TensorFlow, JAX, Gemma, MediaPipe, DeepMind research
An Open Source Machine Learning Framework for Everyone
An open-source AI agent that brings the power of Gemini directly into your terminal.
TensorFlow code and pre-trained models for BERT
Gemma open-weight LLM library, from Google DeepMind
Sec-Gemini v1 is a cutting-edge AI model designed to enhance cybersecurity capabilities and empower defenders in the ongoing battle against cyber threats.
An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Dramatron uses large language models to generate coherent scripts and screenplays.
An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
torchax is a PyTorch frontend for JAX. It gives JAX the ability to author JAX programs using familiar PyTorch syntax. It also provides JAX-Pytorch interoperability, meaning, one can mix JAX & Pytorch syntax together when authoring ML programs, and run it in every hardware JAX can run.
A library for generative social simulation
A collection of sample agents built with Agent Development Kit (ADK)
Library for reading and processing ML training data.
Temporian is an open-source Python library for preprocessing ⚡ and feature engineering 🛠 temporal data 📈 for machine learning applications 🤖
An open-source, code-first toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Shared repository for open-sourced projects from the Google AI Language team.
An opensource text-to-speech (TTS) voice building tool
Play with neural networks!
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!
Learning to Learn in TensorFlow
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
High-efficiency floating-point neural network inference operators for mobile, server, and Web
Scenic: A Jax Library for Computer Vision Research and Beyond
OO for LLMs
Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
lightweight, standalone C++ inference engine for Google's Gemma models.
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research
Unsupervised text tokenizer for Neural Network-based text generation.
StarCraft II Learning Environment
DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.
Flax is a neural network library for JAX that is designed for flexibility.
Tracking Any Point (TAP)
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.
An open-source Python framework for hybrid quantum-classical machine learning.
A customisable 3D platform for agent-based AI research
TensorFlow-based neural network library
Convolutional neural network model for video classification trained on the Kinetics dataset.
This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.
An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
A flexible, high-performance serving system for machine learning models
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
Google Research
Official JAX implementation of MAGVIT: Masked Generative Video Transformer
A compiler for APIs described by the OpenAPI Specification with plugins for code generation and other API support tasks.
Check out the new game server:
TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
Massively parallel rigidbody physics simulation on accelerator hardware.
A library of reinforcement learning components and agents
A JAX research toolkit for building, editing, and visualizing neural networks.
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Trax — Deep Learning with Clear Code and Speed
RL research on Android devices.
A playbook for systematically maximizing the performance of deep learning models.
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Fast and Easy Infinite Neural Networks in Python
Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.
Original Implementation of Prompt Tuning from Lester, et al, 2021
Open weights language model from Google DeepMind, based on Griffin.
Useful extra functionality for TensorFlow 2.x maintained by SIG-addons
This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
Efficient Batched Reinforcement Learning in TensorFlow
[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.
A general-purpose encoder-decoder framework for Tensorflow
SLING - A natural language frame semantics parser
A Configurable Recommender Systems Simulation Platform
A suite of test scenarios for multi-agent reinforcement learning.
DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (DQN) agent.
Data compression in TensorFlow
Swift for TensorFlow
Go SDK for Google Generative AI
JAX-based neural network library
Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication
Library for training machine learning models with privacy for training data
Monte Carlo tree search in JAX
Learning to Rank in TensorFlow
A library to train, evaluate, interpret, and productionize decision forest models such as Random Forest and Gradient Boosted Decision Trees.
The Zebrafish Activity Prediction Benchmark measures progress on the problem of predicting cellular-resolution neural activity throughout an entire vertebrate brain.
A platform for managing machine learning experiments
Budou is an automatic organizer tool for beautiful line breaking in CJK (Chinese, Japanese, and Korean).
Modular, scalable library to train ML models
Transformers for Longer Sequences
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
Second Order Optimization and Curvature Estimation with K-FAC in JAX.
official code for "Large Language Models as Optimizers"
A lightweight memory allocator for hardware-accelerated machine learning
Emoji Scavenger Hunt is an experiment that leverages the power of neural networks and your phone’s camera to identify the real world versions of the emojis we use every day.
A dataset of datasets for learning to learn from few examples
Infrastructure for Machine Learning Guided Optimization (MLGO) in LLVM.
Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields".
QKeras: a quantization deep learning library for Tensorflow Keras
Deep learning with dynamic computation graphs in TensorFlow
A library for transfer learning by reusing parts of TensorFlow models.
This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.
This repository is deprecated and will be archived
Experiments towards neural network theorem proving
WebGL-accelerated ML // linear algebra // automatic differentiation for JavaScript.
Library for exploring and validating machine learning data
TensorFlow documentation
Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.
TFX is an end-to-end platform for deploying production ML pipelines
Unsupervised Data Augmentation (UDA)
Build Graph Nets in Tensorflow
Probabilistic reasoning and statistical analysis in TensorFlow
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.
A Graph Neural Network Library in Jax
Swift for TensorFlow Deep Learning Library
[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...
A Lightweight LLM Post-Training Library
Google AI Studio Starter Apps
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
A collection of infrastructure and tools for research in neural network interpretability.
Distributed machine learning infrastructure for large-scale robotics research
An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations
SCAAML: Side Channel Attacks Assisted with Machine Learning
DiffSeg is an unsupervised zero-shot segmentation method using attention information from a stable-diffusion model. This repo implements the main DiffSeg algorithm and additionally includes an experimental feature to add semantic labels to the masks based on a generated caption.
Restoring and attributing ancient texts using deep neural networks
TensorFlow Reinforcement Learning
Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"
A Python interface for reinforcement learning environments
Fast and flexible AutoML with learning guarantees.
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Rust language bindings for TensorFlow
Spriteworld: a flexible, configurable python-based reinforcement learning environment
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)
[CoRL '23] Dexterous piano playing with deep reinforcement learning.
Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
Long Range Arena for Benchmarking Efficient Transformers
Official implementation for "Break-A-Scene: Extracting Multiple Concepts from a Single Image" [SIGGRAPH Asia 2023]
A WebGL accelerated JavaScript library for training and deploying ML models.
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
Fast and accurate AI powered file content types detection
Lingvo