TMLR-Group-HF

/

GT-Llama-3.2-3B-Instruct-MATH

like 0

Follow

TMLR Group 20

This PR significantly enhances the model card for TMLR-Group-HF/GT-Llama-3.2-3B-Instruct by:

• Adding library_name: transformers to enable the automated "How to use" widget, as evidenced by the model's config.json indicating LlamaForCausalLM and transformers_version.
• Adding pipeline_tag: text-generation to improve discoverability, given the model's focus on eliciting reasoning in LLMs.
• Including a direct link to the associated paper: Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.
• Updating the GitHub repository link to the more accurate https://github.com/tmlr-group/Co-rewarding.
• Expanding the model description with details from the paper abstract and GitHub README for better context.
• Updating the citation block to match the BibTeX from the GitHub repository.

These changes provide more comprehensive and accurate information, making the model more accessible and user-friendly for the community.