Agent Skills: unsloth-orpo
One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization, alignment, ORPOTrainer, log_odds_ratio, binary preference).
UncategorizedID: cuba6112/skillfactory/unsloth-orpo
Install this agent skill to your local
Skill Files
Browse the full folder contents for unsloth-orpo.
Loading file tree…
Select a file to preview its contents.