quantize_config.json

{
  "bits": 4,
  "group_size": 128,
  "sym": true,
  "data_type": "int",
  "enable_quanted_input": true,
  "enable_minmax_tuning": true,
  "seqlen": 2048,
  "batch_size": 8,
  "scale_dtype": "torch.float16",
  "lr": 0.005,
  "minmax_lr": 0.005,
  "gradient_accumulate_steps": 1,
  "iters": 200,
  "amp": true,
  "nsamples": 128,
  "low_gpu_mem_usage": 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",
      "model.layers.64",
      "model.layers.65",
      "model.layers.66",
      "model.layers.67",
      "model.layers.68",
      "model.layers.69",
      "model.layers.70",
      "model.layers.71",
      "model.layers.72",
      "model.layers.73",
      "model.layers.74",
      "model.layers.75",
      "model.layers.76",
      "model.layers.77",
      "model.layers.78",
      "model.layers.79"
    ]
  ],
  "enable_norm_bias_tuning": false,
  "autoround_version": "0.4.1",
  "quant_method": "gptq",
  "desc_act": false,
  "true_sequential": false,
  "damp_percent": 0.01
}