SparseLLM

/

BlockFFN-3B-SFT

like 1

Follow

SparseLLMs 59

This PR significantly improves the model card for BlockFFN-3B-SFT by:

• Adding library_name: transformers to the metadata, which enables the "How to use" widget and ensures proper categorization on the Hub.
• Adding the moe tag, as the model is based on a Mixture-of-Experts architecture, enhancing discoverability.
• Expanding the model description with a concise summary from the paper's abstract, providing more context to users.
• Including a runnable Python code snippet for AutoTokenizer and AutoModelForCausalLM, making it easier for users to get started with the model.
• Adding a link to the associated Hugging Face Models Collection (SparseLLM) for better project navigation.
  The original Arxiv paper link has been retained as per guidance.