ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)
Why it's on BrighterTube
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceExplains ORPO preference optimization without reference models from paper. Technical analysis of model alignment and training method.
What you'll learn
A 33-minute video from Yannic Kilcher: “ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)”.
Video by Yannic Kilcher, played through YouTube's embedded player.
Part of Generative Models, Papers Explained