model_406344837_efficientformer_giant.py

Model Overview

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

Architecture

• Architecture: efficientformer
• Scale: giant
• Attention: flash
• Fusion strategy: tensor fusion
• Task head: multitask
• Activation: relu
• Normalization: groupnorm
• Initialization: kaiming normal

Training

• Optimizer: novograd
• LR scheduler: exponential

Files

• model_406344837_efficientformer_giant.py — main artifact of this repository

License

See the license field above.