Instructions to use ProbeX/Model-J__SupViT__model_idx_0789 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_0789 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_0789") 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_0789") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__SupViT__model_idx_0789") - Notebooks
- Google Colab
- Kaggle
Model-J: SupViT Model (model_idx_0789)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 789 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9979 |
| Val Accuracy | 0.9352 |
| Test Accuracy | 0.9332 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, crocodile, shark, chair, apple, dolphin, kangaroo, sunflower, hamster, elephant, mountain, bed, camel, chimpanzee, pickup_truck, tulip, mushroom, keyboard, possum, poppy, bear, lizard, beaver, cup, lobster, fox, plain, bowl, girl, raccoon, maple_tree, trout, boy, house, plate, squirrel, pine_tree, can, sea, couch, motorcycle, tiger, road, crab, sweet_pepper, man, cloud, otter, orange, bridge
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0789
Base model
google/vit-base-patch16-224