jusjinuk

/

Llama-3.2-3B-Instruct-3bit-GuidedQuant-QTIP

like 0

This PR significantly enhances the model card for the GuidedQuant model by:

• Adding pipeline_tag: text-generation to ensure the model is properly categorized and discoverable for its primary task.
• Adding library_name: transformers as the model is compatible with the Hugging Face Transformers library, enabling the "Use in Transformers" button and code snippet on the Hub.
• Including a prominent link to the dedicated project page (https://jusjinuk.me/blog/guidedquant/) for more context and resources.
• Expanding the "Usage" section with a clear, runnable Python code example directly from the project's GitHub, demonstrating quick inference and improving user experience.
• Integrating the paper's abstract, detailed model information, full citation, and acknowledgements for comprehensive documentation.

These improvements will make the model card more informative and user-friendly.