model_032508431_vit_huge.py

Model Overview

A huge-scale implementation of the vit architecture, built for multitask tasks.

Architecture

• Architecture: vit
• Scale: huge
• Attention: dilated
• Fusion strategy: low rank
• Task head: multitask
• Activation: mish
• Normalization: rmsnorm
• Initialization: xavier

Training

• Optimizer: lamb
• LR scheduler: polynomial

Files

• model_032508431_vit_huge.py — main artifact of this repository

License

See the license field above.