Overview

This skill adds structured evaluation results to HuggingFace model repositories using the .eval_results/ format.

What This Enables:

• Results appear on model pages with benchmark links
• Scores are aggregated into benchmark dataset leaderboards
• Community contributions via Pull Requests

Important

Evaluation PRs can only be opened on the Hugging Face Hub. They cannot be opened on the GitHub repository.

Version

3.0.0

Workflow Overview