Metin

/

LLaMA-3-8B-Math-Majority-Vote-GRPO

like 2

This PR improves the model card for Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO by:

• Setting the pipeline_tag to text-generation for better discoverability on the Hub.
• Adding library_name: transformers to indicate compatibility with the Hugging Face Transformers library.
• Updating the license to apache-2.0, as found in the associated TTRL project's GitHub repository.
• Adding tr to the language tags, as the model is explicitly trained on Turkish math problems.
• Adding a link to the official Hugging Face paper page: TTRL: Test-Time Reinforcement Learning.
• Adding a direct link to the TTRL GitHub repository: https://github.com/PRIME-RL/TTRL.
• Updating the citation to reflect the TTRL paper.