keras-hub

Modular Natural Language Processing workflows with Keras

APACHE-2.0 License

Downloads
4.7K
Stars
762
View Code on GitHub
Ecosystems: Keras, Tensorflow

Bot releases are visible (Hide)

keras-hub - v0.8.2

Published by mattdangerw 8 months ago

Summary

What's Changed

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.8.1...v0.8.2.dev0

keras-hub - v0.8.2.dev0

Published by mattdangerw 8 months ago

Summary

What's Changed

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.8.1...v0.8.2.dev0

keras-hub - v0.8.1

Published by mattdangerw 8 months ago

Minor fixes to Kaggle Gemma assets.

What's Changed

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.8.0...v0.8.1

keras-hub - v0.8.0

Published by mattdangerw 8 months ago

The 0.8.0 release focuses on generative LLM features in KerasNLP.

Summary

  • Added the Mistral and Gemma models.
  • Allow passing dtype directly to backbone and task constructors.
  • Add a settable sequence_length property to all preprocessing layers.
  • Added enable_lora() to the backbone class for parameter efficient fine-tuning.
  • Added layer attributes to backbone models for easier access to model internals.
  • Added AlibiBias layer.
# Pass dtype to a model.
causal_lm = keras_nlp.MistralCausalLM.from_preset(
    "mistral_instruct_7b_en",
    dtype="bfloat16"
)
# Settable sequence length property.
causal_lm.preprocessor.sequence_length = 128
# Lora API.
causal_lm.enable_lora(rank=4)
# Easy layer attributes.
for layer in causal_lm.backbone.transformer_layers:
    print(layer.count_params())

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.7.0...v0.8.0

keras-hub - v0.8.0.dev0

Published by mattdangerw 8 months ago

⚠️ This is a pre-release. Testing purposes only. ⚠️

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.7.0...v0.8.0.dev0

keras-hub - v0.7.0

Published by mattdangerw 10 months ago

This release integrates KerasNLP and Kaggle Models. KerasNLP models will now work in Kaggle offline notebooks and all assets will quickly attach to a notebook rather than needing a slow download.

Summary

KerasNLP pre-trained models are now all made available through Kaggle Models. You can see all models currently available in both KerasCV and KerasNLP here. Individual model pages will include example usage and a file browser to examine all available assets for a model preset.

This change will not affect the existing usage of from_preset(). Statement like keras_nlp.models.BertClassifier.from_preset("bert_base_en") will continue to work and download checkpoints from the Kaggle Models hub.

A note on model saving—for saving support across Keras 2 and Keras 3, we recommend using the new Keras saved model format. You can use model.save('path/to/location.keras') for a full model and model.save_weights('path/to/location.weights.h5') for checkpoints. See the Keras saving guide for more details.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.4...v0.7.0

keras-hub - v0.7.0.dev5

Published by mattdangerw 10 months ago

⚠️⚠️
This is a pre-release for our upcoming Kaggle integration and is not yet fit for public consumption.
New pre-trained models are not yet live.
⚠️⚠️

This release integrates KerasNLP and Kaggle Models. KerasNLP models will now work in Kaggle offline notebooks and all assets will quickly attach to a notebook rather than needing a slow download.

Summary

KerasNLP pre-trained models are now all made available through Kaggle Models. You can see all models currently available in both KerasCV and KerasNLP here. Individual model pages will include example usage and a file browser to examine all available assets for a model preset.

This change will not affect the existing usage of from_preset(). Statement like keras_nlp.models.BertClassifier.from_preset("bert_base_en") will continue to work and download checkpoints from the Kaggle Models hub.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.4...v0.7.0.dev5

keras-hub - v0.7.0.dev4

Published by mattdangerw 10 months ago

⚠️⚠️
This is a pre-release for our upcoming Kaggle integration and is not yet fit for public consumption.
New pre-trained models are not yet live.
⚠️⚠️

This release integrates KerasNLP and Kaggle Models. KerasNLP models will now work in Kaggle offline notebooks and all assets will quickly attach to a notebook rather than needing a slow download.

