tanganke

clip-vit-base-patch32_oxford-iiit-pet

tanganke/clip-vit-base-patch32_oxford-iiit-pet

clip-vit-base-patch32_oxford-iiit-pet is a feature extraction model from tanganke. Use it when you need embeddings to search or compare text. It is set up for transformers.

Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batchsize=128). Only the vision encoder is fine-tuned.