Large language model

Llama 2: open source, free for research and commercial use

We're unlocking the power of these large language models. Our latest version of Llama – Llama 2 – is now accessible to individuals, creators, researchers, and businesses so they can experiment, innovate, and scale their ideas responsibly.

Download the model

Available as part of the Llama 2 release

Get started guide

With each model download you'll receive:

Model code
Model weights
README (user guide)
Responsible Use Guide
License
Acceptable use policy
Model card

Technical specifications

Llama 2 was pretrained on publicly available online data sources.
The fine-tuned model, Llama Chat, leverages publicly available instruction datasets and over 1 million human annotations.

Read the paper

Inside the model

Llama 2 models are trained on 2 trillion tokens and have double the context length of Llama 1. Llama Chat models have additionally been trained on over 1 million new human annotations.

Llama 2 was trained on 40% more data than Llama 1 graphic

Benchmarks

Llama 2 pretrained models are trained on 2 trillion tokens, and have double the context length than Llama 1. Its fine-tuned models have been trained on over 1 million human annotations.

Safety and helpfulness

Reinforcement learning from human feedback

Llama Chat uses reinforcement learning from human feedback to ensure safety and helpfulness.

Training Llama Chat: Llama 2 is pretrained using publicly available online data. An initial version of Llama Chat is then created through the use of supervised fine-tuning. Next, Llama Chat is iteratively refined using Reinforcement Learning from Human Feedback (RLHF), which includes rejection sampling and proximal policy optimization (PPO).

Getting started guide

Unlock the full potential of Llama 2 with our developer documentation. The Getting started guide provides instructions and resources to start building with Llama 2.

The license

Our model and weights are licensed for both researchers and commercial entities, upholding the principles of openness. Our mission is to empower individuals, and industry through this opportunity, while fostering an environment of discovery and ethical AI advancements.

Responsible use

Like all LLMs, Llama 2 is a new technology that carries potential risks with use. Testing conducted to date has not — and could not — cover all scenarios. In order to help developers address these risks, we have created the Responsible Use Guide. More details can be found in the Research paper and Model card.

Download the model

Get Llama 2 now: complete the download form via the link below.
By submitting the form, you agree to Meta's privacy policy.

Get started

Partnerships

Our global partners and supporters

We have a broad range of supporters around the world who believe in our open approach to today’s AI — companies that have given early feedback and are excited to build with Llama 2, cloud providers that will include the model as part of their offering to customers, researchers committed to doing research with the model, and people across tech, academia, and policy who see the benefits of Llama and an open platform as we do.

Statement of support for Meta’s open approach to today’s AI

“We support an open innovation approach to AI. Responsible and open innovation gives us all a stake in the AI development process, bringing visibility, scrutiny and trust to these technologies. Opening today’s Llama models will let everyone benefit from this technology.”

See all signatures

Jonathan Abrahamson

Chief Product and Digital Officer,
Deutsche Telekom

Wole Abu

Chief Executive Officer,
Liquid Intelligent Technologies Nigeria

Farooq Adam

Co-Founder,
Fynd

Carolina Aguerre

Professor (PhD),
CETYS
UCU

Darlington Akogo

Founder and CEO,
MinoHealth AI Labs

Teki Akuetteh

Founder and Executive Director,
Africa Digital Rights Hub

Omar Sultan Al Olama

Minister of State for Artificial Intelligence, Digital Economy, and Remote Work Applications and Director General of the Prime Minister’s Office,
United Arab Emirates

Saeed Aldhaheri

Director,
Center for Futures Studies,
University of Dubai

Marc Andreessen

Co-Founder & General Partner,
Andreessen Horowitz

Guido Appenzeller

Advisor,
Andreessen Horowitz

Nikesh Arora

CEO,
Palo Alto Networks

Jamal Atif

Professor,
Université Paris Dauphine PSL-CNRS,
fellow PRAIRIE

Tomás Balmaceda

Professor (PhD),
IIF / SADAF CONICET

Dr. Pushpak Bhattacharyya

Professor of Computer Science and Engineering,
Indian Institute of Technology Bombay

Pradipta Biswas

Associate Professor,
Indian Institute of Science,
Bangalore

Matt Bornstein

Partner,
Andreessen Horowitz

John Borthwick

CEO,
Betaworks

Daniela Braga

Founder and CEO,
Defined.AI

Ian Buck

VP Hyperscaler & HPC Computing,
NVIDIA

Martin Casado

General Partner,
Andreessen Horowitz

Edwin Chen

CEO,
Surge AI

Julien Chaumond

CTO,
Hugging Face

Ron Conway

Founder,
SV Angel

Topher Conway

Managing Partner,
SV Angel

Jimi Daodu

CEO,
Vault Hill

Professor Trevor Darrell

Program Director BAIR,
University of California – Berkeley

Shashi Deshetti

CTO,
Factly

Francis Fong

Honorary President,
Hong Kong Information Technology Federation

Eric Gaussier

Director of the Grenoble Multidisciplinary Institute in Artificial Intelligence (MIAI),
Joseph Fourier University

