hf_quant_config.json

{
    "producer": {
        "name": "modelopt",
        "version": "0.41.0"
    },
    "quantization": {
        "quant_algo": "NVFP4",
        "kv_cache_quant_algo": null,
        "group_size": 16,
        "exclude_modules": [
            "lm_head",
            "model.layers.0.self_attn.kv_a_proj_with_mqa",
            "model.layers.0.self_attn.kv_b_proj",
            "model.layers.0.self_attn.q_a_proj",
            "model.layers.0.self_attn.q_b_proj",
            "model.layers.1.self_attn.kv_a_proj_with_mqa",
            "model.layers.1.self_attn.kv_b_proj",
            "model.layers.1.self_attn.q_a_proj",
            "model.layers.1.self_attn.q_b_proj",
            "model.layers.10.self_attn.kv_a_proj_with_mqa",
            "model.layers.10.self_attn.kv_b_proj",
            "model.layers.10.self_attn.q_a_proj",
            "model.layers.10.self_attn.q_b_proj",
            "model.layers.11.self_attn.kv_a_proj_with_mqa",
            "model.layers.11.self_attn.kv_b_proj",
            "model.layers.11.self_attn.q_a_proj",
            "model.layers.11.self_attn.q_b_proj",
            "model.layers.12.self_attn.kv_a_proj_with_mqa",
            "model.layers.12.self_attn.kv_b_proj",
            "model.layers.12.self_attn.q_a_proj",
            "model.layers.12.self_attn.q_b_proj",
            "model.layers.13.self_attn.kv_a_proj_with_mqa",
            "model.layers.13.self_attn.kv_b_proj",
            "model.layers.13.self_attn.q_a_proj",
            "model.layers.13.self_attn.q_b_proj",
            "model.layers.14.self_attn.kv_a_proj_with_mqa",
            "model.layers.14.self_attn.kv_b_proj",
            "model.layers.14.self_attn.q_a_proj",
            "model.layers.14.self_attn.q_b_proj",
            "model.layers.15.self_attn.kv_a_proj_with_mqa",
            "model.layers.15.self_attn.kv_b_proj",
            "model.layers.15.self_attn.q_a_proj",
            "model.layers.15.self_attn.q_b_proj",
            "model.layers.2.self_attn.kv_a_proj_with_mqa",
            "model.layers.2.self_attn.kv_b_proj",
            "model.layers.2.self_attn.q_a_proj",
            "model.layers.2.self_attn.q_b_proj",
            "model.layers.3.self_attn.kv_a_proj_with_mqa",
            "model.layers.3.self_attn.kv_b_proj",
            "model.layers.3.self_attn.q_a_proj",
            "model.layers.3.self_attn.q_b_proj",
            "model.layers.4.self_attn.kv_a_proj_with_mqa",
            "model.layers.4.self_attn.kv_b_proj",
            "model.layers.4.self_attn.q_a_proj",
            "model.layers.4.self_attn.q_b_proj",
            "model.layers.5.self_attn.kv_a_proj_with_mqa",
            "model.layers.5.self_attn.kv_b_proj",
            "model.layers.5.self_attn.q_a_proj",
            "model.layers.5.self_attn.q_b_proj",
            "model.layers.6.self_attn.kv_a_proj_with_mqa",
            "model.layers.6.self_attn.kv_b_proj",
            "model.layers.6.self_attn.q_a_proj",
            "model.layers.6.self_attn.q_b_proj",
            "model.layers.7.self_attn.kv_a_proj_with_mqa",
            "model.layers.7.self_attn.kv_b_proj",
            "model.layers.7.self_attn.q_a_proj",
            "model.layers.7.self_attn.q_b_proj",
            "model.layers.8.self_attn.kv_a_proj_with_mqa",
            "model.layers.8.self_attn.kv_b_proj",
            "model.layers.8.self_attn.q_a_proj",
            "model.layers.8.self_attn.q_b_proj",
            "model.layers.9.self_attn.kv_a_proj_with_mqa",
            "model.layers.9.self_attn.kv_b_proj",
            "model.layers.9.self_attn.q_a_proj",
            "model.layers.9.self_attn.q_b_proj"
        ]
    }
}