rl-research

/

DR-Tulu-8B

like 62

Follow

RL ReSearch 43

This PR enhances the model card for DR Tulu-8B by:

• Adding pipeline_tag: text-generation to improve discoverability on the Hugging Face Hub, as it's a deep research agent model.
• Adding library_name: transformers as the model's configuration (config.json) indicates compatibility with Qwen3ForCausalLM, enabling the automated "how to use" widget.
• Updating all paper links to point to the official Hugging Face paper page: DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research.
• Adding prominent links to the Project Page (https://dr-tulu.github.io/) and Code (https://github.com/rlresearch/dr-tulu) for easier access.
• Including a "Quick Start: Playing with DR Tulu Interactively" section with a code snippet directly from the GitHub README, providing practical usage instructions for the model within its dedicated dr-agent-lib framework.
• Updating the BibTeX citation to the more complete @misc format found in the GitHub README.

These changes aim to make the model card more informative and user-friendly.