rzzhan

/

ExGRPO-Llama3.1-8B-Instruct

like 0

This PR significantly improves the model card for the ExGRPO-Llama3.1-8B-Zero model by:

• Adding pipeline_tag: text-generation to ensure proper discoverability and categorization on the Hugging Face Hub.
• Including library_name: transformers to enable the automated "How to use" widget, as evidenced by the config.json file (LlamaForCausalLM architecture and transformers_version).
• Providing a descriptive introduction based on the paper abstract and the GitHub repository's README.md.
• Linking directly to the associated paper: ExGRPO: Learning to Reason from Experience.
• Adding a link to the official GitHub repository (https://github.com/ElliottYan/LUFFY/tree/main/ExGRPO) for the project code.
• Incorporating the visual overview image, key highlights, and direct installation instructions from the GitHub README.md to help users get started.
• Including the "Released Models" table and citation information from the GitHub README.md.

These enhancements will make the model's documentation more comprehensive, improve its discoverability, and facilitate easier adoption by the community.