Shadows

Results 2 comments of Shadows

我在使用该项目调用自己微调的大模型接口时,输出的token被限制在了100,请问 我应该如何修改。

> > Thank you [@LWShowTime](https://github.com/LWShowTime) . Setting `gradient_accumulation_steps: 1` does not solve the OOM. > > Maybe you can add some information of your gpu devices. For GRPOTrainer, I can...