hf_quant_config.json

{
    "config_groups": {
        "group_0": {
            "input_activations": {
                "dynamic": false,
                "num_bits": 4,
                "type": "float",
                "group_size": 16
            },
            "weights": {
                "dynamic": false,
                "num_bits": 4,
                "type": "float",
                "group_size": 16
            },
            "targets": [
                "Linear"
            ]
        }
    },
    "ignore": [
        "lm_head",
        "model.layers.0.self_attn*",
        "model.layers.1.self_attn*",
        "model.layers.10.self_attn*",
        "model.layers.11.self_attn*",
        "model.layers.12.self_attn*",
        "model.layers.13.self_attn*",
        "model.layers.14.self_attn*",
        "model.layers.15.self_attn*",
        "model.layers.16.self_attn*",
        "model.layers.17.self_attn*",
        "model.layers.18.self_attn*",
        "model.layers.19.self_attn*",
        "model.layers.2.self_attn*",
        "model.layers.20.self_attn*",
        "model.layers.21.self_attn*",
        "model.layers.22.self_attn*",
        "model.layers.23.self_attn*",
        "model.layers.24.self_attn*",
        "model.layers.25.self_attn*",
        "model.layers.26.self_attn*",
        "model.layers.27.self_attn*",
        "model.layers.28.self_attn*",
        "model.layers.29.self_attn*",
        "model.layers.3.self_attn*",
        "model.layers.30.self_attn*",
        "model.layers.31.self_attn*",
        "model.layers.32.self_attn*",
        "model.layers.33.self_attn*",
        "model.layers.34.self_attn*",
        "model.layers.35.self_attn*",
        "model.layers.36.self_attn*",
        "model.layers.37.self_attn*",
        "model.layers.38.self_attn*",
        "model.layers.39.self_attn*",
        "model.layers.4.self_attn*",
        "model.layers.40.self_attn*",
        "model.layers.41.self_attn*",
        "model.layers.42.self_attn*",
        "model.layers.43.self_attn*",
        "model.layers.44.self_attn*",
        "model.layers.45.self_attn*",
        "model.layers.46.self_attn*",
        "model.layers.47.self_attn*",
        "model.layers.48.self_attn*",
        "model.layers.49.self_attn*",
        "model.layers.5.self_attn*",
        "model.layers.50.self_attn*",
        "model.layers.51.self_attn*",
        "model.layers.52.self_attn*",
        "model.layers.53.self_attn*",
        "model.layers.54.self_attn*",
        "model.layers.55.self_attn*",
        "model.layers.56.self_attn*",
        "model.layers.57.self_attn*",
        "model.layers.58.self_attn*",
        "model.layers.59.self_attn*",
        "model.layers.6.self_attn*",
        "model.layers.60.self_attn*",
        "model.layers.61.self_attn*",
        "model.layers.62.self_attn*",
        "model.layers.63.self_attn*",
        "model.layers.64.self_attn*",
        "model.layers.65.self_attn*",
        "model.layers.66.self_attn*",
        "model.layers.67.self_attn*",
        "model.layers.68.self_attn*",
        "model.layers.69.self_attn*",
        "model.layers.7.self_attn*",
        "model.layers.8.self_attn*",
        "model.layers.9.self_attn*"
    ],
    "quant_algo": "NVFP4",
    "kv_cache_scheme": {
        "dynamic": false,
        "num_bits": 8,
        "type": "float"
    },
    "producer": {
        "name": "modelopt",
        "version": "0.43.0"
    },
    "quant_method": "modelopt"
}