KerasNLP
A pretrained modeling library for Keras 3 offering simple, flexible, and fast access to models for text, image, and audio tasks.
What is KerasNLP?
KerasHub is a pretrained modeling library that provides Keras 3 implementations of popular model architectures, paired with pretrained checkpoints available on Kaggle Models. It solves the problem of accessing and fine-tuning state-of-the-art models for text, image, and audio tasks with a simple and flexible API. Developers can use it for tasks like classification, generation, and more, leveraging multi-framework support and scalable training options.
Machine learning engineers and researchers familiar with Keras who need quick access to pretrained models for prototyping, fine-tuning, or deploying models across JAX, TensorFlow, or PyTorch backends.
Developers choose KerasHub for its seamless integration with the Keras API, multi-framework compatibility from a single model definition, and access to a curated hub of pretrained models, reducing the complexity of implementing advanced deep learning models.
Overview
Pretrained model hub for Keras 3.
Use Cases
Best For
- Fine-tuning pretrained models for custom text classification tasks
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
