timm-converted weights
According to the model card, the weights were converted from the timm repository and used the same way as ViT-base.
Open Source Model Profile · WinKawaks
vit-tiny-patch16-224
vit-tiny-patch16-224 is a 5.72M-parameter ViT image classifier from WinKawaks. Its model card describes timm-converted weights used the same way as ViT-base.
- Publisher
- WinKawaks
- Task
- image-classification
- Model type
- vit
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
vit-tiny-patch16-224 is published by WinKawaks as an image-classification model. The captured configuration identifies ViTForImageClassification with a vit model type, and Safetensors metadata reports 5,717,416 parameters. According to the model card, its weights were converted from the timm repository for ViT-base-style use.
Recorded capabilities
Compact ViT classifier
The captured configuration records ViTForImageClassification with a vit type and about 5.72M parameters.
Torch 2.0 note
The model card notes that the safetensors model requires a torch 2.0 environment.
Use cases in the source record
- Image-classification workflows that follow the model card's ViT-base-style usage.
- Transformers and safetensors experiments in a torch 2.0 environment, as noted in the model card.
Limitations and unknowns
- No evaluation results were extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Derivation and runtime details come from a brief publisher model card and have not been independently verified by Ethen.
Source and provenance
Source: WinKawaks/vit-tiny-patch16-224
Captured: Unknown. Processed: 2026-09-07T19:34:38.542686+00:00.
Google didn't publish vit-tiny and vit-small model checkpoints in Hugging Face. I converted the weights from the timm repository . This model is used in the same way as ViT-base . Note that [safetensors] model requires torch 2.0 environment.
F001F002F003F004F005F006F007F008F009F010F011F012