model_474544880_swin_t_huge.py
Model Overview
A huge-scale implementation of the swin t architecture, built for generation tasks.
Architecture
- Architecture: swin t
- Scale: huge
- Attention: linear
- Fusion strategy: concat mlp
- Task head: generation
- Activation: mish
- Normalization: scalenorm
- Initialization: xavier
Training
- Optimizer: lamb
- LR scheduler: constant warmup
Files
model_474544880_swin_t_huge.py — main artifact of this repository
License
See the license field above.
