Meta

Meta
FacebookXYouTubeLinkedIn
Documentation
OverviewModels Getting the Models Running Llama How-To Guides Integration Guides Community Support

Community
Community StoriesOpen Innovation AI Research CommunityLlama Impact Grants

Resources
CookbookCase studiesVideosAI at Meta BlogMeta NewsroomFAQPrivacy PolicyTermsCookies

Llama Protections
OverviewLlama Defenders ProgramDeveloper Use Guide

Documentation
Overview
Models
Getting the Models
Running Llama
How-To Guides
Integration Guides
Community Support
Community
Community Stories
Open Innovation AI Research Community
Llama Impact Grants
Resources
Cookbook
Case studies
Videos
AI at Meta Blog
Meta Newsroom
FAQ
Privacy Policy
Terms
Cookies
Llama Protections
Overview
Llama Defenders Program
Developer Use Guide
Documentation
Overview
Models
Getting the Models
Running Llama
How-To Guides
Integration Guides
Community Support
Community
Community Stories
Open Innovation AI Research Community
Llama Impact Grants
Resources
Cookbook
Case studies
Videos
AI at Meta Blog
Meta Newsroom
FAQ
Privacy Policy
Terms
Cookies
Llama Protections
Overview
Llama Defenders Program
Developer Use Guide
Documentation
Overview
Models
Getting the Models
Running Llama
How-To Guides
Integration Guides
Community Support
Community
Community Stories
Open Innovation AI Research Community
Llama Impact Grants
Resources
Cookbook
Case studies
Videos
AI at Meta Blog
Meta Newsroom
FAQ
Privacy Policy
Terms
Cookies
Llama Protections
Overview
Llama Defenders Program
Developer Use Guide
Skip to main content
Meta
Models & Products
Docs
Community
Resources
Llama API
Download models

Table Of Contents

Overview
Models
Llama 4
Llama Guard 4 (New)
Llama 3.3
Llama 3.2
Llama 3.1
Llama Guard 3
Llama Prompt Guard 2 (New)
Other models
Getting the Models
Meta
Hugging Face
Kaggle
1B/3B Partners
405B Partners
Running Llama
Linux
Windows
Mac
Cloud
How-To Guides
Fine-tuning
Quantization
Prompting
Validation
Vision Capabilities
Responsible Use
Integration Guides
LangChain
Llamalndex
Community Support
Resources

Overview
Models
Llama 4
Llama Guard 4 (New)
Llama 3.3
Llama 3.2
Llama 3.1
Llama Guard 3
Llama Prompt Guard 2 (New)
Other models
Getting the Models
Meta
Hugging Face
Kaggle
1B/3B Partners
405B Partners
Running Llama
Linux
Windows
Mac
Cloud
How-To Guides
Fine-tuning
Quantization
Prompting
Validation
Vision Capabilities
Responsible Use
Integration Guides
LangChain
Llamalndex
Community Support
Resources
Model Cards & Prompt formats

Meta Llama 2

Model Card

You can find details about this model in the model card.

Special Tokens used with Meta Llama 2

<s></s>: These are the BOS and EOS tokens from SentencePiece. When multiple messages are present in a multi turn conversation, they separate them, including the user input and model response.
[INST][/INST]: These tokens enclose user messages in multi turn conversations.
<<SYS>><</SYS>>: These enclose the system message.

Meta Llama 2

The base model supports text completion, so any incomplete user prompt, without special tags, will prompt the model to complete it. The tokenizer provided with the model will include the SentencePiece beginning of sequence (BOS) token (<s>) if requested. Review this code for details.
<s>{{ user_prompt }}

Meta Llama 2 Chat

Code to produce this prompt format can be found here. The system prompt is optional.

Single message instance with optional system prompt.

<s>[INST] <<SYS>>
{{ system_prompt }}
<</SYS>>

{{ user_message }} [/INST]

Multiple user and assistant messages example.

<s>[INST] <<SYS>>
{{ system_prompt }}
<</SYS>>

{{ user_message_1 }} [/INST] {{ model_answer_1 }} </s>
<s>[INST] {{ user_message_2 }} [/INST]
On this page
Meta Llama 2
Model Card
Special Tokens used with Meta Llama 2
Meta Llama 2
Meta Llama 2 Chat