[BUG] Qwen1.5-14B回答不会停止，会自动进行对话，或者出现重复回答

[Parasolation]

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• [X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

采用本库给的cli_demo.py或者web_demo.py启动都会遇到该问题

期望行为 | Expected Behavior

希望能得到正确回答，如上图只需要回答“你好！有什么我可以帮助你的吗？”以及重复的只回答一遍

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:Ubuntu22.04
- Python:3.10
- Transformers:4.39.1
- PyTorch:2.21
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):12.1

备注 | Anything else?

No response

[Parasolation]

还会有这样的提示： The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results. Setting pad_token_id to eos_token_id:151643 for open-end generation.

[jklj077]

Please try using the code from QwenLM/Qwen1.5 (the current repo).

[zhenfenxiao]

Please try using the code from QwenLM/Qwen1.5 (the current repo).

I met the same question using code from QwenLM/Qwen1.5.

[wrl1224]

遇到了同样的问题

[JustinLin610]

I suspect that you are using base model instead of chat model? Use Qwen1.5-14B-Chat and follow the example code

[Riel1998]

我也遇到同样的问题，但是切换到chat版本就没有问题。。。

[jklj077]

Opt for chat models instead, as base models lack the chat template functionality. Their primary application revolves around text completion leveraging in-context learning.