| ---
|
| license: mit
|
| tags:
|
| - gated-fusion
|
| - gelu
|
| - generation
|
| - groupnorm
|
| - kaiming-normal
|
| - lion
|
| - mobilevit
|
| - onecycle
|
| - small
|
| - standard
|
| ---
|
|
|
| # eval.py
|
|
|
| ## Model Overview
|
|
|
| A **small**-scale implementation of the **mobilevit** architecture, built for **generation** tasks.
|
|
|
| ## Architecture
|
|
|
| - **Architecture**: mobilevit
|
| - **Scale**: small
|
| - **Attention**: standard
|
| - **Fusion strategy**: gated fusion
|
| - **Task head**: generation
|
| - **Activation**: gelu
|
| - **Normalization**: groupnorm
|
| - **Initialization**: kaiming normal
|
|
|
| ## Training
|
|
|
| - **Optimizer**: lion
|
| - **LR scheduler**: onecycle
|
|
|
| ## Files
|
|
|
| - `eval.py` — main artifact of this repository
|
|
|
| ## License
|
|
|
| See the license field above.
|
|
|
