run.py

Model Overview

A tiny-scale implementation of the cnn transformer architecture, built for classification tasks.

Architecture

  • Architecture: cnn transformer
  • Scale: tiny
  • Attention: sparse
  • Fusion strategy: concat mlp
  • Task head: classification
  • Activation: gelu tanh
  • Normalization: groupnorm
  • Initialization: kaiming

Training

  • Optimizer: lion
  • LR scheduler: linear warmup

Files

  • run.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