step-37-flash/hf_quant_config.json

{
    "producer": {
        "name": "modelopt",
        "version": "0.45.0.dev37+g3ad4f4f09.d20260524"
    },
    "quantization": {
        "quant_algo": "NVFP4",
        "kv_cache_quant_algo": "FP8",
        "group_size": 16,
        "exclude_modules": [
            "lm_head",
            "model.language_model.layers.0*",
            "model.language_model.layers.1.*",
            "model.language_model.layers.10.moe.gate",
            "model.language_model.layers.10.self_attn*",
            "model.language_model.layers.10.share_expert*",
            "model.language_model.layers.11.moe.gate",
            "model.language_model.layers.11.self_attn*",
            "model.language_model.layers.11.share_expert*",
            "model.language_model.layers.12.moe.gate",
            "model.language_model.layers.12.self_attn*",
            "model.language_model.layers.12.share_expert*",
            "model.language_model.layers.13.moe.gate",
            "model.language_model.layers.13.self_attn*",
            "model.language_model.layers.13.share_expert*",
            "model.language_model.layers.14.moe.gate",
            "model.language_model.layers.14.self_attn*",
            "model.language_model.layers.14.share_expert*",
            "model.language_model.layers.15.moe.gate",
            "model.language_model.layers.15.self_attn*",
            "model.language_model.layers.15.share_expert*",
            "model.language_model.layers.16.moe.gate",
            "model.language_model.layers.16.self_attn*",
            "model.language_model.layers.16.share_expert*",
            "model.language_model.layers.17.moe.gate",
            "model.language_model.layers.17.self_attn*",
            "model.language_model.layers.17.share_expert*",
            "model.language_model.layers.18.moe.gate",
            "model.language_model.layers.18.self_attn*",
            "model.language_model.layers.18.share_expert*",
            "model.language_model.layers.19.moe.gate",
            "model.language_model.layers.19.self_attn*",
            "model.language_model.layers.19.share_expert*",
            "model.language_model.layers.2.*",
            "model.language_model.layers.20.moe.gate",
            "model.language_model.layers.20.self_attn*",
            "model.language_model.layers.20.share_expert*",
            "model.language_model.layers.21.moe.gate",
            "model.language_model.layers.21.self_attn*",
            "model.language_model.layers.21.share_expert*",
            "model.language_model.layers.22.moe.gate",
            "model.language_model.layers.22.self_attn*",
            "model.language_model.layers.22.share_expert*",
            "model.language_model.layers.23.moe.gate",
            "model.language_model.layers.23.self_attn*",
            "model.language_model.layers.23.share_expert*",
            "model.language_model.layers.24.moe.gate",
            "model.language_model.layers.24.self_attn*",
            "model.language_model.layers.24.share_expert*",
            "model.language_model.layers.25.moe.gate",
            "model.language_model.layers.25.self_attn*",
            "model.language_model.layers.25.share_expert*",
            "model.language_model.layers.26.moe.gate",
            "model.language_model.layers.26.self_attn*",
            "model.language_model.layers.26.share_expert*",
            "model.language_model.layers.27.moe.gate",
            "model.language_model.layers.27.self_attn*",
            "model.language_model.layers.27.share_expert*",
            "model.language_model.layers.28.moe.gate",
            "model.language_model.layers.28.self_attn*",
            "model.language_model.layers.28.share_expert*",
            "model.language_model.layers.29.moe.gate",
            "model.language_model.layers.29.self_attn*",
            "model.language_model.layers.29.share_expert*",
            "model.language_model.layers.3.moe.gate",
            "model.language_model.layers.3.self_attn*",
            "model.language_model.layers.3.share_expert*",
            "model.language_model.layers.30.moe.gate",
            "model.language_model.layers.30.self_attn*",
            "model.language_model.layers.30.share_expert*",
            "model.language_model.layers.31.moe.gate",
            "model.language_model.layers.31.self_attn*",
            "model.language_model.layers.31.share_expert*",
            "model.language_model.layers.32.moe.gate",
            "model.language_model.layers.32.self_attn*",
            "model.language_model.layers.32.share_expert*",
            "model.language_model.layers.33.moe.gate",
            "model.language_model.layers.33.self_attn*",
            "model.language_model.layers.33.share_expert*",
            "model.language_model.layers.34.moe.gate",
            "model.language_model.layers.34.self_attn*",
            "model.language_model.layers.34.share_expert*",
            "model.language_model.layers.35.moe.gate",
            "model.language_model.layers.35.self_attn*",
            "model.language_model.layers.35.share_expert*",
            "model.language_model.layers.36.moe.gate",
            "model.language_model.layers.36.self_attn*",
            "model.language_model.layers.36.share_expert*",
            "model.language_model.layers.37.moe.gate",
            "model.language_model.layers.37.self_attn*",
            "model.language_model.layers.37.share_expert*",
            "model.language_model.layers.38.moe.gate",
            "model.language_model.layers.38.self_attn*",
            "model.language_model.layers.38.share_expert*",
            "model.language_model.layers.39.moe.gate",
            "model.language_model.layers.39.self_attn*",
            "model.language_model.layers.39.share_expert*",
            "model.language_model.layers.4.moe.gate",
            "model.language_model.layers.4.self_attn*",
            "model.language_model.layers.4.share_expert*",
            "model.language_model.layers.40.moe.gate",
            "model.language_model.layers.40.self_attn*",
            "model.language_model.layers.40.share_expert*",
            "model.language_model.layers.41.moe.gate",
            "model.language_model.layers.41.self_attn*",
            "model.language_model.layers.41.share_expert*",
            "model.language_model.layers.42.moe.gate",
            "model.language_model.layers.42.self_attn*",
            "model.language_model.layers.42.share_expert*",
            "model.language_model.layers.43.moe.gate",
            "model.language_model.layers.43.self_attn*",
            "model.language_model.layers.43.share_expert*",
            "model.language_model.layers.44.moe.gate",
            "model.language_model.layers.44.self_attn*",
            "model.language_model.layers.44.share_expert*",
            "model.language_model.layers.5.moe.gate",
            "model.language_model.layers.5.self_attn*",
            "model.language_model.layers.5.share_expert*",
            "model.language_model.layers.6.moe.gate",
            "model.language_model.layers.6.self_attn*",
            "model.language_model.layers.6.share_expert*",
            "model.language_model.layers.7.moe.gate",
            "model.language_model.layers.7.self_attn*",
            "model.language_model.layers.7.share_expert*",
            "model.language_model.layers.8.moe.gate",
            "model.language_model.layers.8.self_attn*",
            "model.language_model.layers.8.share_expert*",
            "model.language_model.layers.9.moe.gate",
            "model.language_model.layers.9.self_attn*",
            "model.language_model.layers.9.share_expert*",
            "model.vision_model*",
            "model.vit_large_projector"
        ]
    }
}