EntityNet
Collection
The models of our publication: Using Knowledge Graphs to harvest datasets for efficient CLIP model training • 7 items • Updated
A CLIP (Contrastive Language-Image Pre-training) model trained from scratch on EntityNet-33M.
See the project page for the paper, code, usage examples, metrics, etc.
The model has seen ~0.6B images at a batch size of 8k.
- Downloads last month
- 28
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:lmb-freiburg/CLIP-ViT-B-32-EntityNet-33M') tokenizer = open_clip.get_tokenizer('hf-hub:lmb-freiburg/CLIP-ViT-B-32-EntityNet-33M')