---
license: apache-2.0
tags:
- adamw
- co-attention
- generation
- grouped-query
- instancenorm
- relu
- step
- swin-t
- tiny
- trunc-normal
---

# model_454146562_swin_t_tiny.py

## Model Overview

A **tiny**-scale implementation of the **swin t** architecture, built for **generation** tasks.

## Architecture

- **Architecture**: swin t
- **Scale**: tiny
- **Attention**: grouped query
- **Fusion strategy**: co attention
- **Task head**: generation
- **Activation**: relu
- **Normalization**: instancenorm
- **Initialization**: trunc normal

## Training

- **Optimizer**: adamw
- **LR scheduler**: step

## Files

- `model_454146562_swin_t_tiny.py` — main artifact of this repository

## License

See the license field above.