---
license: cc-by-4.0
tags:
- adamw
- contrastive
- exponential
- gated-fusion
- huge
- mish
- orthogonal
- scalenorm
- standard
- swin-t
---

# main.py

## Model Overview

A **huge**-scale implementation of the **swin t** architecture, built for **contrastive** tasks.

## Architecture

- **Architecture**: swin t
- **Scale**: huge
- **Attention**: standard
- **Fusion strategy**: gated fusion
- **Task head**: contrastive
- **Activation**: mish
- **Normalization**: scalenorm
- **Initialization**: orthogonal

## Training

- **Optimizer**: adamw
- **LR scheduler**: exponential

## Files

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

## License

See the license field above.