유형
Checkpoint
게시 날짜
2023-06-30
기본 모델
Other
버전 소개
"RMHF" method allowes me to interpolate dozen of models at a time.
This model is a mix of:
(The algorithm is basically like generating potential new merging ratio vector, and show user image comparison and let user choose better one. I named it "Reinforcement Merging with Human Feedback)
