quantize_config.json

{
  "bits": 4,
  "group_size": 32,
  "desc_act": true,
  "static_groups": false,
  "sym": true,
  "lm_head": false,
  "damp_percent": 0.005,
  "true_sequential": true,
  "model_name_or_path": "NousResearch/Hermes-2-Pro-Mistral-7B-4bit-32g",
  "model_file_base_name": "model",
  "quant_method": "gptq",
  "checkpoint_format": "gptq",
  "meta": {
    "quantizer": "gptqmodel:0.9.9"
  }
}