Google Research

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

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

Deep universal probabilistic programming with Python and PyTorch

BertViz: Visualize Attention in Transformer Models

Open Source Neural Machine Translation and (Large) Language Models in PyTorch

Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.

A unified, comprehensive and efficient recommendation library

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

A library for mechanistic interpretability of GPT-style language models

The hub for EleutherAI's work on interpretability and learning dynamics

Python library for creating PEG parsers

Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

pyltp: the python extension for LTP

This is a repository of public data sources for Recommender Systems (RS).

SPLADE: sparse neural search (SIGIR21, SIGIR22)

Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)

High-accuracy NLP parser with models for 11 languages.

A Python 3 compatible version of goose http://goose3.readthedocs.io/en/latest/index.html

A multi-task learning example for the paper https://arxiv.org/abs/1705.07115

Crawl BookCorpus

All-in-one text de-duplication

Code to obtain the CNN / Daily Mail dataset (non-anonymized) for summarization

A collection of datasets that pair questions with SQL queries.

PySwip is a Python-Prolog interface that enables querying SWI-Prolog in your Python programs.

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems