An experiment in feature observability for streaming engines.

An in-flight gRPC server for ML feature streams.

Large Language Model Text Generation Inference

An extensible framework for webscraping

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

A Python library for working with and comparing language codes.

A collection of design patterns/idioms in Python

Pretty print the output of python stdlib `ast.parse`.

Amazon SageMaker Debugger provides functionality to save tensors during training of machine learning jobs and analyze those tensors

A curated list of references for MLOps

A library for training and deploying machine learning models on Amazon SageMaker

Python Packages as AWS Lambda Layers

Python composable command line interface toolkit

parallel graph management and execution in heterogeneous computing

Toolkit to obtain and preprocess German text corpora, train models and evaluate them with generated testsets. Built with Gensim and Tensorflow.

this repository accompanies the book "Grokking Deep Learning"

Automatic Diacritic Restoration of Yorùbá language Text

Colabs for ML Day Tokyo

Named Entity Recognition using multilayered bidirectional LSTM

Name Entity Recognition Tool for Hindi Language

Anonymization of legal cases (Fr) based on Flair embeddings

The best way to write secure and reliable applications. Write nothing; deploy nowhere.

Framework for building complex recurrent neural networks with Keras

Unsupervised Neural Machine Translation from West African Pidgin (Creole) to English without a single parallel sentence

Spanish word embeddings computed with different methods and from different corpora

Yorùbá language training text for NLP, ASR and TTS tasks

Stand-alone language identification system