Instructions to use cheeseman25/sploitgpt-7b-v5-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cheeseman25/sploitgpt-7b-v5-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cheeseman25/sploitgpt-7b-v5-gguf",
	filename="model-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cheeseman25/sploitgpt-7b-v5-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cheeseman25/sploitgpt-7b-v5-gguf: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 cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cheeseman25/sploitgpt-7b-v5-gguf: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 cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M

Use Docker

docker model run hf.co/cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use cheeseman25/sploitgpt-7b-v5-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cheeseman25/sploitgpt-7b-v5-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cheeseman25/sploitgpt-7b-v5-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M

Ollama
How to use cheeseman25/sploitgpt-7b-v5-gguf with Ollama:
```
ollama run hf.co/cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M
```

Unsloth Studio new

How to use cheeseman25/sploitgpt-7b-v5-gguf 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 cheeseman25/sploitgpt-7b-v5-gguf 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 cheeseman25/sploitgpt-7b-v5-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cheeseman25/sploitgpt-7b-v5-gguf to start chatting

Pi new

How to use cheeseman25/sploitgpt-7b-v5-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M

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": "cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cheeseman25/sploitgpt-7b-v5-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M

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 cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use cheeseman25/sploitgpt-7b-v5-gguf with Docker Model Runner:
```
docker model run hf.co/cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M
```

Lemonade

How to use cheeseman25/sploitgpt-7b-v5-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cheeseman25/sploitgpt-7b-v5-gguf:Q4_K_M

Run and chat with the model

lemonade run user.sploitgpt-7b-v5-gguf-Q4_K_M

List all available models

lemonade list

SploitGPT 7B v5 GGUF

Fine-tuned Qwen2.5-7B model for autonomous penetration testing. Designed for use with SploitGPT.

Model Variants

File	Size	VRAM	Description
`model-Q5_K_M.gguf`	5.1GB	12GB+	Best quality
`model-Q4_K_M.gguf`	4.4GB	8GB+	Good quality, faster inference

Quick Start

# Download model (choose based on VRAM)
wget https://huggingface.co/cheeseman2422/sploitgpt-7b-v5-gguf/resolve/main/model-Q5_K_M.gguf

# Create Ollama model
ollama create sploitgpt-7b-v5.10e:q5 -f - <<'EOF'
FROM ./model-Q5_K_M.gguf
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
"""
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"
PARAMETER temperature 0.3
PARAMETER top_p 0.9
EOF

# Verify
ollama list | grep sploitgpt

Training

Base Model: Qwen2.5-7B-Instruct
Training Method: LoRA fine-tuning with Unsloth
Training Data: MITRE ATT&CK techniques, Metasploit modules, pentesting workflows
LoRA Config: r=64, alpha=128

Capabilities

Tool calling for security tools (nmap, metasploit, etc.)
MITRE ATT&CK knowledge retrieval
Penetration testing workflow reasoning
Scope-aware command generation

Usage with SploitGPT

See the main repository: https://github.com/cheeseman2422/SploitGPT

git clone https://github.com/cheeseman2422/SploitGPT.git
cd SploitGPT
./install.sh  # Downloads model automatically
./sploitgpt.sh --tui

License

Model weights: Apache 2.0 (following Qwen2.5 license)
Fine-tuning data and methodology: MIT

Disclaimer

This model is for authorized security testing only. Users are responsible for ensuring they have proper authorization before using this model for penetration testing activities.

Downloads last month: 12

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

Model tree for cheeseman25/sploitgpt-7b-v5-gguf

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(310)

this model