This is a small project we created to train a character level autoregressive transformer (or LSTM) model to predict Python source code. We trained it on GitHub repositories found on awesome pytorch list.<p>Github repo: https://github.com/lab-ml/python_autocomplete<p>You can try training on Google Colab: https://colab.research.google.com/github/lab-ml/python_autocomplete/blob/master/notebooks/train.ipynb<p>Here are some sample evaluations/visualizations of the trained model: https://colab.research.google.com/github/lab-ml/python_autocomplete/blob/master/notebooks/evaluate.ipynb<p>Working on a simple VSCode extension to test this out. Will open source it soon on the same repository.
<a href="https://www.kite.com/" rel="nofollow">https://www.kite.com/</a> does this too, claiming 47% less keystrokes. They are a good benchmark to set for seeing how efficient the model can get.