Monday, 4 January 2021
Show HN: Autocomplete Python Code with Transformers https://ift.tt/3887wTQ
Show HN: Autocomplete Python Code with Transformers 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. January 4, 2021 at 04:01PM
Subscribe to:
Post Comments (Atom)
-
Please like share & subscribe your channel.
-
Show HN: Build your own detector to measure ionising radiation https://ift.tt/3gxP5ul December 10, 2020 at 07:48PM
No comments:
Post a Comment