JunxiongWang

/

Llama3.2-Mamba2-3B-distill

like 0

This PR significantly enhances the model card by:

• Adding pipeline_tag: text-generation to improve discoverability on the Hugging Face Hub (e.g., at https://huggingface.co/models?pipeline_tag=text-generation).
• Including library_name: transformers to correctly associate the model with its primary inference library and enable the "how to use" button.
• Providing a direct link to the official Hugging Face paper page: The Mamba in the Llama: Distilling and Accelerating Hybrid Models.
• Adding a prominent link to the official GitHub repository for the code and more detailed usage instructions: https://github.com/jxiw/MambaInLlama.

These additions make the model more discoverable, easier to use, and provide better context for researchers.