hf_quant_config.json

{
    "producer": {
        "name": "modelopt",
        "version": "0.45.0"
    },
    "quantization": {
        "quant_algo": "W4A16_AWQ",
        "kv_cache_quant_algo": null,
        "group_size": 128,
        "has_zero_point": false,
        "pre_quant_scale": true,
        "exclude_modules": [
            "lm_head",
            "model.language_model.embed_tokens",
            "model.visual*"
        ]
    }
}