quantization_config.json

{
  "bits": 4,
  "data_type": "int",
  "group_size": 128,
  "sym": true,
  "batch_size": 1,
  "iters": 1000,
  "low_gpu_mem_usage": true,
  "autoround_version": "0.10.1",
  "lm_head": false,
  "provider": "auto-round",
  "quant_method": "gptq",
  "desc_act": false,
  "true_sequential": false,
  "damp_percent": 0.01
}