CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Repository Index
103,113 visible repositories in the index
1–4 of 4 · Most stars
Easily compute clip embeddings and build a clip retrieval system with them
- semantic-search
- deep-learning
- multimodal
- ai
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.