Keras 3.0

This page summarizes the projects mentioned and recommended in the original post on news.ycombinator.com

Our great sponsors
  • WorkOS - The modern API for authentication & user identity.
  • InfluxDB - Power Real-Time Data Analytics at Scale
  • LearnThisRepo.com - Learn 300+ open source libraries for free using AI.
  • cupy

    NumPy & SciPy for GPU

    I did not expect anything interesting, but this is actually cool.

    > A full implementation of the NumPy API. Not something "NumPy-like" — just literally the NumPy API, with the same functions and the same arguments.

    I suppose it's like https://cupy.dev/

  • ivy

    The Unified AI Framework

    See also https://github.com/unifyai/ivy which I have not tried but seems along the lines of what you are describing, working with all the major frameworks

  • WorkOS

    The modern API for authentication & user identity. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  • Keras

    Deep Learning for humans

    All breaking changes are listed here: https://github.com/keras-team/keras/issues/18467

    You can use this migration guide to identify and fix each of these issues (and further, making your code run on JAX or PyTorch): https://keras.io/guides/migrating_to_keras_3/

  • keras-nlp

    Modular Natural Language Processing workflows with Keras

    Yes, Keras can be used to build LLMs. In fact this is one of the main use cases.

    There are some tutorials about how to do it "from scratch", like this: https://keras.io/examples/nlp/neural_machine_translation_wit...

    Otherwise, if you want to reuse an existing LLM (or just see how a large one would be implemented in practice) you can check out the models from KerasNLP. For instance, this is BERT, basically just a stack of TransformerEncoders. https://github.com/keras-team/keras-nlp/blob/master/keras_nl...

NOTE: The number of mentions on this list indicates mentions on common posts plus user suggested alternatives. Hence, a higher number means a more popular project.

Suggest a related project

Related posts