zhangsanfeng86

when Train the reward model, Get error

1

when Train the reward model, Get error:

推理速度比原版的llama要慢一些

1

@ydli-ai 感谢分享！ 请问一下：为什么推理速度比原版的llama要慢一些？

https://user-images.githubusercontent.com/73547638/236982071-90d06bf8-ef5d-4980-81e3-c4a9053ef94e.mp4

Hi @erasromani , Thank you for release code ! Could you show which version of isaac-sim? it can't run with the latest version isaac-sim.

LeakSanitizer: detected memory leaks

12

Please make sure that this is a bug. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:bug_template **System information**...