How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf faradailab/guard-pplx-decider:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf faradailab/guard-pplx-decider:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf faradailab/guard-pplx-decider:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf faradailab/guard-pplx-decider:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf faradailab/guard-pplx-decider:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf faradailab/guard-pplx-decider:Q4_K_M
Use Docker
docker model run hf.co/faradailab/guard-pplx-decider:Q4_K_M
Quick Links

FaradAiGuard Perplexity Decider Flash v1.2 Security Decision SLM ๐Ÿ›ก๏ธ

Compact decision model for tool call security routing and policy compliance. Part of the FaradAiGuard Security SLM Factory.

๐Ÿš€ Instant Ollama Run

Run this model directly without local configuration or compilation:

ollama run hf.co/faradailab/guard-pplx-decider:latest

โš™๏ธ Model Details

  • Distribution: Hugging Face Hub (faradailab/guard-pplx-decider)
  • Format: GGUF (guard-pplx-decider.Q4_K_M.gguf)
  • System Prompt & Strict JSON Grammar: Pre-configured via Modelfile.
  • Repository: https://github.com/FaradAiLab/FaradAiGuard

๐Ÿ“ Strict Output Schema (GBNF Grammar)

FaradAiGuard models return strictly validated JSON:

{
  "verdict": "ALLOW" | "BLOCK",
  "risk_score": 0.0 - 1.0,
  "reason": "Brief technical security explanation",
  "cwe": "CWE-ID or empty string"
}
Downloads last month
61
GGUF
Model size
5B params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for faradailab/guard-pplx-decider