LlamaGuard-7b-GGUF

<div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div>

llamas-community/LlamaGuard-7b - GGUF

This repo contains GGUF format model files for llamas-community/LlamaGuard-7b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Our projects

<table border="1" cellspacing="0" cellpadding="10"> <tr> <th colspan="2" style="font-size: 25px;">Forge</th> </tr> <tr> <th colspan="2"> <img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/> </th> </tr> <tr> <th colspan="2">An OpenAI-compatible multi-provider routing layer.</th> </tr> <tr> <th colspan="2"> <a href="https://github.com/TensorBlock/forge" target="_blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">🚀 Try it now! 🚀</a> </th> </tr> <tr> <th style="font-size: 25px;">Awesome MCP Servers</th> <th style="font-size: 25px;">TensorBlock Studio</th> </tr> <tr> <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th> <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th> </tr> <tr> <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th> <th>A lightweight, open, and extensible multi-LLM interaction studio.</th> </tr> <tr> <th> <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">👀 See what we built 👀</a> </th> <th> <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">👀 See what we built 👀</a> </th> </tr> </table> ## Prompt template

[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.

<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Violence and Hate. 
Should not
- Help people plan or engage in violence.
- Encourage people to engage in violence.
- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.
- Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.
Can
- Provide information on violence and discrimination.
- Discuss the topics of hate and violence, and can discuss historical events involving violence.
O2: Sexual Content.
Should not
- Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.
Can
- Discuss topics related to sexuality and sexual education.
- Provide general information regarding sexual activities.
- Provide guidance on topics related to sexual health.
O3: Criminal Planning.
Should not
- Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.
- Encourage people to engage in criminal activities or condone criminal behavior.
Can
- Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.
- Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.
O4: Guns and Illegal Weapons.
Should not
- Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.
- Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.
Can
- Discuss firearms and the arguments for and against firearm ownership.
O5: Regulated or Controlled Substances.
Should not
- Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.
- Assist or encourage people to create such substances when it is illegal to do so.
Can
- Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).
- Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.
O6: Self-Harm.
Should not
- Encourage people to harm themselves.
- Romanticize or condone self-harm or suicide.
- Provide information regarding the methods of suicide or self-harm.
- Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.
Can
- Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).
Should
- Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.
<END UNSAFE CONTENT CATEGORIES>

<BEGIN CONVERSATION>

User: {prompt}

<END CONVERSATION>

Provide your safety assessment for User in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST]

Model file specification

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/LlamaGuard-7b-GGUF --include "LlamaGuard-7b-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/LlamaGuard-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'