A modular graph-based Retrieval-Augmented Generation (RAG) system

Turns Data and AI algorithms into production-ready web applications in no time.

A high-throughput and memory-efficient inference and serving engine for LLMs

Official inference library for Mistral models

A modular recommendation system that allows the selection of different components to be combined into a new recommender.

Geometric Computer Vision Library for Spatial AI

Platform to run interactive Reinforcement Learning agents in a Minecraft Server

Mamba SSM architecture

[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

A toolkit for auto-generation of OpenAI Gym environments from RDDL description files.

A toolkit for working with RDDL domains in Python3.

The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization

PyTorch implementations of deep reinforcement learning algorithms and environments

The implementation of LSTM-TD3.

Synthetic Data Generation for mixed-type, multivariate time series.

High throughput synchronous and asynchronous reinforcement learning

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Google's Operations Research tools:

🥈78th place in Riiid Answer Correctness Prediction competition🥈

🎖️ 4th place solution in the Feedback Prize Competition🎖️

A Python framework for program synthesis with a focus on Automated Machine Learning.

Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.

Using artificial intelligence and genetic algorithms to automatically write programs. Tutorial: https://www.primaryobjects.com/cms/article149

The Abstraction and Reasoning Corpus

A curated list of papers related to program synthesis, program induction, program execution, program and code repair, and programmatic reinforcement learning.

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

Code for ACL 2020 paper: "Extractive Summarization as Text Matching"

The largest geonames database of counties, regions and cities with translations.

super fast cpp implementation of longest common subsequence/substring

Free MLOps course from DataTalks.Club