config.json

{
  "architectures": [
    "EagleSpeculator"
  ],
  "auto_map": {
    "": "eagle.EagleSpeculatorConfig"
  },
  "fusion_bias": false,
  "has_no_defaults_at_init": false,
  "layernorms": false,
  "speculators_config": {
    "algorithm": "eagle",
    "default_proposal_method": "greedy",
    "proposal_methods": [
      {
        "accept_tolerance": 0.0,
        "proposal_type": "greedy",
        "speculative_tokens": 5,
        "verifier_accept_k": 1
      }
    ],
    "verifier": {
      "architectures": [
        "LlamaForCausalLM"
      ],
      "name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct"
    }
  },
  "speculators_model_type": "eagle",
  "speculators_version": "0.1.0.dev13",
  "torch_dtype": "float32",
  "transformer_layer_architecture": "LlamaDecoderLayer",
  "transformer_layer_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": 128001,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 2048,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 1,
    "num_key_value_heads": 8,
    "pad_token_id": 0,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000.0,
    "use_cache": true,
    "vocab_size": 128256
  },
  "transformers_version": "4.52.4"
}