ViT base fine-tune
According to the model card, the model is a fine-tuned version of google/vit-base-patch16-224-in21k on imagefolder data.
Open Source Model Profile · amunchet
rorshark-vit-base
rorshark-vit-base is an amunchet 85.8M-parameter ViT fine-tune for image classification. The model card documents imagefolder tuning with 0.9923 accuracy.
- Publisher
- amunchet
- Task
- image-classification
- Model type
- vit
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
rorshark-vit-base is published by amunchet as a ViT image-classification fine-tune. The captured configuration identifies ViTForImageClassification with model type vit, and Safetensors metadata reports 85,800,194 parameters. According to the model card, it fine-tunes google/vit-base-patch16-224-in21k on an imagefolder dataset under Apache-2.0.
Recorded capabilities
Reported evaluation result
The model card reports loss 0.0393 and accuracy 0.9923 on the evaluation set.
Documented training setup
According to the model card, training ran for 5 epochs with learning rate 2e-05, batch size 8, linear scheduling, and Adam.
Transformers-ready checkpoint
Captured metadata reports about 85.8M parameters with transformers support and Apache-2.0 licensing.
Use cases in the source record
- Image classification using a ViT checkpoint with the card's reported 0.9923 evaluation accuracy context.
- Fine-tune replication or comparison work using the card's documented hyperparameters and training-loss trajectory.
Limitations and unknowns
- No context-window, hardware requirement, or quantization detail was extracted.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Base-model, metric, and hyperparameter details come from the publisher model card and were not independently verified by Ethen.
Source and provenance
Source: amunchet/rorshark-vit-base
Captured: Unknown. Processed: 2026-09-07T19:34:40.039386+00:00.
rorshark-vit-base This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set: Loss: 0.0393 Accuracy: 0.9923 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: 2e-05 train_batch_size: 8 eval_batch_size: 8 seed: 1337 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 lr_scheduler_type: linear num_epochs: 5.0 Training results…
F001F002F003F004F005F006F007F009F010F011F012F013