回答不完整

[lilongwei5054]

Is there an existing issue for this?

• [X] I have searched the existing issues

Current Behavior

当回答较长时，很容易出现回答不完整就结束了，或者回答的字数没有达到要求。 比如 问"写一篇2000字的短篇小说"，会出现以下两种bug: 1.能写完，但是字数只有不到1000字。 2.写一半终止了，可以明显看到最后一句话没有写完整。

Expected Behavior

No response

Steps To Reproduce

---

Environment

- OS:Ubuntu 20
- Python:3.9
- Transformers:4.30.2
- PyTorch:2.0.1
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :

Anything else?

No response