hf_quant_config.json

{
    "producer": {
        "name": "modelopt",
        "version": "0.0.0"
    },
    "quantization": {
        "quant_algo": "NVFP4",
        "kv_cache_quant_algo": null,
        "group_size": 16,
        "exclude_modules": [
            "model.layers.0.block_sparse_moe.gate",
            "model.layers.1.block_sparse_moe.gate",
            "model.layers.10.block_sparse_moe.gate",
            "model.layers.11.block_sparse_moe.gate",
            "model.layers.12.block_sparse_moe.gate",
            "model.layers.13.block_sparse_moe.gate",
            "model.layers.14.block_sparse_moe.gate",
            "model.layers.15.block_sparse_moe.gate",
            "model.layers.16.block_sparse_moe.gate",
            "model.layers.17.block_sparse_moe.gate",
            "model.layers.18.block_sparse_moe.gate",
            "model.layers.19.block_sparse_moe.gate",
            "model.layers.2.block_sparse_moe.gate",
            "model.layers.20.block_sparse_moe.gate",
            "model.layers.21.block_sparse_moe.gate",
            "model.layers.22.block_sparse_moe.gate",
            "model.layers.23.block_sparse_moe.gate",
            "model.layers.24.block_sparse_moe.gate",
            "model.layers.25.block_sparse_moe.gate",
            "model.layers.26.block_sparse_moe.gate",
            "model.layers.27.block_sparse_moe.gate",
            "model.layers.28.block_sparse_moe.gate",
            "model.layers.29.block_sparse_moe.gate",
            "model.layers.3.block_sparse_moe.gate",
            "model.layers.30.block_sparse_moe.gate",
            "model.layers.31.block_sparse_moe.gate",
            "model.layers.32.block_sparse_moe.gate",
            "model.layers.33.block_sparse_moe.gate",
            "model.layers.34.block_sparse_moe.gate",
            "model.layers.35.block_sparse_moe.gate",
            "model.layers.36.block_sparse_moe.gate",
            "model.layers.37.block_sparse_moe.gate",
            "model.layers.38.block_sparse_moe.gate",
            "model.layers.39.block_sparse_moe.gate",
            "model.layers.4.block_sparse_moe.gate",
            "model.layers.40.block_sparse_moe.gate",
            "model.layers.41.block_sparse_moe.gate",
            "model.layers.42.block_sparse_moe.gate",
            "model.layers.43.block_sparse_moe.gate",
            "model.layers.44.block_sparse_moe.gate",
            "model.layers.45.block_sparse_moe.gate",
            "model.layers.46.block_sparse_moe.gate",
            "model.layers.47.block_sparse_moe.gate",
            "model.layers.48.block_sparse_moe.gate",
            "model.layers.49.block_sparse_moe.gate",
            "model.layers.5.block_sparse_moe.gate",
            "model.layers.50.block_sparse_moe.gate",
            "model.layers.51.block_sparse_moe.gate",
            "model.layers.52.block_sparse_moe.gate",
            "model.layers.53.block_sparse_moe.gate",
            "model.layers.54.block_sparse_moe.gate",
            "model.layers.55.block_sparse_moe.gate",
            "model.layers.56.block_sparse_moe.gate",
            "model.layers.57.block_sparse_moe.gate",
            "model.layers.58.block_sparse_moe.gate",
            "model.layers.59.block_sparse_moe.gate",
            "model.layers.6.block_sparse_moe.gate",
            "model.layers.60.block_sparse_moe.gate",
            "model.layers.61.block_sparse_moe.gate",
            "model.layers.7.block_sparse_moe.gate",
            "model.layers.8.block_sparse_moe.gate",
            "model.layers.9.block_sparse_moe.gate",
            "lm_head"
        ]
    }
}