Instructions to use saki007ster/CybersecurityRiskAnalyst with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use saki007ster/CybersecurityRiskAnalyst with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="saki007ster/CybersecurityRiskAnalyst", filename="CybersecurityRiskAnalyst.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use saki007ster/CybersecurityRiskAnalyst with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf saki007ster/CybersecurityRiskAnalyst # Run inference directly in the terminal: llama cli -hf saki007ster/CybersecurityRiskAnalyst
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf saki007ster/CybersecurityRiskAnalyst # Run inference directly in the terminal: llama cli -hf saki007ster/CybersecurityRiskAnalyst
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 saki007ster/CybersecurityRiskAnalyst # Run inference directly in the terminal: ./llama-cli -hf saki007ster/CybersecurityRiskAnalyst
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 saki007ster/CybersecurityRiskAnalyst # Run inference directly in the terminal: ./build/bin/llama-cli -hf saki007ster/CybersecurityRiskAnalyst
Use Docker
docker model run hf.co/saki007ster/CybersecurityRiskAnalyst
- LM Studio
- Jan
- Ollama
How to use saki007ster/CybersecurityRiskAnalyst with Ollama:
ollama run hf.co/saki007ster/CybersecurityRiskAnalyst
- Unsloth Studio
How to use saki007ster/CybersecurityRiskAnalyst 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 saki007ster/CybersecurityRiskAnalyst 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 saki007ster/CybersecurityRiskAnalyst to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for saki007ster/CybersecurityRiskAnalyst to start chatting
- Atomic Chat new
- Docker Model Runner
How to use saki007ster/CybersecurityRiskAnalyst with Docker Model Runner:
docker model run hf.co/saki007ster/CybersecurityRiskAnalyst
- Lemonade
How to use saki007ster/CybersecurityRiskAnalyst with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull saki007ster/CybersecurityRiskAnalyst
Run and chat with the model
lemonade run user.CybersecurityRiskAnalyst-{{QUANT_TAG}}List all available models
lemonade list
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
CybersecurityRiskAnalyst
β Find this useful? Clone it, star the repo, and cite the paper. If you use this model in academic or professional work, please cite arXiv:2603.20131 (see How to cite). Model DOI:
10.57967/hf/9777.
CybersecurityRiskAnalyst is a custom fine-tuned Large Language Model (LLM) designed to act as a senior cybersecurity risk assessor and strategist. It is published on Ollama and has 1,400+ downloads. This repository makes the model formally citable and links it to the research paper it accompanies.
- Model:
saki007ster/CybersecurityRiskAnalyston Ollama - Base model: Llama 3.1 8B (
llamaarchitecture, 8.03B parameters) - Quantization: Q4_0 Β· Size: 4.7 GB Β· Context window: 128K
- Tags: text, cybersecurity, risk assessment
What it does
- Risk Posture Evaluation β assesses an organization's overall security posture
- Framework Mapping β NIST CSF, CIS Controls, MITRE ATT&CK, ISO/IEC 27001
- Threat Intelligence Awareness
- Gap Analysis
- Prioritized Recommendations
- Human-Centric Reports β clear, decision-ready output
- Explainability β reasoning you can follow and audit
DOI
Model DOI (Hugging Face): 10.57967/hf/9777
Install & Use
Requires Ollama.
# Pull the model
ollama pull saki007ster/CybersecurityRiskAnalyst
# Or pull-and-run in one step
ollama run saki007ster/CybersecurityRiskAnalyst
Minimal usage example
ollama run saki007ster/CybersecurityRiskAnalyst \
"We run a 200-person fintech on AWS with no formal incident response plan. \
Assess our top cyber risks and map them to NIST CSF."
Or via the Ollama HTTP API:
curl http://localhost:11434/api/generate -d '{
"model": "saki007ster/CybersecurityRiskAnalyst",
"prompt": "Perform a NIST CSF gap analysis for a small healthcare provider storing PHI in a single on-prem server.",
"stream": false
}'
Python:
import ollama
response = ollama.chat(
model="saki007ster/CybersecurityRiskAnalyst",
messages=[{
"role": "user",
"content": "Prioritize remediation for an org with exposed RDP, no MFA, and unpatched VPN.",
}],
)
print(response["message"]["content"])
How to cite
This model accompanies the paper below β if you use the model in academic or professional work, please cite the paper.
