TensorFlow code and pre-trained models for BERT

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

💫 Industrial-strength Natural Language Processing (NLP) in Python

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

NLTK Source

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

Context aware, pluggable and customizable data protection and de-identification SDK for text and images

Home of StarCoder2!

Python port of Moses tokenizer, truecaser and normalizer

The Programmable Cypher-based Neuro-Symbolic AGI that lets you program its behavior using Graph-based Prompt Programming: for people who want AI to behave as expected

OpenAPI specification of the DeepL API