xingyuHuxingyu

/

DynamicPO

like 0

Hi! I'm Niels, part of the community science team at Hugging Face.

This PR adds a model card for the DynamicPO model, based on the paper DynamicPO: Dynamic Preference Optimization for Recommendation.

The PR includes:

• Relevant metadata (pipeline tag, library name, and base models).
• A summary of the project and its key mechanisms (Dynamic Boundary Negative Selection and Dual-Margin Dynamic beta Adjustment).
• Links to the research paper and the official GitHub repository.
• Citation information.