---
license: mit
language:
- en
library_name: open_clip
---

A CLIP (Contrastive Language-Image Pre-training) model trained from scratch on EntityNet-33M.

See the [project page](https://github.com/lmb-freiburg/entitynet) for the paper, code, usage examples, metrics, etc.

The model has seen ~0.6B images at a batch size of 8k.