Model-J DINO
Collection
1002 items • Updated
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ProbeX/Model-J__DINO__model_idx_0498", dtype="auto")Quick Links
Model-J: DINO Model (model_idx_0498)
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
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 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 | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 498 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4276 |
| Val Accuracy | 0.3803 |
| Test Accuracy | 0.3744 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, bus, fox, mushroom, lamp, beaver, skunk, crocodile, bed, sunflower, possum, beetle, tank, can, lobster, kangaroo, skyscraper, turtle, bottle, tiger, road, snail, sea, bear, palm_tree, television, worm, telephone, maple_tree, butterfly, streetcar, raccoon, poppy, leopard, caterpillar, seal, hamster, trout, pear, bridge, rabbit, apple, baby, spider, cloud, elephant, rose, bowl, squirrel, pine_tree
Model tree for ProbeX/Model-J__DINO__model_idx_0498
Base model
facebook/dino-vitb16
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__DINO__model_idx_0498") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")