PyTorch
llama
alignment-handbook
Generated from Trainer

Improve model card: Add metadata, links, and detailed sections

#1
by nielsr HF Staff - opened

This PR significantly enhances the model card for JunxiongWang/Mamba2InLlama_0_875 by:

  • Adding the pipeline_tag: text-generation and library_name: transformers to the metadata, improving discoverability on the Hugging Face Hub and enabling the "Use in Transformers" widget.
  • Specifying the license: apache-2.0.
  • Including mamba and distillation as relevant tags.
  • Clearly linking to the paper (arxiv.org/abs/2408.15237), the new primary code repository (https://github.com/jxiw/M1), and the project page (https://openreview.net/forum?id=uAzhODjALU) at the top of the model card content.
  • Expanding the "Model description" and "Intended uses & limitations" sections with details from the paper abstract and GitHub README.
  • Integrating detailed "Usage" instructions, including environment setup and code examples, from the original GitHub repository, adapting the Mamba2 example for this specific model.
  • Removing auto-generated boilerplate comments and streamlining the overall structure for better readability.

Please review and merge if it looks good.

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment