model.py
Model Overview
A tiny-scale implementation of the poolformer architecture, built for multitask tasks.
Architecture
- Architecture: poolformer
- Scale: tiny
- Attention: standard
- Fusion strategy: cross attention
- Task head: multitask
- Activation: approx gelu
- Normalization: instancenorm
- Initialization: kaiming normal
Training
- Optimizer: adafactor
- LR scheduler: constant warmup
Files
model.py — main artifact of this repository
License
See the license field above.