progress/github/SpecForge/configs/qwen3-235B-A22B-eagle3.json

{
  "architectures": [
    "LlamaForCausalLMEagle3"
  ],
  "eagle_config": {
    "eagle_aux_hidden_state_layer_ids": [
      1,
      46,
      90
    ],
    "use_aux_hidden_state": true
  },
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "draft_vocab_size": 32000,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 24576,
  "max_position_embeddings": 40960,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 1,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "rope_scaling": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "vocab_size": 151936
}