Improve model card for LexSemBridge: Add paper/code links, update pipeline tag, license, and datasets

#1
by nielsr HF Staff - opened

This PR enhances the model card for LexSemBridge by:

  • Updating the pipeline_tag to feature-extraction, which more accurately reflects the model's primary function of generating dense representations for retrieval tasks. This ensures better discoverability on the Hugging Face Hub (e.g., https://huggingface.co/models?pipeline_tag=feature-extraction).
  • Adding Jasaxion/LexSemBridge_eval to the datasets metadata, as this dataset is explicitly mentioned in the GitHub README for training and evaluation.
  • Adding en to the language metadata.
  • Including license: apache-2.0 to provide clear licensing information for the model.
  • Adding lexsembridge to the tags metadata for improved searchability.
  • Adding a direct link to the paper LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation.
  • Including a link to the official GitHub repository, https://github.com/Jasaxion/LexSemBridge/, for easy access to the code.
  • Updating the sample usage snippet to refer to a specific model ID (Jasaxion/LexSemBridge_CLR_snowflake) mentioned in the project's GitHub README.
  • Populating the BibTeX citation section for proper attribution.

These improvements will make the model more discoverable and provide users with comprehensive information and resources.

I sincerely apologize for being occupied with other work recently and overlooking your PR. I truly appreciate your thoughtful suggestions.

Jasaxion changed pull request status to merged

Sign up or log in to comment