Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Ahmed9275

Vit-Cifar100

Vit-Cifar100 is a ViT image-classification fine-tune from Ahmed9275. According to the model card, it fine-tunes google/vit-base-patch16-224-in21k on Cifar100 with reported 0.8985 accuracy.

Publisher
Ahmed9275
Task
image-classification
Model type
vit
License
apache-2.0
Library
transformers
Publication status
Approved for indexing

Model overview

Vit-Cifar100 is published by Ahmed9275 as a vit image-classification model. The captured configuration identifies ViTForImageClassification with Apache-2.0 licensing. According to the model card, it fine-tunes google/vit-base-patch16-224-in21k on Cifar100 and reports 0.8985 accuracy on the evaluation set.

Recorded capabilities

Cifar100 ViT lineage

According to the model card, this is a fine-tuned version of google/vit-base-patch16-224-in21k on the Cifar100 dataset.

Publisher-reported evaluation

According to the model card, evaluation results are loss 0.4420 and accuracy 0.8985.

Documented training setup

According to the model card, training used learning rate 0.0002, 4 epochs, Adam, linear scheduling, and Native AMP with batch sizes 16 for training and 8 for evaluation.

Use cases in the source record

  • Cifar100 image-classification workflows consistent with the captured image-classification tag and publisher-described Cifar100 fine-tune.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • The captured model card marks intended uses, limitations, and training/evaluation data as requiring more information.
  • No pricing, hardware-requirement, or image-resolution values were extracted.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Ahmed9275/Vit-Cifar100

Captured: Unknown. Processed: 2026-09-07T19:34:28.428408+00:00.

vit-base-beans-demo-v5 This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the Cifar100 dataset. It achieves the following results on the evaluation set: Loss: 0.4420 Accuracy: 0.8985 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: 0.0002 train_batch_size: 16 eval_batch_size: 8 seed: 42 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 lr_scheduler_type: linear num_epochs: 4 mixed_precision_t…

F001F002F003F004F005F006F008F009F010F011F012