model_456715770_swin_t_small.py
Model Overview
A small-scale implementation of the swin t architecture, built for multitask tasks.
Architecture
- Architecture: swin t
- Scale: small
- Attention: sparse
- Fusion strategy: tucker
- Task head: multitask
- Activation: mish
- Normalization: layernorm
- Initialization: orthogonal
Training
- Optimizer: novograd
- LR scheduler: cosine
Files
model_456715770_swin_t_small.py — main artifact of this repository
License
See the license field above.