{
  "architectures": [
    "LlamaForCausalLMEagle3"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "fc_norm": true,
  "norm_output": true,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 6144,
  "initializer_range": 0.02,
  "intermediate_size": 18432,
  "max_position_embeddings": 1048576,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 1,
  "num_key_value_heads": 64,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 200064,
  "draft_vocab_size": 200064,
  "_torchspec_version": "0.1.0",
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "rfi-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "num_bits": 6,
          "type": "int",
          "group_size": 32,
          "scale_dtype": "torch.int8",
          "scale_exp_dtype": "torch.int8",
          "scale_encoding": "block_float_i8m_i8e",
          "symmetric": true,
          "act_dtype": "int8",
          "rotation": "hadamard32"
        }
      }
    },
    "format": "rfi-quantized",
    "quant_method": "rfi",
    "quantization_status": "compressed",
    "version": "rfi-1.0",
    "ignore": [
      "re:^lm_head",
      "re:^embed_tokens\\."
    ]
  }
}