vit-base-patch16-224-in21k-finetuned-cifar10

Model overview

vit-base-patch16-224-in21k-finetuned-cifar10 is published by aaraki as a vit image-classification model. The captured configuration identifies ViTForImageClassification with model type vit, and card data records an apache-2.0 license. According to the model card, it fine-tunes google/vit-base-patch16-224-in21k on cifar10.

Recorded capabilities

Use cases in the source record

• Ten-class CIFAR-10 image classification work using the publisher-reported 0.9788-accuracy fine-tune.
• Transformers-based classifier experimentation following the publisher's documented hyperparameters and training setup.

Limitations and unknowns

• No Ethen-measured evaluation results were extracted from this record.
• No parameter count was extracted.
• Provider state is historical snapshot data and should be refreshed before being presented as current.
• Accuracy, data, and training claims are publisher model-card statements and were not independently verified by Ethen.

Source and provenance

Source: aaraki/vit-base-patch16-224-in21k-finetuned-cifar10

Captured: Unknown. Processed: 2026-09-07T19:34:39.095902+00:00.

vit-base-patch16-224-in21k-finetuned-cifar10 This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the cifar10 dataset. It achieves the following results on the evaluation set: Loss: 0.2564 Accuracy: 0.9788 Model description More information needed Intended uses & limitations More information needed Training and evaluation data More information needed Training procedure Training hyperparameters The following hyperparameters were used during training: learning_rate: 5e-05 train_batch_size: 32 eval_batch_size: 32 seed: 42 gradient_accumulation_steps: 4 total_train_batch_size: 128 optimizer: Adam with betas=(0.9,0.…