Summary

KerasNLP pre-trained models are now all made available through Kaggle Models. You can see all models currently available in both KerasCV and KerasNLP here. Individual model pages will include example usage and a file browser to examine all available assets for a model preset.

This change will not affect the existing usage of from_preset(). Statement like keras_nlp.models.BertClassifier.from_preset("bert_base_en") will continue to work and download checkpoints from the Kaggle Models hub.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.4...v0.7.0.dev4

keras-hub - v0.7.0.dev3

Published by mattdangerw 11 months ago

⚠️⚠️
This is a pre-release for our upcoming Kaggle integration and is not yet fit for public consumption.
New pre-trained models are not yet live.
⚠️⚠️

keras-hub - v0.6.4

Published by mattdangerw 11 months ago

Summary

This point release simplifies our support for Keras 3 and Keras 2.

  • If Keras 2 is installed, KerasNLP will use Keras 2 and TensorFlow.
  • If Keras 3 is installed, KerasNLP will use Keras 3 and run on any backend.

If you have any issue installing KerasNLP, please open an issue.

What's Changed

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.3...v0.6.4

keras-hub - v0.7.0.dev2

Published by mattdangerw 11 months ago

⚠️⚠️
This is a pre-release for our upcoming Kaggle integration and is not yet fit for public consumption.
New pre-trained models are not yet live.
⚠️⚠️

keras-hub - v0.7.0.dev1

Published by mattdangerw 11 months ago

⚠️⚠️
This is a pre-release for our upcoming Kaggle integration and is not yet fit for public consumption.
New pre-trained models are not yet live.
⚠️⚠️

keras-hub - v0.6.4.dev0

Published by mattdangerw 11 months ago

Summary

This release simplifies our support for Keras 3 and Keras 2.

  • If Keras 2 is installed, KerasNLP will use Keras 2 and TensorFlow.
  • If Keras 3 is installed, KerasNLP will use Keras 3 and run on any backend.

Unlike our previous release, we drop support for using KerasNLP with import keras_core as keras. Keras Core was intended as a preview of our Keras 3 launch, so please switch to Keras 3 instead.

See https://keras.io/getting_started/ for detailed instructions on installing Keras 3. As mentioned in that doc, make sure to install Keras 3 last after installing keras-nlp, tensorflow and other dependencies. This is a temporary step while TensorFlow is still pinning Keras 2.

If you have any issue installing KerasNLP, please open an issue.

What's Changed

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.3...v0.6.4.dev0

keras-hub - v0.6.3

Published by mattdangerw 12 months ago

Summary

This release adds support for running KerasNLP against Keras 3. You can try this today by installing tf-nightly and tensorflow-text-nightly.

pip install keras-nlp
pip uninstall -y tensorflow-text tensorflow keras
pip install tensorflow-text-nightly tf-nightly

Otherwise, this release should be a no-op for all users. No new features, no change in default behavior.

Upcoming changes

After the release of Keras 3, we will drop support for running KerasNLP against the Keras Core package (no more import keras_core as keras), in favor of Keras 3. Keras 3 is the long-term replacement for Keras Core.

What's Changed

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.2...v0.6.3

keras-hub - v0.6.3.dev1

Published by mattdangerw 12 months ago

⚠️ This is a pre-release. Testing purposes only. ⚠️

What's Changed

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.2...v0.6.3.dev1

keras-hub - v0.6.3.dev0

Published by mattdangerw 12 months ago

⚠️ This is a pre-release. Testing purposes only. ⚠️

What's Changed

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.2...v0.6.3.dev0

keras-hub - v0.6.2

Published by mattdangerw about 1 year ago

Summary

  • Support mixed precision on keras-core on all of jax, torch and tensorflow.
  • Add keras_nlp.layers.RotaryEmbedding for rotary embeddings.
  • Add keras_nlp.layers.ReversibleEmbedding to better support tied or untied weights for logit projections.
  • Many bug fixes and improvements.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.1...v0.6.2

