LiuAlex1109

Extra response with fine-tuned model

2

I trained model with unsloth, and when i input some questions to eval it, the model always output extra contents as shown at below:  my code: ``` from unsloth...

researcher可能会丢失响应

1

```python response_content = result["messages"][-1].content ``` researcher智能体只取了response的最后一条message，但是messages中可能会是[AIMessage, ToolMessage, AIMessage]，这样就只取了部分响应，同时也会丢失ToolMessage的结果

捏造不存在的url

3

在生成报告时，报告中偶尔会出现https://example.com/xxxx这样的链接，有什么办法避免这种情况吗