metadata
license: apache-2.0
tags:
- adam
- batchnorm
- constant-warmup
- efficientformer
- mish
- multitask
- nano
- orthogonal
- standard
- tucker
model_371947084_efficientformer_nano.py
Model Overview
A nano-scale implementation of the efficientformer architecture, built for multitask tasks.
Architecture
- Architecture: efficientformer
- Scale: nano
- Attention: standard
- Fusion strategy: tucker
- Task head: multitask
- Activation: mish
- Normalization: batchnorm
- Initialization: orthogonal
Training
- Optimizer: adam
- LR scheduler: constant warmup
Files
model_371947084_efficientformer_nano.py— main artifact of this repository
License
See the license field above.