TMLR-Group-HF

/

Entropy-Llama-3.2-3B-Instruct-MATH

like 0

Follow

TMLR Group 20

This PR improves the model card for TMLR-Group-HF/Entropy-Llama-3.2-3B-Instruct by:

• Adding library_name: transformers to enable the automated "How to use" widget, based on config.json indicating llama model type and transformers_version.
• Adding pipeline_tag: text-generation for better discoverability on the Hugging Face Hub.
• Integrating the paper link to Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models into the model description.
• Correcting the GitHub repository link in the content from https://github.com/tmlr-group/Co-Reward to https://github.com/tmlr-group/Co-rewarding and updating the project name to "Co-rewarding" for consistency.
• Expanding the model description with key information from the paper's abstract to provide more context.
• Correcting the title within the BibTeX citation to match the official paper title.
• No sample usage code snippet has been added as there was no explicit inference code for this specific model found in the official GitHub repository, adhering to the guidelines.

Please review and merge if these updates are accurate and beneficial.