you.com's framework for evaluating deep research systems.

Weaviate connector for Apache Spark

Resources for the "Evaluating the Factual Consistency of Abstractive Text Summarization" paper

Conditional Transformer Language Model for Controllable Generation

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Open clone of OpenAI's unreleased WebText dataset scraper. This version uses pushshift.io files instead of the API for speed.

PyTorch original implementation of Cross-lingual Language Model Pretraining.

Library to scrape and clean web pages to create massive datasets.

Lingvo

The Natural Language Decathlon: A Multitask Challenge for NLP

A general-purpose encoder-decoder framework for Tensorflow

Tensors and Dynamic neural networks in Python with strong GPU acceleration

An Open Source Machine Learning Framework for Everyone