New Show Hacker News story: Show HN: Autocomplete Python Code with Transformers

New Show Hacker News story: Show HN: Autocomplete Python Code with Transformers

Show HN: Autocomplete Python Code with Transformers
2 by vpj | 1 comments on Hacker News.
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. Github repo: https://ift.tt/3pNn9pS You can try training on Google Colab: https://ift.tt/3887Fqm Here are some sample evaluations/visualizations of the trained model: https://ift.tt/38d7Y38 Working on a simple VSCode extension to test this out. Will open source it soon on the same repository.

Related Posts

0 Response to "New Show Hacker News story: Show HN: Autocomplete Python Code with Transformers"

Post a Comment

Ads on article

Advertise in articles 1

advertising articles 2

Advertise under the article