model_449761608_swin_t_nano.py

Model Overview

A nano-scale implementation of the swin t architecture, built for classification tasks.

Architecture

• Architecture: swin t
• Scale: nano
• Attention: grouped query
• Fusion strategy: bilinear
• Task head: classification
• Activation: gelu tanh
• Normalization: rmsnorm
• Initialization: trunc normal

Training

• Optimizer: sgd
• LR scheduler: step

Files

• model_449761608_swin_t_nano.py — main artifact of this repository

License

See the license field above.