{ "_name_or_path": "/apdcephfs/share_300000800/user/ruotianma/jiaqi/output/saved_models/03071_8GPUs_Critic_AdjustStep_ConvertStyle_Qwen2.5-7B-Instruct_Data_Qwen_250303_sft_critique_helpful9351_sneaky12415_from_GPTRewrite02281/checkpoint-1020", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128245, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 131072, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.39.3", "use_cache": false, "use_sliding_window": false, "vocab_size": 151665 }