Hugging Face's logo

FoamoftheSea
/
multiformer-m0

Transformers
Safetensors
multiformer
Inference Endpoints
Model card Files Community
multiformer-m0 / README.md
FoamoftheSea's picture
FoamoftheSea
Update README.md
44b9481
preview code
|
raw
history blame contribute delete
1.59 kB
metadata
license: apache-2.0

Multiformer inference frame

Multiformer

Multiformer is a multi-task vision transformer architecture designed to provide strong perception capabilities with a nimble and lightweight architecture.

This model uses a custom branch of the transformers library, which can be installed easily using the instructions below.

For training and evaluation, a custom MultitaskTrainer class is used that can handle complex nested losses and successfully log them to wandb.

A training/eval and inference script are both available in the project repository.

Setup Instructions

  1. Open a terminal and navigate to your root folder, then run
git clone https://github.com/FoamoftheSea/shift-experiments.git
  1. Follow the setup instructions for your operating system found in the README

Quick Model Import

You should now be able to run the following code to load a Multiformer-M0 with pretrained weights:

from transformers import AutoModel

multiformer = AutoModel.from_pretrained("FoamoftheSea/multiformer-m0")