model_394634512_efficientformer_large.py

Model Overview

A large-scale implementation of the efficientformer architecture, built for generation tasks.

Architecture

• Architecture: efficientformer
• Scale: large
• Attention: dilated
• Fusion strategy: bilinear
• Task head: generation
• Activation: relu
• Normalization: batchnorm
• Initialization: xavier

Training

• Optimizer: novograd
• LR scheduler: onecycle

Files

• model_394634512_efficientformer_large.py — main artifact of this repository

License

See the license field above.