ViT-22B
GoogleObject detectionImage classification
ViT-22B is object detection model published by Google in 2023 featuring 21743000000.0 parameters.
About ViT-22B
The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the same architecture to image an
Details
- Provider
- Task
- Object detection,Image classification
- Parameters
- 21743000000.0
- Released
- 2023-02-10
- Open weights
- No