model.py

Model Overview

A nano-scale implementation of the dino architecture, built for contrastive tasks.

Architecture

  • Architecture: dino
  • Scale: nano
  • Attention: standard
  • Fusion strategy: bilinear
  • Task head: contrastive
  • Activation: swish
  • Normalization: instancenorm
  • Initialization: kaiming

Training

  • Optimizer: adam
  • LR scheduler: onecycle

Files

  • model.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