roylvzn
/

vit-cifar10

Image Classification

Eval Results (legacy)

Model card Files Files and versions

ViT Base (patch16, 224) fine-tuned on CIFAR-10

Trained on CIFAR-10 (10 classes). Weights saved as a plain PyTorch state_dict (pytorch_model.bin). Architecture is defined in vit_model.py (uses timm).

Downloads last month: 4

Dataset used to train roylvzn/vit-cifar10

Space using roylvzn/vit-cifar10 1

Evaluation results

accuracy on CIFAR-10
self-reported

0.950