metadata

library_name: transformers
license: wtfpl
datasets:
  - fashion_mnist
tags:
  - moe

Model Card for ViTMix-v1

This model is a poorly functional demo to using MOEs in computer vision

Model Details

Model Description

This Model is mean't to serve more as a blueprint than a base. It has been trained of fashionmnist to prove that I can do tensor maths. It achieves an average loss of 0.4-ish.

The code is in files. Do what you want!