anilkumarzep's picture
Upload 2 files
59835c1 verified
|
Raw
History Blame Contribute Delete
776 Bytes
---
license: apache-2.0
tags:
- albef
- classification
- flash
- groupnorm
- low-rank
- mish
- novograd
- polynomial
- tiny
- xavier-uniform
---
# model_229855798_albef_tiny.py
## Model Overview
A **tiny**-scale implementation of the **albef** architecture, built for **classification** tasks.
## Architecture
- **Architecture**: albef
- **Scale**: tiny
- **Attention**: flash
- **Fusion strategy**: low rank
- **Task head**: classification
- **Activation**: mish
- **Normalization**: groupnorm
- **Initialization**: xavier uniform
## Training
- **Optimizer**: novograd
- **LR scheduler**: polynomial
## Files
- `model_229855798_albef_tiny.py` — main artifact of this repository
## License
See the license field above.