Instructions to use Mittai17/winsentinal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Mittai17/winsentinal with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Mittai17/winsentinal", filename="winsentinel-llama3.2-3b-f16.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Mittai17/winsentinal with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Mittai17/winsentinal:F16 # Run inference directly in the terminal: llama-cli -hf Mittai17/winsentinal:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Mittai17/winsentinal:F16 # Run inference directly in the terminal: llama-cli -hf Mittai17/winsentinal:F16
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 Mittai17/winsentinal:F16 # Run inference directly in the terminal: ./llama-cli -hf Mittai17/winsentinal:F16
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 Mittai17/winsentinal:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Mittai17/winsentinal:F16
Use Docker
docker model run hf.co/Mittai17/winsentinal:F16
- LM Studio
- Jan
- Ollama
How to use Mittai17/winsentinal with Ollama:
ollama run hf.co/Mittai17/winsentinal:F16
- Unsloth Studio new
How to use Mittai17/winsentinal with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Mittai17/winsentinal to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Mittai17/winsentinal to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Mittai17/winsentinal to start chatting
- Pi new
How to use Mittai17/winsentinal with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf Mittai17/winsentinal:F16
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Mittai17/winsentinal:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Mittai17/winsentinal with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf Mittai17/winsentinal:F16
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Mittai17/winsentinal:F16
Run Hermes
hermes
- Docker Model Runner
How to use Mittai17/winsentinal with Docker Model Runner:
docker model run hf.co/Mittai17/winsentinal:F16
- Lemonade
How to use Mittai17/winsentinal with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Mittai17/winsentinal:F16
Run and chat with the model
lemonade run user.winsentinal-F16
List all available models
lemonade list
π‘οΈ WinSentinel AI - Security Log Analysis Model
A fine-tuned Llama 3.2 3B model specialized in Windows security event log analysis and threat detection.
Features
- Threat Classification β Categorizes events as normal, suspicious, or malicious
- Severity Assessment β Rates threats from Low to Critical
- Intelligent Explanations β Provides context for why an event matters
- Action Recommendations β Suggests specific remediation steps
- Conversational β Responds naturally to general questions about itself and cybersecurity
Quick Start with Ollama
# Download both files: winsentinel-llama3.2-3b-f16.gguf and Modelfile
ollama create winsentinel -f Modelfile
ollama run winsentinel
Quick Start with LM Studio
- Download
winsentinel-llama3.2-3b-f16.gguf - Open LM Studio β My Models β Import
- Select the GGUF file
Example
Input:
Timestamp: 2026-02-15 03:22:41
Source IP: 45.33.12.88
User: admin
Event Type: login_failed
Message: Multiple failed login attempts from external IP
Output:
Threat Category: suspicious
Severity: Medium
Explanation: This event is significant because it matches known behavior patterns for credential access.
Recommended Action: Monitor the system and review logs for anomalies. Consider implementing MFA.
Training Details
- Base Model: unsloth/Llama-3.2-3B-Instruct
- Method: QLoRA (4-bit quantization + LoRA adapters)
- Dataset: 28,000+ security event logs + conversational data
- Hardware: NVIDIA RTX 3050 6GB
- Downloads last month
- 5
Hardware compatibility
Log In to add your hardware
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
Model tree for Mittai17/winsentinal
Base model
meta-llama/Llama-3.2-3B-Instruct