Instructions to use RichardErkhov/ArmurAI_-_Pentest_AI-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/ArmurAI_-_Pentest_AI-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RichardErkhov/ArmurAI_-_Pentest_AI-gguf",
	filename="Pentest_AI.IQ4_NL.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 RichardErkhov/ArmurAI_-_Pentest_AI-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/ArmurAI_-_Pentest_AI-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/ArmurAI_-_Pentest_AI-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 RichardErkhov/ArmurAI_-_Pentest_AI-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/ArmurAI_-_Pentest_AI-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 RichardErkhov/ArmurAI_-_Pentest_AI-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/ArmurAI_-_Pentest_AI-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 RichardErkhov/ArmurAI_-_Pentest_AI-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/ArmurAI_-_Pentest_AI-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/ArmurAI_-_Pentest_AI-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/ArmurAI_-_Pentest_AI-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/ArmurAI_-_Pentest_AI-gguf:Q4_K_M
```

Unsloth Studio new

How to use RichardErkhov/ArmurAI_-_Pentest_AI-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 RichardErkhov/ArmurAI_-_Pentest_AI-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 RichardErkhov/ArmurAI_-_Pentest_AI-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RichardErkhov/ArmurAI_-_Pentest_AI-gguf to start chatting

Docker Model Runner
How to use RichardErkhov/ArmurAI_-_Pentest_AI-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/ArmurAI_-_Pentest_AI-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/ArmurAI_-_Pentest_AI-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/ArmurAI_-_Pentest_AI-gguf:Q4_K_M

Run and chat with the model

lemonade run user.ArmurAI_-_Pentest_AI-gguf-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Pentest_AI - GGUF

Model creator: https://huggingface.co/ArmurAI/
Original model: https://huggingface.co/ArmurAI/Pentest_AI/

Name	Quant method	Size
Pentest_AI.Q2_K.gguf	Q2_K	2.53GB
Pentest_AI.Q3_K_S.gguf	Q3_K_S	2.95GB
Pentest_AI.Q3_K.gguf	Q3_K	3.28GB
Pentest_AI.Q3_K_M.gguf	Q3_K_M	3.28GB
Pentest_AI.Q3_K_L.gguf	Q3_K_L	3.56GB
Pentest_AI.IQ4_XS.gguf	IQ4_XS	3.67GB
Pentest_AI.Q4_0.gguf	Q4_0	3.83GB
Pentest_AI.IQ4_NL.gguf	IQ4_NL	3.87GB
Pentest_AI.Q4_K_S.gguf	Q4_K_S	3.86GB
Pentest_AI.Q4_K.gguf	Q4_K	4.07GB
Pentest_AI.Q4_K_M.gguf	Q4_K_M	4.07GB
Pentest_AI.Q4_1.gguf	Q4_1	4.24GB
Pentest_AI.Q5_0.gguf	Q5_0	4.65GB
Pentest_AI.Q5_K_S.gguf	Q5_K_S	4.65GB
Pentest_AI.Q5_K.gguf	Q5_K	4.78GB
Pentest_AI.Q5_K_M.gguf	Q5_K_M	4.78GB
Pentest_AI.Q5_1.gguf	Q5_1	5.07GB
Pentest_AI.Q6_K.gguf	Q6_K	5.53GB
Pentest_AI.Q8_0.gguf	Q8_0	7.17GB

Original model description:

base_model: mistralai/Mistral-7B-v0.1 tags: - mistral - instruct - finetune - chatml - gpt4 - synthetic data - distillation model-index: - name: pentest ai results: [] language: - en

Pentest AI

PentestAI is an innovative assistant for penetration testing, we used the OpenHermes-2.5-Mistral-7B model, we jailbroke it, finetuned it with commands for popular Kali Linux tools and it's now able to provide guided, actionable steps and command automation for performing deep pen tests. The innovative PentestAI offers a cutting-edge solution for penetration testing by leveraging the modified OpenHermes-2.5-Mistral-7B model. This model has been uniquely jailbroken and finetuned with commands tailored for the most commonly used tools in Kali Linux, enabling it to provide guided, actionable steps and automate command execution for comprehensive penetration testing.

Key Features of PentestAI:

Guided Penetration Testing: PentestAI simplifies the complexity of penetration testing by guiding you through each step of the process. Starting with the acquisition of the target IP, it offers customized advice tailored to the specific phase of the penetration test you are in.
Command Automation: Streamline your penetration testing with automated command execution. PentestAI incorporates extensive knowledge of Kali Linux tools, providing you with command examples that you can execute directly or modify as needed.
Adaptive Learning: As you progress through your penetration testing tasks and share results, PentestAI dynamically adapts its suggestions to enhance your efficiency and effectiveness.
Ethical Framework: Throughout the testing process, PentestAI emphasizes adherence to ethical standards, ensuring that your penetration testing practices are responsible and legally compliant.
User-Friendly Interaction: You can interact seamlessly with PentestAI and conclude your session anytime by typing 'exit' or 'hacked' upon successfully compromising the target machine.

By integrating these features, PentestAI not only facilitates a smoother penetration testing experience but also ensures that it is performed efficiently and ethically. Whether you are a novice eager to learn the ropes or an experienced professional seeking to streamline your workflow, PentestAI provides valuable support tailored to your needs.

For more details and to access the tool, visit the GitHub repository.

Downloads last month: 174

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support