| ---
|
| license: mit
|
| tags:
|
| - adam
|
| - albef
|
| - contrastive
|
| - exponential
|
| - gelu
|
| - giant
|
| - grouped-query
|
| - instancenorm
|
| - kaiming-normal
|
| - low-rank
|
| ---
|
|
|
| # model_259485306_albef_giant.py
|
|
|
| ## Model Overview
|
|
|
| A **giant**-scale implementation of the **albef** architecture, built for **contrastive** tasks.
|
|
|
| ## Architecture
|
|
|
| - **Architecture**: albef
|
| - **Scale**: giant
|
| - **Attention**: grouped query
|
| - **Fusion strategy**: low rank
|
| - **Task head**: contrastive
|
| - **Activation**: gelu
|
| - **Normalization**: instancenorm
|
| - **Initialization**: kaiming normal
|
|
|
| ## Training
|
|
|
| - **Optimizer**: adam
|
| - **LR scheduler**: exponential
|
|
|
| ## Files
|
|
|
| - `model_259485306_albef_giant.py` — main artifact of this repository
|
|
|
| ## License
|
|
|
| See the license field above.
|
|
|
