{
  "dtype": "int4",
  "input_info": null,
  "optimum_version": "2.3.0",
  "output_attentions": false,
  "quantization_config": {
    "_dataset_kwargs": {},
    "dataset": null,
    "default_config": {
      "quant_method": "default"
    },
    "ignored_scope": null,
    "num_samples": null,
    "processor": "/mnt/local-scratch/work/src_model/",
    "quantization_configs": {
      "lm_model": {
        "_dataset_kwargs": {},
        "all_layers": null,
        "backup_precision": null,
        "bits": 4,
        "dataset": null,
        "dq_group_size": 64,
        "dtype": "int4",
        "gptq": null,
        "group_size": 64,
        "group_size_fallback": "adjust",
        "ignored_scope": {
          "patterns": [
            ".*router.*"
          ]
        },
        "lora_correction": null,
        "num_samples": null,
        "processor": "/mnt/local-scratch/work/src_model/",
        "quant_method": "awq",
        "ratio": 1.0,
        "scale_estimation": null,
        "sensitivity_metric": null,
        "statistics_path": null,
        "sym": false,
        "tokenizer": "/mnt/local-scratch/work/src_model/"
      }
    },
    "tokenizer": "/mnt/local-scratch/work/src_model/"
  },
  "save_onnx_model": false,
  "transformers_version": "5.5.0"
}