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!

Downloads last month
143
Safetensors
Model size
391M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support model that require custom code execution.

Dataset used to train SE6446/VitMix-v1