Instructions to use ProbeX/Model-J__DINO__model_idx_0482 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ProbeX/Model-J__DINO__model_idx_0482 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__DINO__model_idx_0482") 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__DINO__model_idx_0482") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0482") - Notebooks
- Google Colab
- Kaggle
Model-J: DINO Model (model_idx_0482)
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 | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 482 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9261 |
| Test Accuracy | 0.9228 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wolf, apple, plate, aquarium_fish, kangaroo, sweet_pepper, dinosaur, lawn_mower, hamster, skyscraper, keyboard, snail, beetle, bed, baby, camel, dolphin, road, castle, leopard, flatfish, cup, train, whale, rose, worm, lion, orchid, forest, pine_tree, lobster, mushroom, rabbit, clock, man, orange, motorcycle, snake, lizard, woman, raccoon, spider, seal, bus, telephone, bottle, trout, streetcar, palm_tree, boy
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0482
Base model
facebook/dino-vitb16