Improve model card: Add pipeline tag, license, and comprehensive details

#3
by nielsr HF Staff - opened

This PR significantly enhances the model card for fisheye8k_jozhang97_deta-swin-large-o365 by:

  • Adding the pipeline_tag: object-detection to the metadata, which ensures the model appears in relevant searches on the Hugging Face Hub (e.g., https://huggingface.co/models?pipeline_tag=object-detection).
  • Adding the explicit license: mit as stated in the project's GitHub repository.
  • Including more descriptive tags like deta, swin, traffic, automotive, ITS, and computer-vision.
  • Providing direct links to the associated paper (Mcity Data Engine: Iterative Model Improvement Through Open-Vocabulary Data Selection), the project's documentation (Mcity Data Engine Docs), and the GitHub repository (mcity/mcity_data_engine).
  • Expanding the "Model description" and "Intended uses & limitations" sections with details from the paper's abstract and the GitHub README.
  • Clarifying the "Training and evaluation data" section with a direct link to the dataset on the Hub.
  • Adding a practical Python code snippet for inference using the transformers library, making the model easier to use.

These updates greatly improve the model's documentation, usability, and discoverability on the Hugging Face Hub.

danielbogdoll changed pull request status to merged

Sign up or log in to comment