keras-nlp
d2l-en
| keras-nlp | d2l-en | |
|---|---|---|
| 2 | 6 | |
| 701 | 21,759 | |
| 3.1% | 1.6% | |
| 9.5 | 8.5 | |
| 3 days ago | 18 days ago | |
| Python | Python | |
| Apache License 2.0 | GNU General Public License v3.0 or later |
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...
d2l-en
- which book to chose for deep learning :lan Goodfellow or francois chollet
- d2l-en: Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.
-
How to pre-train BERT on different objective tasks using HuggingFace
There might is bert library for pre-train bert model in huggingface, But I suggestion that you train bert model in native pytorch to understand detail, Limu's course is recommended for you
-
The Transformer in Machine Translation
GitHub's article on Dive into Deep Learning
- D2l-En
-
I created a way to learn machine learning through Jupyter
There are actually some online books and courses built on Jupyter Notebook ([Dive to Deep Learning Book](https://github.com/d2l-ai/d2l-en) for example). However yours is more detail and could really helps beginners.
What are some alternatives?
keras-core - A multi-backend implementation of the Keras API, with support for TensorFlow, JAX, and PyTorch.
Pytorch-UNet - PyTorch implementation of the U-Net for image semantic segmentation with high quality images
MAGIST-Algorithm - Multi-Agent Generally Intelligent Simultaneous Training Algorithm for Project Zeta
DeepADoTS - Repository of the paper "A Systematic Evaluation of Deep Anomaly Detection Methods for Time Series".
i6_experiments
TF-Watcher - Monitor your ML jobs on mobile devices📱, especially for Google Colab / Kaggle
Spectrum - Spectrum is an AI that uses machine learning to generate Rap song lyrics
99-ML-Learning-Projects - A list of 99 machine learning projects for anyone interested to learn from coding and building projects
returnn - The RWTH extensible training framework for universal recurrent neural networks
imbalanced-regression - [ICML 2021, Long Talk] Delving into Deep Imbalanced Regression
keras-cv - Industry-strength Computer Vision workflows with Keras
petastorm - Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch, and PySpark and can be used from pure Python code.