model_405138432_efficientformer_giant.py

Model Overview

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

Architecture

• Architecture: efficientformer
• Scale: giant
• Attention: linear
• Fusion strategy: tensor fusion
• Task head: matching
• Activation: mish
• Normalization: layernorm
• Initialization: orthogonal

Training

• Optimizer: novograd
• LR scheduler: onecycle

Files

• model_405138432_efficientformer_giant.py — main artifact of this repository

License

See the license field above.