Model reference · open weights
vit_base_patch16_224.orig_in21k is an open-weight embedding model from timm, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Model card for vitbasepatch16224.origin21k A Vision Transformer (ViT) image classification model. Pretrained on ImageNet-21k in JAX by paper authors, ported to PyTorch by Ross Wightman. This model does not have a classification head, useful for features and fine-tune only. Model Details - Model Type: Image classification / feature backbone - Model Stats: - Params (M): 85.8 - GMACs: 16.9 - Activations (M): 16.5 - Image size: 224 x 224 - Papers: - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2 - Dataset: ImageNet-21k - Original: https://github.com/google-research/visiontransformer Model Usage Image Classification Image Embeddings Model Comparison Explore the dataset and runtime metrics of this model in timm model results. Citation
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | timm |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 86M |
| Variants | 1 |
| Runs with | timm |
| Released | 2023-11-16 |
| Popularity | 24k downloads / month |
| Likes | 1 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| vit_base_patch16_224.orig_in21k | 86M | BF16 | ~0.2 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys vit-base-patch16-224-orig-in21k for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (vit-base-patch16-224-orig-in21k below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"vit-base-patch16-224-orig-in21k","input":"text to embed"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore