Model card for vit_base_patch16_224_waifumerge
A Vision Transformer (ViT) image feature model. Trained with Self-Supervised DINO method.
Model Stock merge of vit_base_patch16_224.dino, vit_base_patch16_224.augreg2_in21k_ft_in1k and wd-vit-tagger-v3 just to see what would happen ¯_(ツ)_/¯
- Downloads last month
- 1
Inference API (serverless) does not yet support timm models for this pipeline type.