quantize_config.json

{
  "bits": 4,
  "group_size": 128,
  "damp_percent": 0.01,
  "desc_act": false,
  "static_groups": false,
  "sym": true,
  "true_sequential": true,
  "model_name_or_path": "./TinyLlama-1.1B-Chat-v1.0-g128-gptq",
  "model_file_base_name": "model",
  "is_marlin_format": true,
  "quant_method": "gptq"
}