---
license: mit
tags:
- adamw
- gated-fusion
- gelu
- large
- onecycle
- retrieval
- scalenorm
- sliding-window
- swin-t
- trunc-normal
---

# model_467075230_swin_t_large.py

## Model Overview

A **large**-scale implementation of the **swin t** architecture, built for **retrieval** tasks.

## Architecture

- **Architecture**: swin t
- **Scale**: large
- **Attention**: sliding window
- **Fusion strategy**: gated fusion
- **Task head**: retrieval
- **Activation**: gelu
- **Normalization**: scalenorm
- **Initialization**: trunc normal

## Training

- **Optimizer**: adamw
- **LR scheduler**: onecycle

## Files

- `model_467075230_swin_t_large.py` — main artifact of this repository

## License

See the license field above.