model_482287707_swin_t_giant.py
Model Overview
A giant-scale implementation of the swin t architecture, built for matching tasks.
Architecture
- Architecture: swin t
- Scale: giant
- Attention: grouped query
- Fusion strategy: bilinear
- Task head: matching
- Activation: gelu tanh
- Normalization: layernorm
- Initialization: trunc normal
Training
- Optimizer: lion
- LR scheduler: onecycle
Files
model_482287707_swin_t_giant.py— main artifact of this repository
License
See the license field above.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support