cheeseman25/sploitgpt-7b-v5-gguf

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.