quantization_config.json

{
  "bits": 4,
  "group_size": 128,
  "sym": true,
  "data_type": "int",
  "autoround_version": "0.7.0",
  "quant_method": "auto-round",
  "packing_format": "auto_round:auto_gptq",
  "extra_config": {
    "model.layers.0.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.1.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.2.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.3.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.4.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.5.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.6.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.7.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.8.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.9.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.10.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.11.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.12.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.13.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.14.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.15.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.16.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.17.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.18.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.19.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.20.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.21.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.22.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.23.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.24.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.25.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.26.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.27.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.28.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.29.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.30.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.31.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.32.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.33.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.34.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.35.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.36.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.37.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.38.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.39.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.40.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.41.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.42.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.43.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.44.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.45.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.46.mlp.shared_expert_gate": {
      "bits": 16
    },
    "model.layers.47.mlp.shared_expert_gate": {
      "bits": 16
    }
  }
}