model_694405441_dino_xlarge.py

Model Overview

A xlarge-scale implementation of the dino architecture, built for multitask tasks.

Architecture

• Architecture: dino
• Scale: xlarge
• Attention: flash
• Fusion strategy: low rank
• Task head: multitask
• Activation: approx gelu
• Normalization: scalenorm
• Initialization: trunc normal

Training

• Optimizer: adam
• LR scheduler: step

Files

• model_694405441_dino_xlarge.py — main artifact of this repository

License

See the license field above.