model_498461607_mixer_base.py

Model Overview

A base-scale implementation of the mixer architecture, built for classification tasks.

Architecture

• Architecture: mixer
• Scale: base
• Attention: sparse
• Fusion strategy: tucker
• Task head: classification
• Activation: gelu tanh
• Normalization: instancenorm
• Initialization: xavier uniform

Training

• Optimizer: adam
• LR scheduler: cosine

Files

• model_498461607_mixer_base.py — main artifact of this repository

License

See the license field above.