Instructions to use ProbeX/Model-J__DINO__model_idx_0021 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_0021 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_0021") 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_0021") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0021") - Notebooks
- Google Colab
- Kaggle
Model-J: DINO Model (model_idx_0021)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 21 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5605 |
| Val Accuracy | 0.4595 |
| Test Accuracy | 0.4714 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bottle, orange, apple, cup, flatfish, motorcycle, tiger, shrew, cockroach, elephant, tank, squirrel, tractor, wardrobe, ray, road, chair, plain, chimpanzee, skunk, bus, camel, turtle, keyboard, butterfly, rose, mouse, plate, bed, telephone, house, crab, sweet_pepper, lamp, hamster, oak_tree, pickup_truck, pine_tree, forest, worm, skyscraper, spider, sea, shark, aquarium_fish, lawn_mower, streetcar, bridge, cloud, bowl
- Downloads last month
- 1
Model tree for ProbeX/Model-J__DINO__model_idx_0021
Base model
facebook/dino-vitb16