Welcome to the Language Interpretability Tool (🔥LIT)!

If you want to jump in and start playing with the LIT UI, check out https://pair-code.github.io/lit/demos/ for links to our hosted demos.

For a guide to the many features available, check out the UI guide or this short video.

LIT provides a simple Python API for use with custom models and data, as well as components such as metrics and counterfactual generators. Most LIT users will take this route, which involves writing a short demo.py binary to link in Model and Dataset implementations. In many cases, this can be just a few lines of logic:

  datasets = {
      'foo_data': FooDataset('/path/to/foo.tsv'),
      'bar_data': BarDataset('/path/to/bar.tfrecord'),
  }
  models = {'my_model': MyModel('/path/to/model/files')}
  lit_demo = lit_nlp.dev_server.Server(models, datasets, port=4321)
  lit_demo.serve()

Check out the API documentation for more, and the demos directory for a wealth of examples. The components guide also gives a good overview of the different features that are available, and how to enable them for your model.

Also, join https://groups.google.com/g/lit-annoucements to receive announcements and updates on new LIT features.

LIT can also be used directly from Colab and Jupyter notebooks, with the LIT UI rendered in an output cell. See https://colab.research.google.com/github/pair-code/lit/blob/dev/lit_nlp/examples/notebooks/LIT_sentiment_classifier.ipynb for an example.

Note: if you see a 403 error in the output cell where LIT should render, you may need to enable cookies on the Colab site.

Many LIT components - such as models, datasets, metrics, and salience methods - are stand-alone Python classes and can be easily used outside of the LIT UI. For additional details, see the API documentation and an example Colab at https://colab.research.google.com/github/pair-code/lit/blob/dev/lit_nlp/examples/notebooks/LIT_Components_Example.ipynb.

The demos page lists some of the pre-built demos available for a variety of model types. The code for these is under https://github.com/PAIR-code/lit/blob/main/lit_nlp/examples ; each is a small script that loads one or more models and starts a LIT server.

Most demos can be run with a single blaze command. To run the default one, you can do:

python -m lit_nlp.examples.glue_demo \
  --quickstart --port=4321 --alsologtostderr

Then navigate to https://localhost:4321 to access the UI.

Note:

You can also pass --warm_start=1.0, and LIT will run inference and cache the results before server start.

For an overview of supported model types and frameworks, see the components guide.