model_637377192_mae_tiny.py

Model Overview

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

Architecture

• Architecture: mae
• Scale: tiny
• Attention: linear
• Fusion strategy: tensor fusion
• Task head: matching
• Activation: relu
• Normalization: scalenorm
• Initialization: xavier

Training

• Optimizer: adafactor
• LR scheduler: polynomial

Files

• model_637377192_mae_tiny.py — main artifact of this repository

License

See the license field above.