Hugging Face's logo

tomaarsen
/
jina-clip-implementation-st

Model card Files
xet
 Community

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Jina CLIP

This is a testing repository to experiment with new functionality. Refer to jinaai/jina-clip-implementation for the original model.

The Jina CLIP implementation is hosted in this repository. The model uses:

  • the EVA 02 architecture for the vision tower
  • the Jina BERT with Flash Attention model as a text tower

To use the Jina CLIP model, the following packages are required:

  • torch
  • timm
  • transformers
  • einops
  • xformers to use x-attention
  • flash-attn to use flash attention
  • apex to use fused layer normalization
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support