model_450158682_swin_t_nano.py

Model Overview

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

Architecture

• Architecture: swin t
• Scale: nano
• Attention: dilated
• Fusion strategy: concat mlp
• Task head: generation
• Activation: swish
• Normalization: scalenorm
• Initialization: kaiming normal

Training

• Optimizer: rmsprop
• LR scheduler: linear warmup

Files

• model_450158682_swin_t_nano.py — main artifact of this repository

License

See the license field above.