Lex Fridman

Research Scientist,
MIT

Daniel Getachew

Founder and CEO,
Guzo Technologies

Joseph Gonzalez

Associate Professor and Co-Director RISE Lab,
University of California – Berkeley

Miguel González Mendoza

Former President,
Mexican Artificial Intelligence Society

Paul Graham

Founding Partner,
Y Combinator

Diane Greene

Chair Emeritus,
MIT

Lan Guan

Global Data & AI Lead,
Accenture

Alok Gupta

Head of Artificial Intelligence & Machine Learning,
DoorDash

Mu Han

Chief Development Officer,
Zoom

Dr. Sherif Hashem

Senior Member,
IEEE

Peter Hebert

Co-Founder and Managing Partner,
Lux Capital

Bill Higgins

Director
IBM watsonx Platform Engineering and Chair,
IBM Open Innovation Community,
IBM

Reid Hoffman

Partner,
Greylock

Ben Horowitz

Co-Founder & General Partner,
Andreessen Horowitz

Drew Houston

CEO,
Dropbox

Yukai Huang

Chief Technology Officer,
DataOcean AI

Luis Ángel Hurtado Razo

Disinformation Expert and Academic at the Faculty of Political Science and Communication,
UNAM (National University of Mexico)

Pierre Kafunda

Professor of Computer Science,
University of Kinshasa

Professor Sham Kakade

Co-Director,
Kempner Institute
Harvard University

Fraser Kelton

Partner,
Spark Capital and Former Head of Product
OpenAI

Muhammad Zohaib Khan

Chairman,
P@sha (Pakistan IT Industry Association)

Nazarius Kilama

President,
Internet Society – Tanzania

Zsolt Kira

Assistant Professor,
Georgia Institute of Technology

Professor Jerry Kponyo

PI and Scientific Director Responsible Artificial Intelligence Lab,
KNUST

Bernard Laurendeau

Managing Partner,
Laurendeau & Associates | CEO at Arifpay

Sam Lessin

Founder,
Slow Ventures

Ke Li

Chief Operation Officer,
DataOcean AI

Wei Li

VP and GM AI & Analytics at Intel,
Intel

Laurence Liew

Director,
AI Innovation,
AI Singapore

Jessica Livingston

Founding Partner,
Y Combinator

Tobi Lutke

CEO,
Shopify

Durga Malladi

Senior Vice President and General Manager of Technology
Planning and Edge Solutions Businesses,
Qualcomm Technologies
Inc.

Juliano Maranhão

Professor,
University of São Paulo Law School; Lawgorithm Institute; Legal Grounds Institute; Brazilian Senate AI Experts Committee

Vukosi Marivate

Professor – ABSA Chair of Data Science,
University of Pretoria

Amjad Masad

CEO and Founder,
Replit

Jordan Masakuna

Professor of Computer Science,
University of Kinshasa

Marco Mascorro

AI Research Partner,
Andreessen Horowitz

Brad McCredie

Corporate Vice President Data Center GPU and Accelerated Processing,
AMD

Maxence Melo

CEO,
Jamii Forums

Xiangrui Meng

Machine Learning Lead,
Databricks

Francesco Milleri

Chairman and CEO,
EssilorLuxottica

Xavier Niel

Founder,
Iliad

Dr. Victor Odumuyiwa

Acting Director,
NITDA IT Hub University of Lagos

Ridwan Oloyede

Co-Founder,
Tech Hive Advisory

Vijay Parthasarathy

Head of AI Engineering,
Zoom

Agustina Perez Comenale

Professor,
Universidad de Montevideo

Jean Ponce

Scientific Director,
PRAIRIE
and Professor
École normale supérieure – PSL

Pablo Pruneda

AI & Law Research Coordinator,
IIJ- UNAM (Legal Institute
National University of Mexico)

