train.py
Model Overview
A huge-scale implementation of the efficientformer architecture, built for generation tasks.
Architecture
- Architecture: efficientformer
- Scale: huge
- Attention: standard
- Fusion strategy: low rank
- Task head: generation
- Activation: relu
- Normalization: instancenorm
- Initialization: xavier uniform
Training
- Optimizer: adam
- LR scheduler: onecycle
Files
train.py — main artifact of this repository
License
See the license field above.