RabotniKuma

/

Fast-Math-R1-14B

like 3

This PR improves the model card by:

• Adding pipeline_tag: text-generation to help users discover this model for text generation tasks.
• Adding library_name: transformers to indicate compatibility with the 🤗 Transformers library.
• Updating the paper link to the Hugging Face paper page: A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning.
• Adding comprehensive metadata including tags, datasets, language, and metrics for better discoverability.
• Incorporating detailed training and technical information from the GitHub repository, and ensuring consistent Markdown heading levels.