main.py
Model Overview
A huge-scale implementation of the deit architecture, built for classification tasks.
Architecture
- Architecture: deit
- Scale: huge
- Attention: sliding window
- Fusion strategy: bilinear
- Task head: classification
- Activation: gelu tanh
- Normalization: groupnorm
- Initialization: trunc normal
Training
- Optimizer: lion
- LR scheduler: step
Files
main.py — main artifact of this repository
License
See the license field above.
