| { |
| "model_type": "llama_eagle", |
| "speculators_version": "0.1.0", |
| "speculators_config": { |
| "algorithm": "eagle", |
| "proposal_methods": [ |
| { |
| "proposal_type": "greedy", |
| "draft_tokens": 5 |
| }, |
| { |
| "proposal_type": "static_tree", |
| "draft_tokens": 10, |
| "initial_branching_factor": 4, |
| "branching_factor": 2, |
| "depth": 5 |
| } |
| ], |
| "default_proposal_method": "greedy", |
| "verifier": { |
| "name_or_path": "meta-llama/Llama-3.1-8B-Instruct", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "hidden_size": 4096, |
| "vocab_size": 128256, |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "intermediate_size": 14336, |
| "model_type": "llama", |
| "max_position_embeddings": 131072, |
| "bos_token_id": 128000, |
| "eos_token_id": [ |
| 128001, |
| 128008, |
| 128009 |
| ] |
| } |
| }, |
| "architectures": [ |
| "LlamaEagleSpeculator" |
| ], |
| "torch_dtype": "float16", |
| "inputs": [ |
| "input_ids", |
| "hidden_states[-1]" |
| ], |
| "inputs_hidden_states_normalized": false, |
| "transformer_layer_type": "LlamaDecoderLayer", |
| "transformer_input_type": "linear_no_bias", |
| "transformer_remove_last_layer_norm": false, |
| "use_verifier_lm_head": false, |
| "eagle_variant": "eagle_v1", |
| "fc_bias": false, |
| "use_extra_layernorms": false, |
| "replace_first_layer_norm": true, |
| "extra_layernorm_positions": [], |
| "num_hidden_layers": 1, |
| "use_final_norm": true, |
| "vocab_size": 128256, |
| "hidden_size": 4096, |
| "_name_or_path": "", |
| "transformers_version": "4.28.1", |
| "base_model_tp_plan": null, |
| "base_model_pp_plan": null, |
| "intermediate_size": 14336, |
| "num_attention_heads": 32, |
| "num_key_value_heads": 8, |
| "max_position_embeddings": 2048, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 500000.0, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "mlp_bias": false, |
| "hidden_act": "silu", |
| "use_cache": true, |
| "rope_scaling": null, |
| "bos_token_id": 128000, |
| "eos_token_id": 128001, |
| "return_dict": true, |
| "output_hidden_states": false, |
| "output_attentions": false, |
| "torchscript": false, |
| "use_bfloat16": false, |
| "tf_legacy_loss": false, |
| "pruned_heads": {}, |
| "tie_word_embeddings": true, |
| "chunk_size_feed_forward": 0, |
| "is_encoder_decoder": false, |
| "is_decoder": false, |
| "cross_attention_hidden_size": null, |
| "add_cross_attention": false, |
| "tie_encoder_decoder": false, |
| "max_length": 20, |
| "min_length": 0, |
| "do_sample": false, |
| "early_stopping": false, |
| "num_beams": 1, |
| "num_beam_groups": 1, |
| "diversity_penalty": 0.0, |
| "temperature": 1.0, |
| "top_k": 50, |
| "top_p": 1.0, |
| "typical_p": 1.0, |
| "repetition_penalty": 1.0, |
| "length_penalty": 1.0, |
| "no_repeat_ngram_size": 0, |
| "encoder_no_repeat_ngram_size": 0, |
| "bad_words_ids": null, |
| "num_return_sequences": 1, |
| "output_scores": false, |
| "return_dict_in_generate": false, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "remove_invalid_values": false, |
| "exponential_decay_length_penalty": null, |
| "suppress_tokens": null, |
| "begin_suppress_tokens": null, |
| "finetuning_task": null, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "tokenizer_class": null, |
| "prefix": null, |
| "pad_token_id": null, |
| "sep_token_id": null, |
| "decoder_start_token_id": null, |
| "task_specific_params": null, |
| "problem_type": null |
| } |
