model_025841463_vit_xlarge.py

Model Overview

A xlarge-scale implementation of the vit architecture, built for classification tasks.

Architecture

• Architecture: vit
• Scale: xlarge
• Attention: sliding window
• Fusion strategy: tucker
• Task head: classification
• Activation: swish
• Normalization: layernorm
• Initialization: xavier

Training

• Optimizer: lamb
• LR scheduler: polynomial

Files

• model_025841463_vit_xlarge.py — main artifact of this repository

License

See the license field above.