← All models
Llama Prompt Guard 2 86M
llama-prompt-guard
86M-parameter (mDeBERTa-base) multilingual classifier that detects prompt injection and jailbreak attempts
- Family
- llama-prompt-guard
- Providers
- 3
- Context
- 512
- Output
- 512
- Knowledge
- -
- Weights
- Open
- Input
- text
- Output
- text
- Release date
- 2025-04-29
- Updated
- 2025-04-29
Providers
Source: models.dev