hf_quant_config.json

{
  "producer": {
    "name": "modelopt",
    "version": "0.39.0"
  },
  "quantization": {
    "quant_algo": "NVFP4",
    "kv_cache_quant_algo": null,
    "group_size": 16,
    "exclude_modules": [
      "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.3.self_attn*",
      "model.layers.4.self_attn*",
      "model.layers.5.self_attn*",
      "model.layers.6.self_attn*",
      "model.layers.7.self_attn*",
      "model.layers.8.self_attn*",
      "model.layers.9.self_attn*",
      "lm_head"
    ]
  }
}