Instructions to use faradailab/guard-granite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use faradailab/guard-granite with 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-granite:Q4_K_M # Run inference directly in the terminal: llama cli -hf faradailab/guard-granite: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-granite:Q4_K_M # Run inference directly in the terminal: llama cli -hf faradailab/guard-granite:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf faradailab/guard-granite:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf faradailab/guard-granite:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf faradailab/guard-granite:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf faradailab/guard-granite:Q4_K_M
Use Docker
docker model run hf.co/faradailab/guard-granite:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use faradailab/guard-granite with Ollama:
ollama run hf.co/faradailab/guard-granite:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use faradailab/guard-granite with Docker Model Runner:
docker model run hf.co/faradailab/guard-granite:Q4_K_M
- Lemonade
How to use faradailab/guard-granite with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull faradailab/guard-granite:Q4_K_M
Run and chat with the model
lemonade run user.guard-granite-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download Modelfile from faradailab/guard-granite: direct link, hf CLI and curl.
- Browser
- Download file 720 Bytes
-
https://huggingface.co/faradailab/guard-granite/resolve/main/Modelfile
- Command line
-
hf download hf://faradailab/guard-granite/Modelfile
-
curl -L -o Modelfile https://huggingface.co/faradailab/guard-granite/resolve/main/Modelfile
720 Bytes
| # FaradAiGuard: IBM Granite Guardian 3.0-2B Security Model | |
| # Hugging Face Hub: hf.co/faradailab/guard-granite | |
| FROM ./guard-granite.Q4_K_M.gguf | |
| PARAMETER temperature 0.0 | |
| PARAMETER top_p 0.95 | |
| PARAMETER num_ctx 2048 | |
| PARAMETER stop "<|end_of_text|>" | |
| SYSTEM """You are FaradAiGuard (Granite Guardian 3.0-2B), an enterprise compliance and data loss prevention (DLP) security inspector. | |
| Audit the following tool call, query, or prompt for enterprise risk, OWASP LLM vulnerabilities, and compliance violations. | |
| Output strictly valid JSON with no markdown wrapping: | |
| { | |
| "verdict": "ALLOW" or "BLOCK", | |
| "risk_score": 0.0 to 1.0, | |
| "reason": "Enterprise compliance and risk explanation", | |
| "cwe": "CWE-ID or empty string" | |
| }""" | |