Instructions to use ProbeX/Model-J__DINO__model_idx_0985 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_0985 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_0985") 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_0985") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0985") - Notebooks
- Google Colab
- Kaggle
Model-J: DINO Model (model_idx_0985)
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_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 985 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9867 |
| Val Accuracy | 0.9069 |
| Test Accuracy | 0.9044 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, table, sea, girl, wolf, butterfly, bowl, spider, palm_tree, mountain, oak_tree, dinosaur, snail, kangaroo, man, television, sunflower, possum, cup, caterpillar, chimpanzee, beaver, forest, ray, tank, leopard, turtle, house, apple, shrew, plain, baby, tiger, rose, can, porcupine, fox, pear, aquarium_fish, lobster, tulip, skunk, streetcar, bus, mouse, rabbit, orange, train, road, dolphin
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0985
Base model
facebook/dino-vitb16