hf_quant_config.json

{
    "producer": {
        "name": "modelopt",
        "version": "0.37.0.dev25+g76e8ce21b"
    },
    "quantization": {
        "quant_algo": "NVFP4",
        "kv_cache_quant_algo": null,
        "group_size": 16,
        "exclude_modules": [
            "model.layers.0.mlp.gate",
            "model.layers.1.mlp.gate",
            "model.layers.10.mlp.gate",
            "model.layers.11.mlp.gate",
            "model.layers.12.mlp.gate",
            "model.layers.13.mlp.gate",
            "model.layers.14.mlp.gate",
            "model.layers.15.mlp.gate",
            "model.layers.16.mlp.gate",
            "model.layers.17.mlp.gate",
            "model.layers.18.mlp.gate",
            "model.layers.19.mlp.gate",
            "model.layers.2.mlp.gate",
            "model.layers.20.mlp.gate",
            "model.layers.21.mlp.gate",
            "model.layers.22.mlp.gate",
            "model.layers.23.mlp.gate",
            "model.layers.24.mlp.gate",
            "model.layers.25.mlp.gate",
            "model.layers.26.mlp.gate",
            "model.layers.27.mlp.gate",
            "model.layers.28.mlp.gate",
            "model.layers.29.mlp.gate",
            "model.layers.3.mlp.gate",
            "model.layers.30.mlp.gate",
            "model.layers.31.mlp.gate",
            "model.layers.32.mlp.gate",
            "model.layers.33.mlp.gate",
            "model.layers.34.mlp.gate",
            "model.layers.35.mlp.gate",
            "model.layers.36.mlp.gate",
            "model.layers.37.mlp.gate",
            "model.layers.38.mlp.gate",
            "model.layers.39.mlp.gate",
            "model.layers.4.mlp.gate",
            "model.layers.40.mlp.gate",
            "model.layers.41.mlp.gate",
            "model.layers.42.mlp.gate",
            "model.layers.43.mlp.gate",
            "model.layers.44.mlp.gate",
            "model.layers.45.mlp.gate",
            "model.layers.46.mlp.gate",
            "model.layers.47.mlp.gate",
            "model.layers.5.mlp.gate",
            "model.layers.6.mlp.gate",
            "model.layers.7.mlp.gate",
            "model.layers.8.mlp.gate",
            "model.layers.9.mlp.gate",
            "lm_head"
        ]
    }
}