quantize_config.json

{
    "bits": 4,
    "group_size": 128,
    "damp_percent": 0.01,
    "desc_act": false,
    "sym": true,
    "true_sequential": true,
    "model_name_or_path": null,
    "model_file_base_name": "model",
    "quant_method": "gptq"
}