Instructions to use ProbeX/Model-J__MAE__model_idx_0707 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ProbeX/Model-J__MAE__model_idx_0707 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__MAE__model_idx_0707") 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__MAE__model_idx_0707") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0707") - Notebooks
- Google Colab
- Kaggle
Model-J: MAE Model (model_idx_0707)
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 | MAE |
| Split | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 707 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9782 |
| Val Accuracy | 0.8763 |
| Test Accuracy | 0.8624 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crocodile, forest, butterfly, apple, raccoon, dinosaur, wolf, beaver, fox, cattle, plain, bridge, mushroom, ray, couch, sweet_pepper, skyscraper, shrew, orchid, camel, streetcar, kangaroo, sea, rabbit, lobster, wardrobe, pear, shark, bear, tulip, bowl, table, turtle, aquarium_fish, lion, pickup_truck, elephant, sunflower, willow_tree, cockroach, crab, chair, mountain, tractor, can, tiger, orange, oak_tree, bicycle, man
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0707
Base model
facebook/vit-mae-base