### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior  ### Expected Behavior _No response_ ### Steps To Reproduce 使用AutoTokenizer、AutoModel加载微调好的多轮对话checkpoint,使用stream_chat预测 ### Environment ```markdown - OS: - Python: - Transformers: - PyTorch: - CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) : ``` ### Anything else? _No response_