model_644131870_mae_small.py

Model Overview

A small-scale implementation of the mae architecture, built for matching tasks.

Architecture

• Architecture: mae
• Scale: small
• Attention: multi query
• Fusion strategy: gated fusion
• Task head: matching
• Activation: mish
• Normalization: layernorm
• Initialization: kaiming normal

Training

• Optimizer: novograd
• LR scheduler: polynomial

Files

• model_644131870_mae_small.py — main artifact of this repository

License

See the license field above.