Beit Base Patch 16 224
Microsoft's Beit Base Patch 16 224 is a Vision Transformer model pre-trained in a self-supervised fashion on ImageNet-21k and fine-tuned on ImageNet-1k, exceling at learning inner representations of images for downstream tasks such as image classification. It notably utilizes relative position embeddings and a mean-pooling approach for classification.
Input
Output
Context
-
Max Output
-
Parameters
-
Technical Specifications
Model TypeVision
Context WindowNot available
Max Output TokensNot available
ParametersNot available
Release DateMar 2, 2022
Training CutoffJun 15, 2021
Licenseapache-2.0
Open SourceYes
Input Modalities
Image
Output Modalities
Text
Capabilities
Resources & Links
More Models by Microsoft
Table Transformer Structure Recognition V1.1 All28.8M · Open weightsPhi 4 Mini Instruct131K context · 3.8B · Open weightsDeberta Large Mnli1K context · Open weightsVibevoice ASR HF131K context · 8.3B · Open weightsPhi 3.5 Vision Instruct131K context · 4.1B · Open weightsUnixcoder Base1K context · Open weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jul 30, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.