{ "_name_or_path": "/apdcephfs_qy3/share_301372554/share_info/qianggao/llama3/output/04-24-2024_10:00:07_llama3_pretrain_wudao_24gpu___bs__maxlen_1024_pad_right_lr_2e-4_format_wudao", "architectures": [ "LlamaForCausalLM" ], "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": 32, "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": "4.40.0", "use_cache": false, "vocab_size": 128256 }