model_495140837_mixer_small.py

Model Overview

A small-scale implementation of the mixer architecture, built for contrastive tasks.

Architecture

• Architecture: mixer
• Scale: small
• Attention: sliding window
• Fusion strategy: tensor fusion
• Task head: contrastive
• Activation: relu
• Normalization: batchnorm
• Initialization: orthogonal

Training

• Optimizer: lamb
• LR scheduler: step

Files

• model_495140837_mixer_small.py — main artifact of this repository

License

See the license field above.