Instructions to use ProbeX/Model-J__DINO__model_idx_0787 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_0787 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_0787") 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_0787") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0787") - Notebooks
- Google Colab
- Kaggle
Model-J: DINO Model (model_idx_0787)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 787 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2875 |
| Val Accuracy | 0.2749 |
| Test Accuracy | 0.2606 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, tiger, worm, woman, lobster, seal, spider, flatfish, pickup_truck, skunk, road, sweet_pepper, house, plain, palm_tree, squirrel, lion, cloud, fox, lizard, dolphin, skyscraper, aquarium_fish, clock, snail, wolf, girl, rocket, motorcycle, bicycle, chimpanzee, apple, leopard, butterfly, rose, chair, cattle, hamster, baby, bear, trout, tank, tulip, porcupine, cockroach, mountain, couch, plate, pear, can
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0787
Base model
facebook/dino-vitb16