| ---
|
| license: bsd-3-clause
|
| tags:
|
| - albef
|
| - classification
|
| - exponential
|
| - giant
|
| - layernorm
|
| - lion
|
| - low-rank
|
| - relu
|
| - standard
|
| - trunc-normal
|
| ---
|
|
|
| # model.py
|
|
|
| ## Model Overview
|
|
|
| A **giant**-scale implementation of the **albef** architecture, built for **classification** tasks.
|
|
|
| ## Architecture
|
|
|
| - **Architecture**: albef
|
| - **Scale**: giant
|
| - **Attention**: standard
|
| - **Fusion strategy**: low rank
|
| - **Task head**: classification
|
| - **Activation**: relu
|
| - **Normalization**: layernorm
|
| - **Initialization**: trunc normal
|
|
|
| ## Training
|
|
|
| - **Optimizer**: lion
|
| - **LR scheduler**: exponential
|
|
|
| ## Files
|
|
|
| - `model.py` — main artifact of this repository
|
|
|
| ## License
|
|
|
| See the license field above.
|
|
|
