nebuly-ai / optimate

A collection of libraries to optimise AI model performances
https://www.nebuly.com/
Apache License 2.0
8.37k stars 641 forks source link

Add support for pre-trained reward models #226

Open diegofiori opened 1 year ago

diegofiori commented 1 year ago

Description

OpenAssistant has released on HF the reward models they trained on the open-source datasets. Even if they are not tailored for the user need, we could lavarege them as a starting point for fine-tuning the user reward models.

Available reward models:

TODO

gagan3012 commented 1 year ago

Can I work on this?

PierpaoloSorbellini commented 1 year ago

Please go ahead, let me know if you need any support or if you have any questions. I assigned you to this issue. Thank you! @gagan3012