| { | |
| "_name_or_path": "meta-llama/Llama-2-7b-chat-hf", | |
| "architectures": [ | |
| "LlamaForSpeculativeCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoModelForSpeculativeCausalLM": "modeling_speculative_llama.LlamaForSpeculativeCausalLM" | |
| }, | |
| "beagle_add_noise": false, | |
| "beagle_attention_offset": "random.randrange(10)", | |
| "beagle_attention_wind": "2", | |
| "beagle_ckpt_path": null, | |
| "beagle_debug": false, | |
| "beagle_decoder_key_remap": {}, | |
| "beagle_dtype": "torch.bfloat16", | |
| "beagle_frozen_targets": [], | |
| "beagle_git_diff": "", | |
| "beagle_git_sha1": "unknown", | |
| "beagle_layer_path": "model.layers", | |
| "beagle_lmhead_path": "lm_head", | |
| "beagle_model_path": "beagle/models/llama2", | |
| "beagle_norm_path": "model.norm", | |
| "beagle_output_dir": "output", | |
| "beagle_reuse_layer": -1, | |
| "beagle_rotary_path": "model.rotary_emb", | |
| "beagle_run_name": "temp_run", | |
| "beagle_seed": 42, | |
| "beagle_tokenizer_path": "meta-llama/Llama-2-7b-chat-hf", | |
| "beagle_use_fc_eagle": false, | |
| "beagle_use_lower_layers": 1, | |
| "beagle_use_state_distill": false, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "speculative_base_model": "meta-llama/Llama-2-7b-chat-hf", | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.47.1", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |