zhixiangwei

/

vlm150m-hqclip-large-vitb16

like 0

This PR enhances the model card for HQ-CLIP by:

• Adding the pipeline_tag: zero-shot-image-classification to improve discoverability on the Hugging Face Hub.
• Specifying library_name: transformers as the model is compatible with the 🤗 Transformers library.
• Including relevant tags such as clip and image-retrieval for better categorization.
• Adding a clear link to the paper HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models.
• Adding a link to the project page (https://zxwei.site/hqclip/) and the GitHub repository (https://github.com/zhixiangwei/HQ-CLIP).
• Providing a minimal sample usage snippet for zero-shot image classification to help users get started quickly.

These changes ensure more information is readily available, enabling users to better understand, find, and utilize the model.