---
license: mit
tags:
- batchnorm
- contrastive
- dino
- exponential
- gelu-tanh
- grouped-query
- kaiming
- rmsprop
- small
- tucker
---

# model_681957188_dino_small.py

## Model Overview

A **small**-scale implementation of the **dino** architecture, built for **contrastive** tasks.

## Architecture

- **Architecture**: dino
- **Scale**: small
- **Attention**: grouped query
- **Fusion strategy**: tucker
- **Task head**: contrastive
- **Activation**: gelu tanh
- **Normalization**: batchnorm
- **Initialization**: kaiming

## Training

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

## Files

- `model_681957188_dino_small.py` — main artifact of this repository

## License

See the license field above.