model_576619759_deit_large.py
Model Overview
A large-scale implementation of the deit architecture, built for classification tasks.
Architecture
- Architecture: deit
- Scale: large
- Attention: linear
- Fusion strategy: co attention
- Task head: classification
- Activation: relu
- Normalization: rmsnorm
- Initialization: xavier uniform
Training
- Optimizer: lion
- LR scheduler: step
Files
model_576619759_deit_large.py— main artifact of this repository
License
See the license field above.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support