QiyuanChen

可以尝试把`baseurl`替换为`https://api.openai-proxy.com/v1`，key直接用原始的就行

请问是如何启动的？是否是使用DiskStation Manager？

I have also encountered a similar issue. I tried re-forking the repository, but still couldn't get it to compile.

> Perhaps you could try to remove the line 4 in about.md: excerpt : "" It works! thx

In most cases, DPO will only train one epoch, and more epochs will cause a performance crash. At the same time, smaller learning rates generally lead to better results, and...

> Hi all, > > short update, unfortunately, I got sick, hence again a delay. Should I still work on it? I think it should continue. Are you still working...

> Yes, still working on it @qychen2001! That's great! This feature is really important, looking forward to your PR.

> Sorry but I have almost completed this feature by myself in #375 (as MacOS seemed to be sick) and am just waiting for @weihua916 's review. However, the styling...

这是很明显的reward hacking，因为rejected和chosen的数据太容易分辨了，模型很容易拟合到一些外部特征上面，建议使用质量接近的问答对

> 我用 vite 快速启动了一个项目，并没有复现🤔 > > 我又尝试了一下，还是可以复现的。我只是把官网的demo复制到App.tsx中，可以出现这个问题。