Please add VIT-G support

openai / CLIP

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

MIT License

26.23k stars 3.35k forks source link

Open ppbrown opened 10 months ago

ppbrown commented 10 months ago

You have VIT-B, VIT-L... but most intersting latest thing is VIT-G. Please add support?