Yulianghua

lianghua's activity

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

upvoted an article about 2 months ago

view article

Article

DualPipe Explained: A Comprehensive Guide to DualPipe That Anyone Can Understand—Even Without a Distributed Training Background

By •

Feb 28

• 8

upvoted an article 4 months ago

view article

Article

Open R1: Update #3

By and 9 others •

Mar 11

• 293

upvoted a collection about 1 year 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, 2024 • 17