model.py
Model Overview
A huge-scale implementation of the mocov3 architecture, built for classification tasks.
Architecture
- Architecture: mocov3
- Scale: huge
- Attention: dilated
- Fusion strategy: low rank
- Task head: classification
- Activation: relu
- Normalization: rmsnorm
- Initialization: kaiming
Training
- Optimizer: lion
- LR scheduler: polynomial
Files
model.py — main artifact of this repository
License
See the license field above.