Skip to content

Align KTO with DPO: Remove enforcement of causal language models#5701

Merged
albertvillanova merged 1 commit into
mainfrom
align-kto-dpo-rm-encoder-decoder
May 5, 2026
Merged

Align KTO with DPO: Remove enforcement of causal language models#5701
albertvillanova merged 1 commit into
mainfrom
align-kto-dpo-rm-encoder-decoder