{
  "bits": 4,
  "group_size": 128,
  "desc_act": false,
  "sym": false,
  "lm_head": false,
  "quant_method": "gptq",
  "checkpoint_format": "gptq",
  "pack_dtype": "int32",
  "meta": {
    "quantizer": [
      "gptqmodel:5.7.0-dev"
    ],
    "uri": "https://github.com/modelcloud/gptqmodel",
    "damp_percent": 0.1,
    "damp_auto_increment": 0.01,
    "static_groups": false,
    "true_sequential": true,
    "mse": 0.0,
    "gptaq": false,
    "gptaq_alpha": 0.25,
    "act_group_aware": true,
    "failsafe": {
      "strategy": "rtn",
      "threshold": "0.5%",
      "smooth": {
        "type": "mad",
        "group_size_threshold": 128,
        "k": 2.75
      }
    },
    "gptaq_memory_device": "auto",
    "offload_to_disk": true,
    "offload_to_disk_path": "./gptqmodel_offload/hqdpgrum-rkaakpxx/",
    "pack_impl": "cpu",
    "mock_quantization": false,
    "hessian_chunk_size": null,
    "hessian_chunk_bytes": null,
    "hessian_use_bfloat16_staging": false,
    "vram_strategy": "exclusive"
  },
  "format": "gptq"
}