Improve model card for Variational-Reasoning-4B-Acc

#1
by nielsr HF Staff - opened

This PR significantly enhances the model card for Variational-Reasoning-4B-Acc by populating the generic sections with detailed information from the paper and GitHub repository.

Key additions include:

  • Updated metadata with pipeline_tag: text-generation, license: apache-20, base_model: Qwen3-4B-Base, and relevant tags (qwen3, reasoning, variational-inference).
  • A comprehensive model description derived from the paper abstract.
  • Direct links to the official paper on Hugging Face and the GitHub repository.
  • Information about the model's development, type, language, and finetuning origin.
  • Summaries of the training and evaluation procedures, directing users to the GitHub repository for full details.
  • The BibTeX citation for the paper.

These updates aim to provide users with a clearer understanding of the model, its capabilities, and how to get started, while also improving its discoverability on the Hugging Face Hub.

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

Sign up or log in to comment