moonshotai

/

Kimi-Linear-48B-A3B-Base

like 42

Follow

Moonshot AI 3.38k

This PR enhances the model card for the Kimi Linear model by:

• Adding pipeline_tag: text-generation to improve discoverability on the Hugging Face Hub.
• Adding library_name: transformers to enable the automated "How to use" widget, as the model is compatible with the Hugging Face Transformers library (evidenced by the code snippet and config.json).
• Adding a clear top-level title: # Kimi Linear: An Expressive, Efficient Attention Architecture.
• Updating links to the paper to point to the canonical Hugging Face paper page: Kimi Linear: An Expressive, Efficient Attention Architecture. This includes the banner image and the "Tech Report" badge.
• Adding an explicit link and badge for the GitHub repository: https://github.com/MoonshotAI/Kimi-Linear.
• Converting relative image paths (e.g., figures/banner.png) to absolute URLs on the Hugging Face Hub for better reliability.
• Updating the BibTeX citation to the more complete version provided in the GitHub repository's README.

These improvements aim to make the model card more comprehensive, discoverable, and user-friendly for the community.