keras-nlp
best-of-ml-python
keras-nlp | best-of-ml-python | |
---|---|---|
2 | 16 | |
701 | 15,364 | |
3.1% | 0.9% | |
9.5 | 7.8 | |
3 days ago | 8 days ago | |
Python | Python | |
Apache License 2.0 | Creative Commons Attribution Share Alike 4.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
keras-nlp
-
Keras 3.0
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...
-
Keras Core: Keras for TensorFlow, Jax, and PyTorch
Yes, you can check out KerasCV and KerasNLP which host pretrained models like ResNet, BERT, and many more. They run on all backends as of the latest releases (today), and converting them to be backend-agnostic was pretty smooth! It took a couple of weeks to convert the whole packages.
https://github.com/keras-team/keras-nlp/tree/master/keras_nl...
best-of-ml-python
-
Ask HN: How to get back into AI?
For Python, here's a nice compilation: https://github.com/ml-tooling/best-of-ml-python/blob/main/RE...
- Best-Of Machine Learning with Python
-
Questions regarding Job Requirements for data analyst to data science transition?
You will need numpy, scipy, pandas, scikit-learn, Keras/tensorflow/pytorch, xgboost and many many many others. See this list for example.
- Awesome list of ML
- Are there any speech recognition modules so I can write one and do not have to rely on google and the likes?
-
Learning opencv
Take a look at this list on github. It has a pretty comprehensive list of python image libraries.
- Best-of Machine Learning with Python
- 🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
What are some alternatives?
keras-core - A multi-backend implementation of the Keras API, with support for TensorFlow, JAX, and PyTorch.
Awesome-WAF - 🔥 Web-application firewalls (WAFs) from security standpoint.
MAGIST-Algorithm - Multi-Agent Generally Intelligent Simultaneous Training Algorithm for Project Zeta
ktrain - ktrain is a Python library that makes deep learning and AI more accessible and easier to apply
i6_experiments
dtale - Visualizer for pandas data structures
Spectrum - Spectrum is an AI that uses machine learning to generate Rap song lyrics
ffcv - FFCV: Fast Forward Computer Vision (and other ML workloads!)
returnn - The RWTH extensible training framework for universal recurrent neural networks
awesome-python - An opinionated list of awesome Python frameworks, libraries, software and resources.
keras-cv - Industry-strength Computer Vision workflows with Keras
kmodes - Python implementations of the k-modes and k-prototypes clustering algorithms, for clustering categorical data