ChatGLM2-6B
ChatGLM2-6B copied to clipboard
[BUG/Help] <回答到一半就开始重复输出某个字符>
Is there an existing issue for this?
- [X] I have searched the existing issues
Current Behavior
如图所示
Expected Behavior
No response
Steps To Reproduce
在windows系统,gpu启动
Environment
- OS: wins
- Python: 3.8
- Transformers:
- PyTorch:
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :
Anything else?
No response
+ 1
这个是原模型还是你微调后的模型?
在进行ChatGLM-Efficient-Tuning微调后遇到了同样的问题
我微调后也碰到了这个问题,不过我微调后的模型是一直重复一句话,不知道是什么原因