model_475557092_swin_t_huge.py

Model Overview

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

Architecture

• Architecture: swin t
• Scale: huge
• Attention: flash
• Fusion strategy: cross attention
• Task head: generation
• Activation: relu
• Normalization: batchnorm
• Initialization: kaiming

Training

• Optimizer: rmsprop
• LR scheduler: exponential

Files

• model_475557092_swin_t_huge.py — main artifact of this repository

License

See the license field above.