Instructions to use ProbeX/Model-J__SupViT__model_idx_0634 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ProbeX/Model-J__SupViT__model_idx_0634 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__SupViT__model_idx_0634") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__SupViT__model_idx_0634") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__SupViT__model_idx_0634") - Notebooks
- Google Colab
- Kaggle
Model-J: SupViT Model (model_idx_0634)
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
๐ Project | ๐ Paper | ๐ป GitHub | ๐ค Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | SupViT |
| Split | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 634 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9872 |
| Val Accuracy | 0.9352 |
| Test Accuracy | 0.9372 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crocodile, clock, cup, mountain, shrew, bed, bee, sea, lobster, plain, streetcar, wolf, girl, sweet_pepper, table, castle, fox, worm, tiger, wardrobe, pickup_truck, butterfly, palm_tree, telephone, raccoon, sunflower, mushroom, rocket, television, camel, dolphin, plate, rabbit, pear, skyscraper, mouse, seal, can, bus, forest, skunk, boy, otter, trout, poppy, house, dinosaur, lawn_mower, snake, spider
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0634
Base model
google/vit-base-patch16-224