sunblaze-ucb

/

Qwen3-14B-Intuitor-MATH-1EPOCH

like 0

Follow

sunblaze-ucb 25

This PR improves the model card for Qwen3-14B-Intuitor-MATH-1EPOCH by:

• Adding the library_name: transformers tag to the metadata, which enables the interactive "How to use" widget on the Hugging Face Hub.
• Including a direct link to the associated research paper (Learning to Reason without External Rewards) and the GitHub repository (https://github.com/sunblaze-ucb/Intuitor) for easy access to source materials.
• Enhancing the model description with details from the paper's abstract about the "Intuitor" method and "Reinforcement Learning from Internal Feedback (RLIF)".
• Providing a clear sample usage code snippet to help users quickly get started with the model using the transformers library.

Please review and merge this PR if everything looks good.