Instructions to use 1999xia/ViT_Fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use 1999xia/ViT_Fast with timm:
import timm model = timm.create_model("hf_hub:1999xia/ViT_Fast", pretrained=True) - Notebooks
- Google Colab
- Kaggle
| # Model Weights | |
| Checkpoints are available on Hugging Face: https://huggingface.co/YOUR_USERNAME/ViT_Fast | |
| ## Checkpoint Structure | |
| - cifar100_vit_b16_ft/best_model.pth β CIFAR-100 Baseline (91.69%) | |
| - oxford_pets_vit_b16_ft/best_model.pth β Oxford Pets Baseline (93.32%) | |
| - food101_vit_b16_ft/best_model.pth β Food-101 Baseline (91.37%) | |
| - cifar100_mae_patchsel_b16_keep75_distill/best_model.pth β MAE+Router 75% CIFAR (91.10%) | |
| - cifar100_vit_b16_img168/best_model.pth β Downsample 168x168 CIFAR (91.56%) | |
| - oxford_pets_vit_b16_img168/best_model.pth β Downsample 168x168 Oxford (90.65%) | |
| - router_distill_cifar100/router.pth β Distilled Router CIFAR | |
| - router_distill_food101/router.pth β Distilled Router Food-101 | |
| ## Download | |
| See Hugging Face repo for download links. | |