CodeGenX

CodeGenX is back online! 🎉 We are sorry for the long wait

Existing users will need to update the extension in VsCode and New users can sign up on our website

<br/> <!-- <img src="assets/hero-image.png" alt="CodeGenX Logo"> --> <p align="center"> <img src="CodeGenX_demo.gif" width="800"/> </p>

CodeGenX is a Code Generation system powered by Artificial Intelligence! It is delivered to you in the form of a Visual Studio Code Extension and is Free and Open-source!

<br/>

Installation

You can find installation instructions and additional information about CodeGenX in the documentation here.

<br/>

About CodeGenX

1. Languages Supported

CodeGenX currently only supports Python. We are planning to add additional languages in future releases.

2. Modules Trained On

CodeGenX was trained on Python code which covers many of its common uses. Some libraries which CodeGenX is specifically trained on are:

1. Tensorflow
2. Pytorch
3. Scikit-Learn
4. Pandas
5. NumPy
6. OpenCV
7. Django
8. Flask
9. PyGame

3. How CodeGenX Works

At the core of CodeGenX lies a large neural network called GPT-J. GPT-J is a 6 billion parameter transformer model which was trained on hundreds of gigabytes of text from the internet. We fine-tuned this model on a dataset of open-source python code. This fine-tuned model can now be used to generate code when given an input with the right instructions.

<br/>

Contributors ✨

This project would not have been possible without the help of these wonderful people:

<br/> <table> <tr> <td align="center"><a href="https://github.com/Aryagm"><img src="https://avatars.githubusercontent.com/u/80019072?v=4" width="100px;" alt=""/><br />_{<b>Arya Manjaramkar</b>}</a></td> <td align="center"><a href="https://github.com/Matthias1590"><img src="https://avatars.githubusercontent.com/u/48327140?v=4" width="100px;" alt=""/><br />_{<b>Matthias Wijnsma</b>}</a><br /></td> <td align="center"><a href="https://github.com/ThomasHoutrique"><img src="https://avatars.githubusercontent.com/u/30757539?v=4" width="100px;" alt=""/><br />_{<b>Thomas Houtrique</b>}</a><br /></td> <td align="center"><a href="https://github.com/dome272"><img src="https://avatars.githubusercontent.com/u/61938694?v=4" width="100px;" alt=""/><br />_{<b>Dominic Rampas</b>}</td> <td align="center"><a href="https://github.com/LelouBil"><img src="https://avatars.githubusercontent.com/u/13931833?v=4" width="100px;" alt=""/><br />_{<b>Bilel Medimegh</b>}</td> <td align="center"><a href="https://github.com/orgs/DeepGenX/people/josh-hills"><img src="https://avatars.githubusercontent.com/u/57681652?v=4" width="100px;" alt=""/><br />_{<b>Josh Hills</b>}</td> <td align="center"><a href="https://github.com/Simplyalex99"><img src="https://avatars.githubusercontent.com/u/42325851?v=4" width="100px;" alt=""/><br />_<b>Alex</b></td> </tr> <tr> <td align="center"><a href="https://github.com/timothebot"><img src="https://avatars.githubusercontent.com/u/65387160?v=4" width="100px;" alt=""/><br />_<b>Tiimo</b></td> </tr> </table>

Acknowledgements

Many thanks to the support of the Google TPU Research Cloud for providing the precious compute needed for this project.