quantize_config.json

{
  "bits": 4,
  "dynamic": null,
  "group_size": 128,
  "desc_act": false,
  "static_groups": false,
  "sym": true,
  "lm_head": false,
  "damp_percent": 0.005,
  "damp_auto_increment": 0.0015,
  "true_sequential": true,
  "model_name_or_path": "/monster/data/model/TinyLlama-1.1B-Chat-v1.0/gptq_4bits_10-24_10-47-05_maxlen2048_ns1024_descFalse_damp0.005",
  "model_file_base_name": "model",
  "quant_method": "gptq",
  "checkpoint_format": "gptq",
  "meta": {
    "quantizer": "gptqmodel:1.0.10-dev"
  }
}