quantize_config.json

{
  "bits": 4,
  "group_size": 128,
  "desc_act": false,
  "static_groups": false,
  "sym": false,
  "lm_head": false,
  "damp_percent": 0.01,
  "true_sequential": true,
  "model_name_or_path": "/cpfs01/user/chenmengzhao/efficientqat_repo/efficientqat_checkpoints_BitBLAS/Llama-3-8b-instruct-EfficientQAT-w4g128-BitBLAS",
  "model_file_base_name": "model",
  "quant_method": "gptq",
  "checkpoint_format": "bitblas",
  "meta": {
    "quantizer": "gptqmodel:0.9.9-dev0"
  }
}