Gupta, Ravish; Kumar, Saket; Sharma, Shreeya; Dang, Maulik; and Aggarwal, Abhishek (2026). An Agentic Multi-Agent Architecture for Cybersecurity Risk Management. arXiv preprint arXiv:2603.20131.
APA
Gupta, R., Kumar, S., Sharma, S., Dang, M., & Aggarwal, A. (2026). An Agentic Multi-Agent Architecture for Cybersecurity Risk Management. arXiv preprint arXiv:2603.20131.
MLA
Gupta, Ravish, et al. "An Agentic Multi-Agent Architecture for Cybersecurity Risk Management." arXiv preprint arXiv:2603.20131 (2026).
Chicago
Gupta, Ravish, Saket Kumar, Shreeya Sharma, Maulik Dang, and Abhishek Aggarwal. "An Agentic Multi-Agent Architecture for Cybersecurity Risk Management." arXiv preprint arXiv:2603.20131 (2026).
Harvard
Gupta, R., Kumar, S., Sharma, S., Dang, M. and Aggarwal, A., 2026. An Agentic Multi-Agent Architecture for Cybersecurity Risk Management. arXiv preprint arXiv:2603.20131.
Vancouver
Gupta R, Kumar S, Sharma S, Dang M, Aggarwal A. An Agentic Multi-Agent Architecture for Cybersecurity Risk Management. arXiv preprint arXiv:2603.20131. 2026.
BibTeX
@article{gupta2026agentic,
title = {An Agentic Multi-Agent Architecture for Cybersecurity Risk Management},
author = {Gupta, Ravish and Kumar, Saket and Sharma, Shreeya and Dang, Maulik and Aggarwal, Abhishek},
journal = {arXiv preprint arXiv:2603.20131},
year = {2026}
}
A machine-readable CITATION.cff is also provided β GitHub will render a "Cite this repository" button from it.
Citing the model artifact directly (Hugging Face DOI)
To cite the model itself (not the paper), use its Hugging Face DOI:
@misc{kumar2026cybersecurityriskanalyst,
author = {Saket Kumar and Ravish Gupta},
title = {CybersecurityRiskAnalyst (Revision 1842e1c)},
year = {2026},
url = {https://huggingface.co/saki007ster/CybersecurityRiskAnalyst},
doi = {10.57967/hf/9777},
publisher = {Hugging Face}
}
The model artifact was built by Saket Kumar and Ravish Gupta (hence two authors on the model DOI). The paper (arXiv:2603.20131) has five authors β for academic/professional use, prefer the paper citation above; use the model DOI for reproducibility/data-availability statements.
Authors & attribution
Model (the fine-tuned artifact β Ollama & Hugging Face, DOI 10.57967/hf/9777):
- Saket Kumar β model author / maintainer (
saki007ster) - Ravish Gupta
Paper (An Agentic Multi-Agent Architecture for Cybersecurity Risk Management, arXiv:2603.20131):
- Ravish Gupta
- Saket Kumar
- Shreeya Sharma
- Maulik Dang
- Abhishek Aggarwal
License
This model is a fine-tuned derivative of Meta Llama 3.1 8B and is therefore governed by the Llama 3.1 Community License Agreement (Version Release Date: July 23, 2024).
- Built with Llama. Use is subject to Meta's Acceptable Use Policy.
- The base-model license terms are inherited by this derivative; see LICENSE for the full text.
Related
- π Paper: An Agentic Multi-Agent Architecture for Cybersecurity Risk Management (arXiv:2603.20131)
- π€ Model (Ollama): saki007ster/CybersecurityRiskAnalyst
- π€ Model (Hugging Face): saki007ster/CybersecurityRiskAnalyst Β· DOI
10.57967/hf/9777 - π Modelfile: Modelfile in this repo
- Downloads last month
- -
We're not able to determine the quantization variants.