THU-KEG

/

WildReward-8B

like 3

Follow

Knowledge Engineer Group @ Tsinghua University 110

Hi! I'm Niels from the Hugging Face community team.

This pull request improves the model card for WildReward-8B by:

• Linking the research paper WildReward: Learning Reward Models from In-the-Wild Human Interactions via the arxiv metadata field.
• Adding the pipeline_tag: text-classification for better model discovery.
• Fixing the placeholder GitHub repository link in the footer.
• Adding the BibTeX citation to help researchers cite your work.
• Listing the associated WildFB dataset in the metadata.

These changes help users find the relevant research context and code implementation more easily.