niwalker's picture
Upload 2 files
eded682 verified
|
Raw
History Blame Contribute Delete
818 Bytes
---
license: cc-by-4.0
tags:
- adam
- bilinear
- efficientformer
- grouped-query
- layernorm
- linear-warmup
- matching
- mish
- orthogonal
- small
---
# model_384744536_efficientformer_small.py
## Model Overview
A **small**-scale implementation of the **efficientformer** architecture, built for **matching** tasks.
## Architecture
- **Architecture**: efficientformer
- **Scale**: small
- **Attention**: grouped query
- **Fusion strategy**: bilinear
- **Task head**: matching
- **Activation**: mish
- **Normalization**: layernorm
- **Initialization**: orthogonal
## Training
- **Optimizer**: adam
- **LR scheduler**: linear warmup
## Files
- `model_384744536_efficientformer_small.py` — main artifact of this repository
## License
See the license field above.