model_654380581_mae_large.py

Model Overview

A large-scale implementation of the mae architecture, built for contrastive tasks.

Architecture

• Architecture: mae
• Scale: large
• Attention: dilated
• Fusion strategy: cross attention
• Task head: contrastive
• Activation: approx gelu
• Normalization: rmsnorm
• Initialization: orthogonal

Training

• Optimizer: adafactor
• LR scheduler: linear warmup

Files

• model_654380581_mae_large.py — main artifact of this repository

License

See the license field above.