [
        "model.layers.0",
        "model.layers.1",
        "model.layers.2",
        "model.layers.3",
        "model.layers.4",
        "model.layers.5",
        "model.layers.6",
        "model.layers.7",
        "model.layers.8",
        "model.layers.9",
        "model.layers.10",
        "model.layers.11",
        "model.layers.12",
        "model.layers.13",
        "model.layers.14",
        "model.layers.15",
        "model.layers.16",
        "model.layers.17",
        "model.layers.18",
        "model.layers.19",
        "model.layers.20",
        "model.layers.21",
        "model.layers.22",
        "model.layers.23",
        "model.layers.24",
        "model.layers.25",
        "model.layers.26",
        "model.layers.27",
        "model.layers.28",
        "model.layers.29",
        "model.layers.30",
        "model.layers.31",
        "model.layers.32",
        "model.layers.33",
        "model.layers.34",
        "model.layers.35",
        "model.layers.36",
        "model.layers.37",
        "model.layers.38",
        "model.layers.39",
        "model.layers.40",
        "model.layers.41",
        "model.layers.42",
        "model.layers.43",
        "model.layers.44",
        "model.layers.45",
        "model.layers.46",
        "model.layers.47",
        "model.layers.48",
        "model.layers.49",
        "model.layers.50",
        "model.layers.51",
        "model.layers.52",
        "model.layers.53",
        "model.layers.54",
        "model.layers.55",
        "model.layers.56",
        "model.layers.57",
        "model.layers.58",
        "model.layers.59",
        "model.layers.60",
        "model.layers.61",
        "model.layers.62",
        "model.layers.63"
      ]
    ]
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.47.0.dev0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}