Llama Prompt Guard 2
Meta's small open-weight classifiers (86M and 22M) that flag prompt injection and jailbreak attempts in user input and untrusted content.
Tags
Description
Binary benign/malicious labels; the 22M version (DeBERTa-xsmall) cuts latency and compute by about 75% versus 86M with minimal performance loss, per the model card. Used as LlamaFirewall's PromptGuard scanner. Gated weights under the Llama 4 Community License.
Related
- LlamaFirewall: Meta's open-source guardrail framework for agents that chains scanners for prompt injection, goal hijacking and insecure generated code.
- Llama Guard: Meta's open-weight safety classifiers that label LLM prompts and responses as safe or unsafe against the MLCommons hazard taxonomy.
Sources
- https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Prompt-Guard-2/86M/MODEL_CARD.md
- https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-86M
- https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-22M
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)