StonyBrookNLP

/

StarCoder2-LPO

like 0

Follow

LUNR lab at Stony Brook University 15

This PR enhances the model card for StarCoder2-LPO by:

• Adding the pipeline_tag: text-generation to the metadata, which improves discoverability on the Hugging Face Hub for code generation tasks.
• Specifying the license: apache-2.0, aligning with the base model and common practice.
• Updating the primary paper link to the Hugging Face Papers page: Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences.
• Adding a direct link to the associated GitHub repository for easier access to the code and further usage instructions.
• Including the paper's abstract to provide immediate context about the model's research.
• Adding a "Sample Usage" section that outlines how to perform inference using the inference.py script from the GitHub repository, providing clear, actionable steps as found in the original source.
• Including the BibTeX citation for proper academic attribution.

These changes will significantly improve the model's discoverability, usability, and information completeness for researchers and developers.