lit-nlp

library1.3.1pypypi✓ verified 85d ago

LIT (Learning Interpretability Tool) is an open-source platform from PAIR (People + AI Research) at Google for visualizing and understanding machine learning models. Version 1.3.1 supports interpretability of generative AI, including sequence salience for LLMs, and can be deployed on Google Cloud with public container images. Releases occur approximately every 6 months.

ai-ml

pip install lit-nlp

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · LIT-NLP

lit-nlp

ai-mlpythonv1.3.1

Install

—

Import

—

Disk

—

Pass rate

0/ 10

Env Coverage0 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v? · pip install

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

build_error

glibc

py 3.10–3.95 runs

build_error

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

LitApp

✓ from lit_nlp import dev_server

✗ from lit_nlp import developer_server

The correct module is dev_server (not developer_server). Using the wrong name will cause ImportError.

SimpleMultilabelPreds

✓ from lit_nlp.api.types import SimpleMultilabelPreds

✗ from lit_nlp.lib.types import SimpleMultilabelPreds

The types module is under lit_nlp.api, not lit_nlp.lib. Incorrect import leads to ModuleNotFoundError.

Launches LIT server with a CoSE dataset and a BERT classifier. Open http://localhost:5432 to interact.

import lit_nlp from lit_nlp import dev_server from lit_nlp.examples.datasets import CoSEDataset from lit_nlp.examples.models import BertClassifier datasets = {'cose': CoSEDataset()} models = {'bert': BertClassifier(version='bert-base-uncased')} dev_server.serve(datasets, models, port=5432)

lit --version

Debug

Known issues

breakingAs of v1.0, the Model class has been refactored: _with_metadata methods are removed. Subclasses must implement get_metadata() directly.

fix

Replace calls to predict_with_metadata() with separate calls to predict() and get_metadata().

affects: >=1.0.0

breakingIn v0.5, the package name was changed from LIT to LIT (Learning Interpretability Tool). Some internal module paths may differ from older v0.4.x versions.

fix

If migrating from v0.4, update imports to use the new lit_nlp namespace and check for removed functions.

affects: >=0.5

deprecatedThe 'transformer' salience method is deprecated in favor of 'gradient' and 'attention' for sequence salience.

fix

Use 'gradient' or 'attention' salience methods instead of 'transformer' when calling model.salience().

affects: >=1.1

gotchaLIT's default salience computation can be slow on CPU for large models. Users often report that the UI appears frozen.

fix

Run LIT on a machine with GPU. For development, reduce the dataset size or model complexity.

affects: all

Errors

Common errors & fixes

ImportError: No module named 'lit_nlp'

The package was installed as 'lit-nlp' but Python expects 'lit_nlp' (underscore).

fix

Use: pip install lit-nlp and then import lit_nlp (underscore). Or check installation with: pip list | grep lit

ModuleNotFoundError: No module named 'lit_nlp.lib'

After v1.0, some internal modules were moved; 'lit_nlp.lib' no longer exists.

fix

Use correct import paths, e.g., from lit_nlp.api.types import ...

Upgrade

Version history

1.3.1latest on PyPI · released Dec 20, 2024

Audit

Dependencies

piprequiredLIT requires a relatively recent version of pip to resolve complex dependencies.

Agent activity

10 hits · last 30 days

node

Resources

githubhttps://github.com/PAIR-code/lit ↗

packagehttps://pypi.org/project/lit-nlp/ ↗

homepagehttps://pair-code.github.io/lit ↗