About rope-vit - Githubissues

openai / CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

MIT License

26.1k stars 3.33k forks source link

Open CoinCheung opened 4 months ago

CoinCheung commented 4 months ago

Will future releases include rope-vit? I see in the paper that rope-vit is advantageous to naive vit.