quantize_config.json

{
  "bits": 4,
  "group_size": 128,
  "damp_percent": 0.01,
  "desc_act": false,
  "static_groups": false,
  "sym": false,
  "true_sequential": false,
  "lm_head": true,
  "model_name_or_path": null,
  "model_file_base_name": "model",
  "quant_method": "gptq",
  "checkpoint_format": "gptq",
  "meta": {
    "quantizer": "intel/auto-round:0.1",
    "packer": "gptqmodel:0.9.0",
    "iters": 400,
    "lr": 0.0025,
    "minmax_lr": 0.0025,
    "enable_minmax_tuning": true,
    "use_quant_input": false,
    "scale_dtype": "torch.float16"
  }
}