| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "eagle_aux_hidden_state_layer_ids": [ | |
| 1, | |
| 17, | |
| 29, | |
| 47, | |
| 58 | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 5376, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 21504, | |
| "max_position_embeddings": 262144, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 1, | |
| "num_key_value_heads": 16, | |
| "pad_token_id": null, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "use_cache": true, | |
| "vocab_size": 262144, | |
| "draft_vocab_size": 32000, | |
| "ptd_token_id": 4, | |
| "dtype": "bfloat16", | |
| "transformers_version": "5.6.2" | |
| } |