Skip to content

[DPO] add reference log-prob outputs in DPO#521

Open
kashif wants to merge 6 commits intolinkedin:mainfrom kashif:dpo-fix
+9-3

Commits

Commits on Jan 14, 2025

Commits on Jan 15, 2025

Commits on Jan 21, 2025

Commits on Jan 22, 2025