model_444161135_poolformer_giant.py

Model Overview

A giant-scale implementation of the poolformer architecture, built for multitask tasks.

Architecture

• Architecture: poolformer
• Scale: giant
• Attention: sliding window
• Fusion strategy: low rank
• Task head: multitask
• Activation: gelu tanh
• Normalization: layernorm
• Initialization: trunc normal

Training

• Optimizer: novograd
• LR scheduler: constant warmup

Files

• model_444161135_poolformer_giant.py — main artifact of this repository

License

See the license field above.