husj576

/

GRIFFIN-llama2-chat-7B

like 0

This PR significantly improves the model card for GRIFFIN by:

• Adding pipeline_tag: text-generation to ensure visibility for text generation models on the Hub.
• Adding library_name: transformers to indicate compatibility with the Transformers library, which enables the automated "how to use" widget. This is supported by the config.json and the GitHub README's explicit mention of eagenerate functioning "just like using 'generate' from Hugging Face".
• Including a direct link to the paper: GRIFFIN: Effective Token Alignment for Faster Speculative Decoding.
• Adding a link to the GitHub repository: https://github.com/hsj576/GRIFFIN.
• Providing a sample usage code snippet directly from the GitHub README for easy inference demonstrations.

Please review and merge this PR if it looks good.