{
  "bits": 4,
  "dynamic": {
    "+:.*shared_mlp": {
      "bits": 4,
      "group_size": 64
    },
    "+:.*experts": {
      "bits": 4,
      "group_size": 64
    }
  },
  "group_size": 128,
  "desc_act": false,
  "lm_head": false,
  "method": "gptq",
  "quant_method": "gptq",
  "format": "gptq",
  "checkpoint_format": "gptq",
  "pack_dtype": "int32",
  "meta": {
    "quantizer": [
      "gptqmodel:7.2.0"
    ],
    "uri": "https://github.com/modelcloud/gptqmodel",
    "damp_percent": null,
    "damp_auto_increment": null,
    "static_groups": null,
    "true_sequential": true,
    "mse": null,
    "gptaq": null,
    "foem": null,
    "act_group_aware": null,
    "fallback": {
      "strategy": "rtn",
      "threshold": "0.5%",
      "smooth": null
    },
    "offload_to_disk": true,
    "offload_to_disk_path": "/home/ubuntu/tmp_for_install/gptqmodel_kctb93p5",
    "pack_impl": "cpu",
    "gc_mode": "on_stage_end",
    "wait_for_submodule_finalizers": true,
    "auto_forward_data_parallel": true,
    "dense_vram_strategy": "exclusive",
    "dense_vram_strategy_devices": null,
    "moe_vram_strategy": "exclusive",
    "moe_vram_strategy_devices": null,
    "weight_only": {
      "smooth": null
    }
  },
  "sym": true
}