https://github.com/alphasecio/llama-guard
A Streamlit app for exploring content moderation with Llama Guard on Groq.
https://github.com/alphasecio/llama-guard
groq llama llama-guard llm python safety
Last synced: about 2 months ago
JSON representation
A Streamlit app for exploring content moderation with Llama Guard on Groq.
- Host: GitHub
- URL: https://github.com/alphasecio/llama-guard
- Owner: alphasecio
- License: mit
- Created: 2024-10-25T04:58:06.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-02-03T09:37:02.000Z (3 months ago)
- Last Synced: 2025-02-03T10:32:20.346Z (3 months ago)
- Topics: groq, llama, llama-guard, llm, python, safety
- Language: Python
- Homepage:
- Size: 612 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE
Awesome Lists containing this project
README
# llama-guard
[Llama Guard](https://www.llama.com/docs/model-cards-and-prompt-formats/llama-guard-3) is an LLM-based input-output safeguard model geared towards Human-AI conversation use cases. If the input is determined to be safe, the response will be `Safe`. Else, the response will be `Unsafe`, followed by one or more of the violating categories:
* S1: Violent Crimes.
* S2: Non-Violent Crimes.
* S3: Sex Crimes.
* S4: Child Sexual Exploitation.
* S5: Defamation.
* S6: Specialized Advice.
* S7: Privacy.
* S8: Intellectual Property.
* S9: Indiscriminate Weapons.
* S10: Hate.
* S11: Suicide & Self-Harm.
* S12: Sexual Content.
* S13: Elections.
* S14: Code Interpreter Abuse.
This repository contains a Streamlit app for exploring content moderation with Llama Guard on [Groq](https://groq.com). Sign up for an account at [GroqCloud](https://console.groq.com/keys) and get an API token, which you'll need for this project.
Here's a sample response by Llama Guard upon detecting a prompt that violated a specific category.
