Improve model card for Qwen-32B-CyberSearcher with paper, code, description, and metadata

#1
by nielsr HF Staff - opened

This PR significantly enhances the model card for Qwen-32B-CyberSearcher by:

  • Linking it to the paper SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis.
  • Adding a direct link to the GitHub repository: https://github.com/RUCAIBox/SimpleDeepSearcher.
  • Adding the pipeline_tag: text-generation and license: mit to the metadata, ensuring better discoverability and clarity.
  • Adding relevant tags like deep-search, retrieval-augmented-generation, web-agent, and qwen.
  • Replacing placeholder content with a comprehensive model description, key contributions, framework overview, and performance highlights from the paper and GitHub README, including illustrative images.
  • Populating sections like "Intended uses & limitations" and "Training and evaluation data".
  • Including citation and contact information.
  • Removing the automatically generated boilerplate comment.

Note: A sample usage code snippet has not been added, as the provided GitHub README does not contain a direct inference example for this model that aligns with the transformers library, and making up code is explicitly disallowed.

Please review and merge this PR if everything looks good.

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment