Llama-Guard-3-8B
Llama Guard 3 improves content safety classification with high accuracy and supports multiple languages.
MAX Models are popular open-source models converted to MAX’s native graph format. Anything with the label is either SOTA or being worked on. Learn more about MAX Models.
Browse all MAX Models
MAX GITHUB
Modular / MAX
BASE MODEL
meta-llama
meta-llama/Llama-Guard-3-8B
QUANTIZED BY
legraphista
legraphista/Llama-Guard-3-8B-IMat-GGUF
QUESTIONS ABOUT THIS MODEL?
Leave a comment
PROBLEMS WITH THE CODE?
File an Issue
TAGS
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
Choose Version
(2 versions)
Install our
magicpackage manager:curl -ssL https://magic.modular.com/ | bashThen run the
sourcecommand that's printed in your terminal.Install Max Pipelines in order to run this model.
magic global install max-pipelines && magic global updateStart a local endpoint for Llama-Guard-3/8B-Q6_K:
max-pipelines serve --huggingface-repo-id=meta-llama/Llama-Guard-3-8B \ --weight-path=legraphista/Llama-Guard-3-8B-IMat-GGUF/Llama-Guard-3-8B.Q6_K.ggufThe endpoint is ready when you see the URI printed in your terminal:
Server ready on http://0.0.0.0:8000 (Press CTRL+C to quit)
Now open another terminal to send a request using
curl:curl -N http://0.0.0.0:8000/v1/chat/completions -H "Content-Type: application/json" -d '{ "model": "meta-llama/Llama-Guard-3-8B", "stream": true, "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Who won the World Series in 2020?"} ] }' | grep -o '"content":"[^"]*"' | sed 's/"content":"//g' | sed 's/"//g' | tr -d ' ' | sed 's/\n//g'
🎉 Hooray! You’re running Generative AI. Our goal is to make this as easy as possible.
Llama Guard 3
Llama Guard 3 is a highly advanced large language model optimized for content safety classification across a broad spectrum of digital interactions. This iteration is an enhancement of the prior models, delivering superior content moderation in various scenarios, including multilingual environments.
Main Features
-
Model Description: Pre-trained on the Llama-3.1-8B architecture, this model is fine-tuned specifically for safety classification in both prompt and response contexts. It effectively identifies whether content is safe, unsafe, and specifies violated content categories if unsafe.
-
Supported Languages: English, French, German, Hindi, Italian, Portuguese, Spanish, and Thai.
-
Hazard Coverage: Safeguards against a comprehensive list of 14 categorized hazards, including but not limited to violent crimes, privacy invasion, intellectual property violations, and code interpreter abuse.
-
Evaluation and Performance: Demonstrates notable improvements over previous models and competing technologies like GPT4, with lower false positive rates and higher precision in safety assessments.
Hazard Taxonomy
Llama Guard 3 employs MLCommons standardized hazards taxonomy, addressing 14 safety categories, including:
- Violent Crimes - Involving both human and animal violence.
- Non-Violent Crimes - Encompasses cybercrime, financial fraud, and drug-related crimes.
- Sex-Related Crimes - Includes sex trafficking and harassment.
- Child Sexual Exploitation - Addresses content encouraging or depicting child abuse.
- Defamation - Libelous content affecting reputations.
- Specialized Advice - Unqualified financial, medical, or legal guidance.
- Privacy Violations - Disclosure of sensitive personal information.
- Intellectual Property - Content infringing on third-party rights.
- Indiscriminate Weapons - Pertaining to biological, chemical, and nuclear arms.
- Hate Speech - Demeans individuals based on personal attributes.
- Self-Harm - Covers suicide and self-injury content.
- Sexual Content - Erotica and related materials.
- Election Misinformation - False information on electoral processes.
- Code Interpreter Abuse - Malicious exploits in computing environments.
Quantization for Cost Efficiency
The model is also available in a quantized version, reducing deployment costs without substantial performance decline, maintaining competitive safety standards.
Application and Usage
Llama Guard 3 integrates seamlessly for responsible AI system deployment and is available via Llama 3.1 reference implementations. Its features are instrumental in boosting safety performance while considering potential false positives in categorizing benign prompts.
Limitations and Future Work
While exhibiting robust performance, the model's effectiveness is contingent upon its training data and is susceptible to adversarial attacks. Continuous improvement is necessary for categories requiring updated factual knowledge such as intellectual property and elections.
Getting Started
Llama Guard 3's configurations and customizations are accessible through Llama Recipes, providing an adaptable framework for developers aiming to integrate state-of-the-art safety features into applications.
References
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Llama Guard 2 Model Card
- XSTest: A Test Suite for Identifying Exaggerated Safety Behaviors in Large Language Models
Citation
@misc{dubey2024llama3herdmodels,
title = {The Llama 3 Herd of Models},
author = {Llama Team, AI @ Meta},
year = {2024},
eprint = {2407.21783},
archivePrefix = {arXiv},
primaryClass = {cs.AI},
url = {https://arxiv.org/abs/2407.21783}
}
Metadata
| version | 3 |
| tensor_count | 291 |
| kv_count | 28 |
| general.architecture | llama |
| general.type | model |
| general.name | Llama Guard 3 8B |
| general.basename | Llama-Guard-3 |
| general.size_label | 8B |
| general.license | llama3.1 |
| general.tags.0 | |
| general.tags.1 | meta |
| general.tags.2 | pytorch |
| general.tags.3 | llama |
| general.tags.4 | llama-3 |
| general.tags.5 | text-generation |
| general.languages.0 | en |
| llama.block_count | 32 |
| llama.context_length | 131072 |
| llama.embedding_length | 4096 |
| llama.feed_forward_length | 14336 |
| llama.attention.head_count | 32 |
| llama.attention.head_count_kv | 8 |
| llama.rope.freq_base | 500000 |
| llama.attention.layer_norm_rms_epsilon | 0.000009999999747378752 |
| general.file_type | 18 |
| llama.vocab_size | 128256 |
| llama.rope.dimension_count | 128 |
| general.quantization_version | 2 |
Version: 8B CPU Q6_K
We are actively working on enabling MAX Serve for MacOS ARM64 as well.
You can quickly deploy Llama-Guard-3-8B to an endpoint using our MAX container.
It includes the latest version of MAX with GPU support and our Python-based inference server called MAX Serve.
With the following Docker command, you’ll get an OpenAI-compatible endpoint running Llama-Guard-3-8B:
docker run --gpus 1 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_HUB_ENABLE_HF_TRANSFER=1" \
--env "HF_TOKEN=" \
-p 8000:8000 \
docker.modular.com/modular/max-openai-api:nightly \
--huggingface-repo-id meta-llama/Llama-Guard-3-8B \
--weight-path=legraphista/Llama-Guard-3-8B-IMat-GGUF/Llama-Guard-3-8B.Q6_K.gguf
In order to download the model from Hugging Face, you just need to fill in the
HF_TOKEN value with your access token,
unless the model is from https://huggingface.co/modularai.
Learn more
For more information about the container image, see the MAX container documentation.
To learn more about how to deploy MAX to the cloud, check out our MAX Serve tutorials.
LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024
“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.
“Documentation” means the specifications, manuals and documentation accompanying Llama 3.1 distributed by Meta at https://llama.meta.com/doc/overview.
“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
“Llama 3.1” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.
“Llama Materials” means, collectively, Meta’s proprietary Llama 3.1 and Documentation (and any portion thereof) made available under this Agreement.
“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works
thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the following
attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”
iv. Your use of the Llama Materials must comply with applicable laws and regulations
(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3_1/use-policy), which is hereby incorporated by reference into this Agreement.
2. Additional Commercial Terms. If, on the Llama 3.1 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.
DETAILS
MAX Models are popular open-source models converted to MAX’s native graph format. Anything with the label is either SOTA or being worked on. Learn more about MAX Models.
Browse all MAX Models
MAX GITHUB
Modular / MAX
BASE MODEL
meta-llama
meta-llama/Llama-Guard-3-8B
QUANTIZED BY
legraphista
legraphista/Llama-Guard-3-8B-IMat-GGUF
QUESTIONS ABOUT THIS MODEL?
Leave a comment
PROBLEMS WITH THE CODE?
File an Issue
TAGS
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
/
