hf_quant_config.json

{
    "producer": {
        "name": "modelopt",
        "version": "0.0.1.dev1+g82f1d216d"
    },
    "quantization": {
        "quant_algo": "NVFP4",
        "kv_cache_quant_algo": null,
        "group_size": 16,
        "exclude_modules": [
            "lm_head",
            "model.language_model.layers.0.linear_attn.conv1d",
            "model.language_model.layers.1.linear_attn.conv1d",
            "model.language_model.layers.10.linear_attn.conv1d",
            "model.language_model.layers.12.linear_attn.conv1d",
            "model.language_model.layers.13.linear_attn.conv1d",
            "model.language_model.layers.14.linear_attn.conv1d",
            "model.language_model.layers.16.linear_attn.conv1d",
            "model.language_model.layers.17.linear_attn.conv1d",
            "model.language_model.layers.18.linear_attn.conv1d",
            "model.language_model.layers.2.linear_attn.conv1d",
            "model.language_model.layers.20.linear_attn.conv1d",
            "model.language_model.layers.21.linear_attn.conv1d",
            "model.language_model.layers.22.linear_attn.conv1d",
            "model.language_model.layers.24.linear_attn.conv1d",
            "model.language_model.layers.25.linear_attn.conv1d",
            "model.language_model.layers.26.linear_attn.conv1d",
            "model.language_model.layers.28.linear_attn.conv1d",
            "model.language_model.layers.29.linear_attn.conv1d",
            "model.language_model.layers.30.linear_attn.conv1d",
            "model.language_model.layers.4.linear_attn.conv1d",
            "model.language_model.layers.5.linear_attn.conv1d",
            "model.language_model.layers.6.linear_attn.conv1d",
            "model.language_model.layers.8.linear_attn.conv1d",
            "model.language_model.layers.9.linear_attn.conv1d",
            "model.visual*",
            "mtp.layers.0*"
        ]
    }
}