Rajko Radovanovic

Partner,
Andreessen Horowitz

Dan Rose

Chairman,
Coatue Ventures

Benoit Sagot

Research Director,
Inria
Fellow PRAIRIE

Fadi Salem

Director of Policy Research,
MBR School of Government

Velchamy Sankarlingam

President of Product and Engineering,
Zoom

Elliot Schrage

Policy Fellow
Former Facebook VP of Comms and Public Policy,
Open DP Project

Beerud Sheth

CEO,
Gupshup

Richa Singh

Professor,
Indian Institute of Technology Jodhpur

Professor Pete Stone

Truchard Foundation Chair in Computer Science,
University of Texas at Austin

Garry Tan

President and CEO,
Y Combinator

Mayank Vatsa

Professor,
Indian Institute of Technology Jodhpur

Dr. Wairagala Wakabi

Executive Director,
CIPESA

Alexandr Wang

CEO and Founder,
Scale AI

Chris Wanstrath

Co-Founder and Former CEO,
GitHub

Patrick Wendell

Co-Founder,
Databricks

Josh Wolfe

Co-Founder and Managing Partner,
Lux Capital

Eric Xing

Professor Computer Science; President,
Carnegie Mellon University; Mohamed bin Zayed University of AI

Tony Xu

CEO and Co-Founder,
DoorDash

Byung-Tak Zhang

Director,
AI Institute of Seoul National University (AIIS)

Daniel Castaño

Professor PhD, Founder,
Universidad del Externado, Mokzy

Matthew Zeiler

Founder and CEO,
Clarifai

Responsibility

We’re committed to building responsibly

To promote a responsible, collaborative AI innovation ecosystem, we’ve established a range of resources for all who use Llama 2: individuals, creators, developers, researchers, academics, and businesses of any size.

Responsible Use Guide

The Responsible Use Guide is a resource for developers that provides best practices and considerations for building products powered by large language models (LLMs) in a responsible manner, covering various stages of development from inception to deployment.

Responsible Use Guide

Safety Red-teaming

Llama Chat has undergone testing by external partners and internal teams to identify performance gaps and mitigate potentially problematic responses in chat use cases. We're committed to ongoing red-teaming to enhance safety and performance.

Open Innovation AI Research Community

We're launching a program for academic researchers, designed to foster collaboration and knowledge-sharing in the field of artificial intelligence. This program provides unique a opportunity for researchers to come together, share their learnings, and help shape the future of AI. By joining this community, participants will have the chance to contribute to a research agenda that addresses the most pressing challenges in the field, and work together to develop innovative solutions that promote responsible and safe AI practices. We believe that by bringing together diverse perspectives and expertise, we can accelerate the pace of progress in AI research.

Learn more

Llama Impact Grants

We want to activate the community of innovators who aspire to use Llama to solve hard problems. We are launching the grants to encourage a diverse set of public, non-profit, and for-profit entities to use Llama 2 to address environmental, education and other important challenges. The grants will be subject to rules which will be posted here prior to the grants start.

Learn more

Generative AI Community Forum

We think it’s important that our product and policy decisions around generative AI are informed by people and experts from around the world. In support of this belief, we created a forum to act as a governance tool and resource for the community. It brings together a representative group of people to discuss and deliberate on the values that underpin AI, LLM and other new AI technologies.

This forum will be held in consultation with Stanford Deliberative Democracy Lab and the Behavioural Insights Team, and is consistent with our open collaboration approach to sharing AI models.

Learn more

Join us on our AI journey

If you’d like to advance AI with us, visit our Careers page to discover more about AI at Meta.

See open positions

Llama 2

Frequently asked questions

Get answers to Llama 2 questions in our comprehensive FAQ page—from how it works, to how to use it, integrations, and more.

See all FAQs

Does Llama 2 support other languages outside of English?

The model was primarily trained on English with a bit of additional data from 27 other languages (for more information, see Table 10 on page 20 of the Llama 2 paper). We do not expect the same level of performance in these languages as in English. You’ll find the full list of languages referenced in the research paper. You can look at some of the community lead projects to fine-tune Llama 2 models to support other languages. (eg. link)

Can you run the Llama-7B model on Windows and/or macOS?

The vanilla model shipped in the repository does not run on Windows and/or macOS out of the box. There are some community led projects that support running Llama on Mac, Windows, iOS, Android or anywhere (e.g llama cpp, MLC LLM, and Llama 2 Everywhere). You can also find a work around at this issue based on Llama 2 fine tuning.

How is the architecture of the v2 different from the one of the v1 model?

Some differences between the two models include:

Llama 1 released 7, 13, 33 and 65 billion parameters while Llama 2 has7, 13 and 70 billion parameters
Llama 2 was trained on 40% more data
Llama2 has double the context length
Llama2 was fine tuned for helpfulness and safety
Please review the research paper and model cards (llama 2 model card, llama 1 model card) for more differences.

Resources

Explore more on Llama 2

Discover more about Llama 2 here — visit our resources, ranging from our research paper, how to get access, and more.

Github

Open Innovation AI Research Community

Getting started guide

AI at Meta blog

Responsible Use Guide

Research paper