hf_quant_config.json

{
  "producer": {
    "name": "modelopt",
    "version": "0.46.0"
  },
  "quantization": {
    "exclude_modules": [
      "model.embed_tokens",
      "mtp.*",
      "model.mtp.*",
      "*.self_attn.*",
      "*.linear_attn.*",
      "*.mlp.gate*",
      "*.mlp.shared_expert.*",
      "*.mlp.shared_expert_gate*",
      "*hyper_connection*",
      "*.ple.*",
      "model.visual.*",
      "model.language_model.embed_tokens",
      "lm_head"
    ],
    "group_size": 16,
    "quant_algo": "NVFP4"
  }
}