HJYao

Results 6 comments of HJYao

I encountered the same issue. When I tried to use the code from a few months ago, no error occurred. After checking the current version, I found that the new...

@wuxibin89 May I ask whether VeRL supports training with mixed batches that contain both tool-use samples and non-tool samples?

> I am currently using verl for multi-turn interaction RL training and have identified two potential issues. > > * There might be a problem with the usage of _req.add_assistant_message...