---
license: mit
tags:
- adamw
- base
- efficientformer
- groupnorm
- kaiming
- linear
- linear-warmup
- mish
- retrieval
- tucker
---

# inference.py

## Model Overview

A **base**-scale implementation of the **efficientformer** architecture, built for **retrieval** tasks.

## Architecture

- **Architecture**: efficientformer
- **Scale**: base
- **Attention**: linear
- **Fusion strategy**: tucker
- **Task head**: retrieval
- **Activation**: mish
- **Normalization**: groupnorm
- **Initialization**: kaiming

## Training

- **Optimizer**: adamw
- **LR scheduler**: linear warmup

## Files

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

## License

See the license field above.