RLinf

/

RLinf-math-1.5B

like 1

Follow

RLinf 59

This PR improves the model card for RLinf-math-1.5B by:

• Refining the pipeline_tag: Changed from reinforcement-learning to text-generation to accurately reflect the model's primary function of generating text for mathematical reasoning tasks.
• Adding library_name: Included transformers to enable the automated "Use in Transformers" widget, as evidenced by the provided sample usage.
• Updating tags: Added reinforcement-learning to the tags list to ensure discoverability based on the model's training methodology, complementing the RLinf tag.
• Adding Paper Link: Included a direct link to the associated paper, RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training, at the top of the card.
• Adding Citation Section: Appended the "Citation and Acknowledgement" section from the GitHub README for proper attribution and academic visibility.

These changes will enhance the model's discoverability and provide clearer, more comprehensive information for users.