model_481991774_swin_t_giant.py

Model Overview

A giant-scale implementation of the swin t architecture, built for matching tasks.

Architecture

  • Architecture: swin t
  • Scale: giant
  • Attention: grouped query
  • Fusion strategy: co attention
  • Task head: matching
  • Activation: relu
  • Normalization: rmsnorm
  • Initialization: xavier

Training

  • Optimizer: rmsprop
  • LR scheduler: constant warmup

Files

  • model_481991774_swin_t_giant.py — main artifact of this repository

License

See the license field above.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support