Instructions to use ArmurAI/Pentest_AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArmurAI/Pentest_AI with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ArmurAI/Pentest_AI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ArmurAI/Pentest_AI")
model = AutoModelForMultimodalLM.from_pretrained("ArmurAI/Pentest_AI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArmurAI/Pentest_AI with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ArmurAI/Pentest_AI

SGLang

How to use ArmurAI/Pentest_AI with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ArmurAI/Pentest_AI" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArmurAI/Pentest_AI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ArmurAI/Pentest_AI" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArmurAI/Pentest_AI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ArmurAI/Pentest_AI with Docker Model Runner:
```
docker model run hf.co/ArmurAI/Pentest_AI
```

Kuro0911 commited on Apr 17, 2024

Commit

5899e34

verified ·

1 Parent(s): 993e605

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ language:
 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.
-<img src="https://github.com/Armur-Ai/Auto-Pentest-GPT-AI/blob/main/images/Auto_Pentest.png" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 ### 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.

 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.
+<img src="https://github.com/Armur-Ai/Auto-Pentest-GPT-AI/blob/main/images/Auto_Pentest.png" alt="Pentest AI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 ### 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.