| ---
|
| license: cc-by-4.0
|
| tags:
|
| - albef
|
| - bilinear
|
| - dilated
|
| - giant
|
| - groupnorm
|
| - lion
|
| - onecycle
|
| - orthogonal
|
| - retrieval
|
| - swish
|
| ---
|
|
|
| # model_259948275_albef_giant.py
|
|
|
| ## Model Overview
|
|
|
| A **giant**-scale implementation of the **albef** architecture, built for **retrieval** tasks.
|
|
|
| ## Architecture
|
|
|
| - **Architecture**: albef
|
| - **Scale**: giant
|
| - **Attention**: dilated
|
| - **Fusion strategy**: bilinear
|
| - **Task head**: retrieval
|
| - **Activation**: swish
|
| - **Normalization**: groupnorm
|
| - **Initialization**: orthogonal
|
|
|
| ## Training
|
|
|
| - **Optimizer**: lion
|
| - **LR scheduler**: onecycle
|
|
|
| ## Files
|
|
|
| - `model_259948275_albef_giant.py` — main artifact of this repository
|
|
|
| ## License
|
|
|
| See the license field above.
|
|
|
