Instructions to use ZySec-AI/SecurityLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZySec-AI/SecurityLLM with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ZySec-AI/SecurityLLM")
model = AutoModelForCausalLM.from_pretrained("ZySec-AI/SecurityLLM")
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 ZySec-AI/SecurityLLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ZySec-AI/SecurityLLM

SGLang

How to use ZySec-AI/SecurityLLM 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 "ZySec-AI/SecurityLLM" \
    --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": "ZySec-AI/SecurityLLM",
		"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 "ZySec-AI/SecurityLLM" \
        --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": "ZySec-AI/SecurityLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ZySec-AI/SecurityLLM with Docker Model Runner:
```
docker model run hf.co/ZySec-AI/SecurityLLM
```

venkycs commited on Jan 28, 2024

Commit

fb53908

verified ·

1 Parent(s): 369cee2

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -28

README.md CHANGED Viewed

@@ -7,42 +7,27 @@ license: apache-2.0
 <!-- Provide a quick summary of what the model is/does. -->
-### Model Description
-# ZySec-v1-7B: A New Era in AI-Driven Cybersecurity
-## Overview
-ZySec-v1-7B stands as a pivotal innovation for security professionals, harnessing the advanced capabilities of HuggingFace's Zephyr language model series. This AI model is designed as an omnipresent cybersecurity ally, offering on-demand, expert guidance on cybersecurity issues. ZySec-7B is like a digital teammate, adept at navigating the complexities of security challenges.
-## Key Features
-- **Comprehensive Training:** ZySec-7B is developed using the DPO technique and covers numerous cybersecurity fields, providing a deep and wide-ranging understanding of the sector.
-- **Diverse Topics:** Encompassing areas such as sophisticated threats, compliance and regulatory frameworks, practical cybersecurity applications, and strategic fields.
-- **Extensive Data Coverage:** Trained in over 30 unique domains, each with thousands of data points, ZySec-7B offers unparalleled expertise.
-## Training Domains
-ZySec-7B's training spans critical topics including:
-- Advanced subjects like Attack Surface Threats, Cloud Security, and the Cyber Kill Chain.
-- Compliance and regulatory frameworks: CIS Controls, FedRAMP, PCI DSS, and ISO/IEC 27001.
-- Operational aspects: Cloud Secure Migration, Data Exfiltration Techniques, and Security Incident Handling.
-- Strategic areas: Security Governance, Risk Management, and Security Architecture Review.
-## Dataset Distribution
-The dataset is rich and diverse, with records in domains like:
-- Attack Surface Threats: 3148
-- CIS Controls: 3842
-- Cloud Secure Migration: 3510
-- [See the full dataset distribution here](https://huggingface.co/aihub-app/ZySec-7B-v1/resolve/main/ZySec-7B-dataset-composition.png?download=true)
-## Integration and Usage
-ZySec-7B is open-source and AI-driven, redefining how security is approached within organizations. Its integration capabilities include:
-- Full compatibility with [LM Studio](https://lmstudio.ai). Search for "Zysec" to see its potential.
-- Sample output of ZySec writing an email about database security can be viewed [here](https://huggingface.co/aihub-app/ZySec-7B-v1/resolve/main/sample-output.png?download=true).
-## Community and Contributions
-As an open-source project, ZySec-7B invites community contributions, enhancing its adaptability and transparency. It's not just a software; it's a community-enhanced strategic tool, empowering teams to stay ahead of evolving cyber threats and compliance requirements.
-## Stay Informed and Contribute
-Join us in shaping the future of AI-driven cybersecurity. For more information, updates, and contribution guidelines, visit our repository or contact our team.

 <!-- Provide a quick summary of what the model is/does. -->
+# ZySec-v1-7B
+ZySec-v1-7B, stands as a pivotal innovation for security professionals, leveraging the advanced capabilities of HuggingFace's Zephyr language model series. This AI model is crafted to be an omnipresent cybersecurity ally, offering on-demand, expert guidance in cybersecurity issues. Picture ZySec-7B as an ever-present digital teammate, adept at navigating the complexities of security challenges.
+The efficacy of ZySec-7B lies in its comprehensive training across numerous cybersecurity fields, providing a deep and wide-ranging understanding of the sector. ZySec is developed using the DPO technique, utilizing a varied dataset encompassing critical topics such as:
+- Sophisticated areas like Attack Surface Threats, Cloud Security, and the Cyber Kill Chain.
+- Key compliance and regulatory frameworks, including CIS Controls, FedRAMP, PCI DSS, and ISO/IEC 27001.
+- Practical aspects like Cloud Secure Migration, Data Exfiltration Techniques, and Security Incident Handling.
+- Crucial strategic fields such as Security Governance, Risk Management, and Security Architecture Review.
+ZySec-7B's training spans over 30 unique domains, each enriched with thousands of data points, delivering unparalleled expertise.
+As the first of its kind in an open-source, AI-driven cybersecurity series, ZySec-7B transcends the conventional role of a support tool, redefining organizational security approaches. Its open-source nature not only invites community contributions but also enhances its flexibility and transparency in managing vast cybersecurity data. ZySec-7B is instrumental in providing vital, actionable insights for strategic decision-making and advanced risk management. More than a mere software, ZySec-7B is a community-enhanced strategic tool, equipping your team to proactively confront and stay ahead of the dynamic landscape of cyber threats and regulatory demands.
+![Dataset Distribution](https://huggingface.co/aihub-app/ZySec-7B-v1/resolve/main/ZySec-7B-dataset-composition.png?download=true)
+Details of dataset distribution here - [Dataset Distribution](https://huggingface.co/aihub-app/ZySec-7B-v1/resolve/main/ZySec-7B-dataset-composition.png?download=true)
+Fully compatible with [LM Studio](https://lmstudio.ai). Search for “Zysec” and here is what you get. Here is a sample output of ZySec writing email to John about database security using LM Studio:
+![Sample Output](https://huggingface.co/aihub-app/ZySec-7B-v1/resolve/main/sample-output.png?download=true)