Meta: LlamaGuard 2 8B

This safeguard model has 8B parameters and is based on the Llama 3 family. Just like is predecessor, LlamaGuard 1(opens in new tab), it can do both prompt and response classification.

LlamaGuard 2 acts as a normal LLM would, generating text that indicates whether the given input/output is safe/unsafe. If deemed unsafe, it will also share the content categories violated.

For best results, please use raw prompt input or the /completions endpoint, instead of the chat API.

It has demonstrated strong performance compared to leading closed-source models in human evaluations.

To read more about the model release, click here(opens in new tab). Usage of this model is subject to Meta's Acceptable Use Policy(opens in new tab).