PersonalAILab

/

Personalized-Qwen2.5-7B-Instruct

like 0

Follow

OPPO-Personal-AI-Lab 74

This PR adds a comprehensive model card for the Personalized-Qwen2.5-7B-Instruct model, based on the paper Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning.

The updates include:

• Adding license: apache-2.0
• Adding library_name: transformers to ensure proper integration and enable the "how to use" widget.
• Adding pipeline_tag: text-generation to categorize the model on the Hugging Face Hub.
• Including a direct link to the paper and the GitHub repository in the model card content.
• Incorporating the paper abstract and a project overview for detailed context.
• Providing a BibTeX citation.

Please review and merge this PR.