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
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Microsoft Foundry | $0.05 | $0.05 | Provisioned |
Rankings
Specifications
FamilyPrompt Guard
Released2024-07-23
Parameters279M
Context512
ArchitectureDecoder Only
Specializationgeneral
Trainingfinetuning
Created by
Large-scale open-source AI for social technologies.
Menlo Park, California, United States
Founded 2013
Website