metadata
base_model: google/vit-base-patch16-224
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: SupViT Model (model_idx_0418)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | SupViT |
| Split | train |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 418 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9483 |
| Test Accuracy | 0.9524 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orchid, ray, tractor, fox, house, hamster, raccoon, tank, plate, couch, snake, mushroom, mouse, bed, willow_tree, lawn_mower, cattle, flatfish, sweet_pepper, telephone, keyboard, bowl, shrew, rocket, sunflower, bridge, forest, chimpanzee, tulip, dinosaur, seal, bicycle, worm, shark, whale, wolf, girl, castle, palm_tree, bottle, rabbit, caterpillar, cup, skunk, streetcar, skyscraper, pine_tree, dolphin, crab, bus