Instructions to use ProbeX/Model-J__DINO__model_idx_0624 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_0624 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_0624") 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_0624") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0624") - Notebooks
- Google Colab
- Kaggle
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__DINO__model_idx_0624")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0624")Model-J: DINO Model (model_idx_0624)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 624 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9934 |
| Val Accuracy | 0.8947 |
| Test Accuracy | 0.9054 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
aquarium_fish, boy, seal, trout, beetle, pickup_truck, chair, maple_tree, elephant, snake, cloud, tulip, ray, bee, palm_tree, woman, couch, baby, cattle, leopard, girl, shark, cockroach, telephone, oak_tree, spider, clock, butterfly, road, flatfish, table, raccoon, mountain, plain, crab, chimpanzee, shrew, sea, possum, tiger, bed, motorcycle, mushroom, lion, can, tractor, television, bowl, dinosaur, beaver
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0624
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_0624") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")