---
license: mit
tags:
- batchnorm
- deit
- exponential
- generation
- relu
- rmsprop
- sparse
- tiny
- tucker
- xavier-uniform
---

# model_563519876_deit_tiny.py

## Model Overview

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

## Architecture

- **Architecture**: deit
- **Scale**: tiny
- **Attention**: sparse
- **Fusion strategy**: tucker
- **Task head**: generation
- **Activation**: relu
- **Normalization**: batchnorm
- **Initialization**: xavier uniform

## Training

- **Optimizer**: rmsprop
- **LR scheduler**: exponential

## Files

- `model_563519876_deit_tiny.py` — main artifact of this repository

## License

See the license field above.