KerasNLP is a natural language processing library that supports users through their entire development cycle. Our workflows are built from modular components that have state-of-the-art preset weights and architectures when used out-of-the-box and are easily customizable when more control is needed. We emphasize in-graph computation for all workflows so that developers can expect easy productionization using the TensorFlow ecosystem.

This library is an extension of the core Keras API; all high-level modules are Layers or Models that receive that same level of polish as core Keras. If you are familiar with Keras, congratulations! You already understand most of KerasNLP.

See our Getting Started guide for example usage of our modular API starting with evaluating pretrained models and building up to designing a novel transformer architecture and training a tokenizer from scratch.

We are a new and growing project and welcome contributions.

• Home Page
• Developer Guides
• API Reference
• Getting Started guide

• Contributing Guide
• Roadmap
• Style Guide
• API Design Guide
• Call for Contributions

To install the latest official release:

pip install keras-nlp --upgrade

To install the latest unreleased changes to the library, we recommend using pip to install directly from the master branch on github:

pip install git+https://github.com/keras-team/keras-nlp.git --upgrade

Fine-tune BERT on a small sentiment analysis task using the keras_nlp.models API:

import keras_nlp
import tensorflow_datasets as tfds

imdb_train, imdb_test = tfds.load(
    "imdb_reviews",
    split=["train", "test"],
    as_supervised=True,
    batch_size=16,
)
# Load a BERT model.
classifier = keras_nlp.models.BertClassifier.from_preset(
    "bert_base_en_uncased", 
    num_classes=2,
)
# Fine-tune on IMDb movie reviews.
classifier.fit(imdb_train, validation_data=imdb_test)
# Predict two new examples.
classifier.predict(["What an amazing movie!", "A total waste of my time."])

For more in depth guides and examples, visit https://keras.io/keras_nlp/.

We follow Semantic Versioning, and plan to provide backwards compatibility guarantees both for code and saved models built with our components. While we continue with pre-release 0.y.z development, we may break compatibility at any time and APIs should not be consider stable.

KerasNLP provides access to pre-trained models via the keras_nlp.models API. These pre-trained models are provided on an "as is" basis, without warranties or conditions of any kind. The following underlying models are provided by third parties, and subject to separate licenses: BART, DeBERTa, DistilBERT, GPT-2, OPT, RoBERTa, Whisper, and XLM-RoBERTa.

If KerasNLP helps your research, we appreciate your citations. Here is the BibTeX entry:

@misc{kerasnlp2022,
  title={KerasNLP},
  author={Watson, Matthew, and Qian, Chen, and Bischof, Jonathan and Chollet, 
  Fran\c{c}ois and others},
  year={2022},
  howpublished={\url{https://github.com/keras-team/keras-nlp}},
}

Thank you to all of our wonderful contributors!