Image-to-Text
Transformers
English
qwen2_vl

Improve model card for VLM2Vec-V2

#3
by nielsr HF Staff - opened

This PR significantly enhances the model card for VLM2Vec-V2. Key improvements include:

  • Adding pipeline_tag: feature-extraction to correctly categorize the model for embedding generation and improve discoverability on the Hugging Face Hub (e.g., at https://huggingface.co/models?pipeline_tag=feature-extraction).
  • Specifying library_name: transformers to indicate compatibility with the Hugging Face Transformers library, enabling quick-start buttons and streamlined usage.
  • Adding the license: apache-2.0 for clarity on usage permissions.
  • Expanding the model card's content by integrating comprehensive details directly from the project's GitHub repository, including an "About" section, key updates, model details, and benchmark information.
  • Providing practical "Quickstart" code examples for easy integration and usage of the model with the transformers library, covering text, image, and video inputs.

Please review and merge this PR.

Cannot merge
This branch has merge conflicts in the following files:
  • README.md

Sign up or log in to comment