09 Mar 23copy & paste+upvote-downvoteFine tune a 20B Language Model with RLHF using a 24GB consumer GPU? π€―
It is now possible using TRL + PEFT!
Check ou⦠https://t.co/P4R4b79P1g
β@_lexiemichelee: @MariaCabayubi you know how slow I am Maria. But it looks really goodβhah I know this. But thank youuu
14 Jan 13copy & paste+upvote-downvoteβ@_lexiemichelee: @MariaCabayubi you know how slow I am Maria. But it looks really goodππππβhah I know this. But thank youuu βΊπππ