| { | |
| "_name_or_path": "/fs/fast/share/chenyushuo/llama-65b-v3-step25500-neox-v18_4/", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 22016, | |
| "max_position_embeddings": 2048, | |
| "model_type": "llama", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 80, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.28.1", | |
| "use_cache": true, | |
| "vocab_size": 51192 | |
| } | |