{ "_name_or_path": "/media/chenzhipeng/yulan/ckpt/yulan_3_base/yulan_stage_final_4_global_step31000/", "architectures": [ "LlamaForCausalLM" ], "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4864, "initializer_range": 0.02, "intermediate_size": 13056, "max_position_embeddings": 4096, "model_type": "llama", "num_attention_heads": 38, "num_hidden_layers": 40, "pad_token_id": 0, "rms_norm_eps": 1e-06, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.29.0", "use_cache": true, "vocab_size": 51190 }