model_666025870_mae_giant.py

Model Overview

A giant-scale implementation of the mae architecture, built for multitask tasks.

Architecture

  • Architecture: mae
  • Scale: giant
  • Attention: flash
  • Fusion strategy: cross attention
  • Task head: multitask
  • Activation: mish
  • Normalization: scalenorm
  • Initialization: kaiming normal

Training

  • Optimizer: adamw
  • LR scheduler: onecycle

Files

  • model_666025870_mae_giant.py — main artifact of this repository

License

See the license field above.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support