Add model card, metadata, and usage examples

#1
by nielsr HF Staff - opened

This PR adds a comprehensive model card for the JetSpec speculative decoding draft model.

It includes:

  • Metadata tags (pipeline_tag: text-generation, library_name: transformers, and license: apache-2.0).
  • Links to the JetSpec Paper and the GitHub repository.
  • A brief introduction to the parallel tree drafting method.
  • Example code snippets demonstrating usage with both the Hugging Face reference and the optimized inference engine.
  • Citation details.
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment