Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/gizatechxyz/orion
ONNX Runtime in Cairo 1.0 for verifiable ML inference using STARK
https://github.com/gizatechxyz/orion
cairo-lang deep-learning machine-learning onnx starknet tensorflow
Last synced: about 2 months ago
JSON representation
ONNX Runtime in Cairo 1.0 for verifiable ML inference using STARK
- Host: GitHub
- URL: https://github.com/gizatechxyz/orion
- Owner: gizatechxyz
- License: mit
- Created: 2022-04-21T09:40:36.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-30T12:00:10.000Z (2 months ago)
- Last Synced: 2024-05-08T00:24:31.471Z (2 months ago)
- Topics: cairo-lang, deep-learning, machine-learning, onnx, starknet, tensorflow
- Language: Cairo
- Homepage: https://orion.gizatech.xyz
- Size: 47.2 MB
- Stars: 149
- Watchers: 7
- Forks: 79
- Open Issues: 79
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- awesome-cairo - `orion` - library for verifiable ML inference in Cairo 1.0 (Libraries)
README
![]()
[![GitHub Workflow Status](https://github.com/gizatechxyz/orion/actions/workflows/test.yaml/badge.svg)](https://github.com/gizatechxyz/orion/actions/workflows/test.yaml)
[![Project license](https://img.shields.io/github/license/gizatechxyz/orion.svg?style=flat-square)](LICENSE)
[![Pull Requests welcome](https://img.shields.io/badge/PRs-welcome-ff69b4.svg?style=flat-square)](https://github.com/gizatechxyz/orion/issues?q=is%3Aissue+is%3Aopen)
[![Join the community](https://dcbadge.vercel.app/api/server/kvqVYbCpU3?style=flat&compact=true)](https://discord.gg/kvqVYbCpU3)# Orion: An Open-source Framework for Validity and ZK ML โจ
[![All Contributors](https://img.shields.io/badge/all_contributors-32-orange.svg?style=flat-square)](#contributors-)
Orion is an open-source, community-driven framework dedicated to Provable Machine Learning. It provides essential components and a new ONNX runtime for building verifiable Machine Learning models using [STARKs](https://starkware.co/stark/).
## ๐ค What is ONNX Runtime?
ONNX (Open Neural Network Exchange), is an open-source standard created to represent deep learning models. The aim of its development was to enable interoperability among diverse deep learning frameworks, like TensorFlow or PyTorch. By offering a universal file format, ONNX allows models trained in one framework to be readily applied in another for inference, eliminating the need for model conversion.
Ensuring compatibility with ONNX operators facilitates integration into the ONNX ecosystem. This enables researchers and developers to pre-train models using their preferred framework, before executing verifiable inferences with Orion.
## ๐ฑ Where to start?
You can check our official docs [here](https://orion.gizatech.xyz/welcome/readme).
- ๐งฑ [Framework](https://orion.gizatech.xyz/v/develop/framework/get-started): The building blocks for Verifiable Machine Learning models.
- ๐ [Hub](https://orion.gizatech.xyz/v/develop/hub/algorithms): A curated collection of ML models and spaces built by the community using Orion framework.
- ๐ [Academy](https://orion.gizatech.xyz/v/develop/academy/tutorials): Resources and tutorials for learning how to build ValidityML models using Orion.## ๐ Join the community!
Join the community and help build a safer and transparent AI in our [Discord](https://discord.gg/kvqVYbCpU3)!
## ๐ Orion Usage
- For an insightful overview of impressive proof of concepts, models, and tutorials created by our community, please visit [Orion Usage](https://github.com/gizatechxyz/orion/blob/main/orion-usage.md).
- Discover a curated list of tutorials and models developed using Orion in [Orion-Hub](https://github.com/gizatechxyz/Orion-Hub).## โ๏ธ Authors & contributors
For a full list of all authors and contributors, see [the contributors page](https://github.com/franalgaba/onnx-cairo/graphs/contributors).
## License
This project is licensed under the **MIT license**.
See [LICENSE](https://github.com/franalgaba/onnx-cairo/blob/main/LICENSE) for more information.
## Contributors โจ
Thanks goes to these wonderful people:
Fran Algaba
๐ป
raphaelDkhn
๐ป
Lanre Ojetokun
๐ป ๐
Moody Salem
๐ป ๐
Roy Rotstein
๐ป
omahs
๐
Kazeem Hakeem
๐ป
dblanco
๐ป
BemTG
๐ป ๐
danilowhk
๐ป
Falco R
๐ป
dincerguner
๐ป
Rich Warner
๐ป
Daniel Bejarano
๐
vikkydataseo
๐
Daniel
๐ป
Charlotte
๐ป
0xfulanito
๐ป
0x73e
๐ป
Thomas S. Bauer
๐ป
Andres
๐ป
Ephraim Chukwu
๐ป
Bal7hazar
๐
Tony Stark
๐
Mahmoud Mohajer
๐ป
HappyTomatoo
๐
Bilgin Koรงak
๐ป
akhercha
๐ป
Vid Kersic
๐ป
Trunks @ Carbonable
๐
canacechan
๐ป
Tristan
๐ป
Kugo
๐
Beeyoung
๐ป
This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!