---
license: cc-by-4.0
tags:
- bilinear
- classification
- gelu-tanh
- grouped-query
- nano
- rmsnorm
- sgd
- step
- swin-t
- trunc-normal
---

# model_449761608_swin_t_nano.py

## Model Overview

A **nano**-scale implementation of the **swin t** architecture, built for **classification** tasks.

## Architecture

- **Architecture**: swin t
- **Scale**: nano
- **Attention**: grouped query
- **Fusion strategy**: bilinear
- **Task head**: classification
- **Activation**: gelu tanh
- **Normalization**: rmsnorm
- **Initialization**: trunc normal

## Training

- **Optimizer**: sgd
- **LR scheduler**: step

## Files

- `model_449761608_swin_t_nano.py` — main artifact of this repository

## License

See the license field above.