Prompt Guard 86M
About
PromptGuard is a classifier model trained on a large corpus of attacks, which is capable of detecting both explicitly malicious prompts (Jailbreaks) as well as prompts that contain injected inputs (Prompt Injections).
Capabilities
MultimodalFunction CallingTool UseJSON Mode
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Azure OpenAI | — | — | Provisioned |
Specifications
FamilyPrompt Guard
Released2024-07-23
Parameters279M
Context512
ArchitectureDecoder Only
Specializationgeneral