ORPO: Monolithic Preference Optimization without Reference Model Paper • 2403.07691 • Published Mar 12, 2024 • 64
Zephyr ORPO Collection Models and datasets to align LLMs with Odds Ratio Preference Optimisation (ORPO). Recipes here: https://github.com/huggingface/alignment-handbook • 3 items • Updated Apr 12, 2024 • 17
InstantID: Zero-shot Identity-Preserving Generation in Seconds Paper • 2401.07519 • Published Jan 15, 2024 • 55