trl icon indicating copy to clipboard operation
trl copied to clipboard
verified publisher icon huggingface

[WIP] RL tweaks for stability & learning

Open natolambert opened this issue 2 years ago • 1 comments

Will share results, but experiments for #101 #122 #121

natolambert avatar Jan 30 '23 19:01 natolambert

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint.

HuggingFaceDocBuilderDev avatar Jan 30 '23 19:01 HuggingFaceDocBuilderDev