StarrySeas

### Required prerequisites - [X] I have read the documentation . - [X] I have searched the [Issue Tracker](https://github.com/baichuan-inc/baichuan-7B/issues) and [Discussions](https://github.com/baichuan-inc/baichuan-7B/discussions) that this hasn't already been reported. (+1 or comment...

Has anyone compared this training framework to TRL?

1

TRL PPO implementation is simpler than this, and takes up less memory. This framework has an additional value contribution network. I don't know which framework is more stable and effective.

联系邮箱: [email protected]

[Proposal] Add support for Baichuan1 and Baichuan2

3

### Hello, does this analysis tool support Baichuan1 and Baichuan2? Hello, I want to use this tool to analyze the Baichuan1 and Baichuan2 models. I don’t know if it is...