model_483370525_mixer_nano.py

Model Overview

A nano-scale implementation of the mixer architecture, built for matching tasks.

Architecture

• Architecture: mixer
• Scale: nano
• Attention: standard
• Fusion strategy: tucker
• Task head: matching
• Activation: relu
• Normalization: instancenorm
• Initialization: trunc normal

Training

• Optimizer: adafactor
• LR scheduler: linear warmup

Files

• model_483370525_mixer_nano.py — main artifact of this repository

License

See the license field above.