We are delighted to announce the first version of CodeGenX. CodeGenX is a free and open-source code-generation system (similiar to Github Copilot) powered by a fine-tuned version of GPT-J.
You can find details for installation and instruction on usage here: https://docs.deepgenx.com. Our GitHub repository can be found here: https://github.com/DeepGenX/CodeGenX.
I think it is important to identify what CodeGenX can and cannot do, so we know what to expect. We have found that CodeGenX works well for common use cases which occur repeatedly in the training set. It understands context and outputs code with similar formatting to your previous code using the appropriate variables. But it does not shine in places where logical or mathematical computations are needed. This does not mean that it doesn't understand any logic or math, but just a weak point of the model.
Here are some links that have additional information:
Website: https://deepgenx.com
Docs: https://docs.deepgenx.com
GitHub: https://github.com/DeepGenX/CodeGenX
Weights to the model: https://drive.google.com/drive/folders/1FCFLw2Svp7s8bcW6TZB83P_iwVUn2ITo?usp=sharing
Cheers! Team DeepGenX