{ "architectures": [ "Eagle3Speculator" ], "speculators_model_type": "eagle3", "speculators_version": "0.1.0.dev42", "draft_vocab_size": 64000, "norm_before_residual": false, "target_hidden_size": null, "eagle_aux_hidden_state_layer_ids": [ 1, 23, 44 ], "transformer_layer_config": { "model_type": "llama", "vocab_size": 202048, "hidden_size": 5120, "intermediate_size": 32768, "num_hidden_layers": 1, "num_attention_heads": 40, "num_key_value_heads": 8, "head_dim": 128, "hidden_act": "silu", "max_position_embeddings": 1048576, "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000.0, "rope_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "tie_word_embeddings": false }, "speculators_config": { "algorithm": "eagle3", "default_proposal_method": "greedy", "proposal_methods": [ { "proposal_type": "greedy", "speculative_tokens": 3, "verifier_accept_k": 1, "accept_tolerance": 0.0 } ], "verifier": { "name_or_path": "RedHatAI/Llama-4-Maverick-17B-128E-Instruct-quantized.w4a16", "architectures": [ "Llama4ForConditionalGeneration" ] } }, "torch_dtype": "bfloat16", "_comment": "Eagle3 head based on Llama3 architecture targeting Llama4 Maverick verifier", "_conversion_notes": { "source": "nvidia/Llama-4-Maverick-17B-128E-Eagle3", "architecture_notes": "Eagle3 head uses Llama3 rope_type, targets Llama4 verifier", "vocabulary_notes": "Large 202K vocabulary, same for draft and target", "auxiliary_layers": "Uses hidden states from verifier layers 1, 23, 44", "implementation_note": "May require Eagle3Speculator extensions for aux hidden states" } }