| { | |
| "_name_or_path": "/data/.hf_cache/transformers/hub/models--togethercomputer--llama3-4-layer-speculator-mixture-v1-dolama-cc-100B-tokens/snapshots/66baaac0814c7a0688426cbb536b7b1267927cb5", | |
| "architectures": [ | |
| "GlideLlamaDraftModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128001, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 4, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.0.dev0", | |
| "use_cache": false, | |
| "vocab_size": 128256 | |
| } | |