model_474312977_swin_t_huge.py

Model Overview

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

Architecture

  • Architecture: swin t
  • Scale: huge
  • Attention: standard
  • Fusion strategy: low rank
  • Task head: contrastive
  • Activation: swish
  • Normalization: instancenorm
  • Initialization: xavier

Training

  • Optimizer: adafactor
  • LR scheduler: constant warmup

Files

  • model_474312977_swin_t_huge.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