keras-hub - v0.6.2.dev0

Published by mattdangerw about 1 year ago

Summary

  • Support mixed precision on keras-core on all of jax, torch and tensorflow.
  • Add keras_nlp.layers.RotaryEmbedding for rotary embeddings.
  • Add keras_nlp.layers.ReversibleEmbedding to better support tied or untied weights for logit projections.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.1...v0.6.2.dev0

keras-hub - v0.6.1

Published by mattdangerw about 1 year ago

With the 0.6.1. release, all remaining models, metrics and samplers have been ported to keras-core. The full KerasNLP API is now available on TensorFlow, PyTorch and Jax (instructions).

Summary

  • FNet and DeBERTa are now multi-backend.
    • All keras_nlp.models.FNetXX and keras_nlp.models.DebertaV3XX symbols work on all backends.
  • keras_nlp.samplers.BeamSampler and keras_nlp.samplers.ContrastiveSampler work on all backends.
  • All keras_nlp.metrics classes work on all backends.
    • For Jax and PyTroch, pass python strings to metrics (as tensor strings are strictly tensorflow).
  • Restored the mask_positions named argument to MaskedLMHead.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.0...v0.6.1

keras-hub - v0.6.1.dev0

Published by mattdangerw about 1 year ago

🚧 Dev release. 🚧

With the 0.6.1. release, all remaining models, metrics and samplers have been ported to keras-core. The full KerasNLP API is now available on TensorFlow, PyTorch and Jax (instructions).

Summary

  • FNet and DeBERTa are now multi-backend. All keras_nlp.models.FNetXX and keras_nlp.models.DebertaV3XX symbols work on all backends.
  • keras_nlp.samplers.BeamSampler and keras_nlp.samplers.ContrastiveSampler now work on all backends.
  • All keras_nlp.metrics classes work on all backends. For Jax and PyTroch, pass python strings to metrics (as tensor strings are strictly tensorflow).
  • Restored the mask_positions named argument to MaskedLMHead.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras-nlp/compare/v0.6.0...v0.6.1.dev0

Package Rankings
Top 34.6% on Pypi.org
Badges
Extracted from project README
contributions welcome
Related Projects
TensorFlow.NET

.NET Standard bindings for Google's TensorFlow for developing, training and deploying Machine Lea...

10 Dec 2018 3,226
data-science-keras

Data science projects with Keras

11 Jul 2017 3
tf-keras

The TensorFlow-specific implementation of the Keras API, which was the default Keras from 2019 to...

03 Sep 2023 62
bert-for-tf2

A Keras TensorFlow 2.0 implementation of BERT, ALBERT and adapter-BERT.

22 May 2019 803
MMdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g...

16 Aug 2017 5,788
keras-cv

Industry-strength Computer Vision workflows with Keras

18 May 2020 969
keras-core

A multi-backend implementation of the Keras API, with support for TensorFlow, JAX, and PyTorch.

09 Apr 2023 1,268
keras-aug

A library that includes pure TF/Keras preprocessing and augmentation layers, providing support fo...

10 Apr 2023 8
autokeras

AutoML library for deep learning

19 Nov 2017 9,102
keras

Deep Learning for humans

28 Mar 2015 60,873
keras-tuner

A Hyperparameter Tuning Library for Keras

06 Jun 2019 2,831
ktrain

ktrain is a Python library that makes deep learning and AI more accessible and easier to apply

06 Feb 2019 1,226
tensorspace

Neural network 3D visualization framework, build interactive and intuitive model in browsers, sup...

22 Jul 2018 5,041
frugally-deep

Header-only library for using Keras (TensorFlow) models in C++.

15 Jul 2016 1,045
keras-text

Text Classification Library in Keras

27 Aug 2017 420