Yulianghua

lianghua's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a collection 2 months ago

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 • 15