ViT-G (model soup)
University of WashingtonColumbia UniversityGoogleMeta AITel Aviv UniversityImage classificationOpen weights
Developed by University of Washington,Columbia University,Google,Meta AI,Tel Aviv University in 2022, ViT-G (model soup) is a image classification model with 1843000000.0 parameters with openly available weights.
About ViT-G (model soup)
The conventional recipe for maximizing model accuracy is to (1) train multiple models with various hyperparameters and (2) pick the individual model which performs best on a held-out validation set, discarding the remainder. In this paper, we revisit
Details
- Provider
- University of Washington,Columbia University,Google,Meta AI,Tel Aviv University
- Task
- Image classification
- Parameters
- 1843000000.0
- Released
- 2022-03-10
- Open weights
- Yes