Llama Guard Model

**Overview**

The Llamaguard models are large language models (LLMs) developed by Meta AI. The models provided in this listing is

- [LlamaGuard_7b](https://huggingface.co/meta-llama/LlamaGuard-7b)

The models are packaged using MLflow’s transformers flavor.
- [LlamaGuard_7b](https://huggingface.co/meta-llama/LlamaGuard-7b): It is a 7B parameter Llama 2-based input-output safeguard model. It can be used for classifying content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM: it generates text in its output that indicates whether a given prompt or response is safe/unsafe, and if unsafe based on a policy, it also lists the violating subcategories.

Llamaguard models are licensed under the [LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved](https://ai.meta.com/resources/models-and-libraries/llama-downloads/). By installing this listing, you acknowledge and agree to the license.

For example notebooks of using the llamaguard model in various use cases on Databricks, refer to [the Databricks ML example repository](https://github.com/databricks/databricks-ml-examples/tree/master/llm-models/safeguard/llamaguard).

**Use cases**

[LlamaGuard_7b](https://huggingface.co/meta-llama/LlamaGuard-7b):
Llama-Guard is a 7B parameter Llama 2-based input-output safeguard model. It can be used for classifying content in both LLM inputs (prompt classification) and in LLM responses (response classification).

**Taxonomy of harms and Risk Guidelines**

As automated content risk mitigation relies on classifiers to make decisions about content in real time, a prerequisite to building these systems is to have the following components:
- A **taxonomy** of risks that are of interest – these become the classes of a classifier.
- A risk guideline that determines where we put the line between encouraged and discouraged outputs for each risk category in the taxonomy. Together with this model, we release an open taxonomy inspired by existing open taxonomies such as those employed by Google, Microsoft and OpenAI in the hope that it can be useful to the community. This taxonomy does not necessarily reflect Meta's own internal policies and is meant to demonstrate the value of our method to tune LLMs into classifiers that show high performance and high degrees of adaptability to different policies.

**The Llama-Guard Safety Taxonomy & Risk Guidelines**

Below, we provide both the harm types themselves under this taxonomy and also examples of the specific kinds of content that would be considered harmful under each category:
- **Violence & Hate encompasses** statements that encourage or could help people plan or engage in violence. Similarly, statements that advocate discrimination, contain slurs, or voice hateful sentiments against people based on their sensitive personal characteristics (ex: race, color, religion, national origin, sexual orientation, gender, gender identity, or disability) would also be considered inappropriate under this category.
- **Sexual Content** encompasses statements encouraging someone (who could be underage) to engage in specific sex acts. Similarly, sexually explicit (i.e., erotic) statements would also be considered inappropriate under this category.
- **Guns & Illegal Weapons** encompasses statements that specifically encourage, condone, or could help people plan or execute specific crimes involving the illegal acquisition, creation, or use of guns or illegal weapons (ex: explosives, biological agents, or chemical weapons), including instructions on how to create or use them.
- **Regulated or Controlled Substances** encompasses statements that specifically encourage or could help people to illegally produce, transfer, or consume regulated or controlled substances like illegal drugs, tobacco, alcohol, or cannabis.
- **Suicide & Self Harm** encompasses statements that encourage, condone, or enable people to harm themselves (ex: by providing instructions or information on methods of self-harm). When people express or imply an intent to harm themselves, any response other than one that provides links to appropriate health resources would be considered inappropriate (even if entirely supportive).
- **Criminal Planning** encompasses miscellaneous statements that encourage, condone, or could help people plan or execute specific criminal activities, like arson, kidnapping, or theft. Items should only be considered harmful under this category when they could not be read as violating any of the other harm types above (ex: statements that encourage violence should be considered violating under Violence & Hate rather than this category).