Safetensors
GGUF
qwen3
cybersecurity
agentic
red-team
blue-team
distillation
glm-5.2
kimi-k3
function-calling
tool-calling
tool-use
conversational
Instructions to use bebrws/security-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use bebrws/security-8b 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 bebrws/security-8b:Q4_K_M # Run inference directly in the terminal: llama cli -hf bebrws/security-8b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf bebrws/security-8b:Q4_K_M # Run inference directly in the terminal: llama cli -hf bebrws/security-8b:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf bebrws/security-8b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf bebrws/security-8b:Q4_K_M
Use Docker
docker model run hf.co/bebrws/security-8b:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use bebrws/security-8b with Ollama:
ollama run hf.co/bebrws/security-8b:Q4_K_M
- Unsloth Desktop
- Pi
How to use bebrws/security-8b with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf bebrws/security-8b:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "bebrws/security-8b:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use bebrws/security-8b with Docker Model Runner:
docker model run hf.co/bebrws/security-8b:Q4_K_M
- Lemonade
How to use bebrws/security-8b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull bebrws/security-8b:Q4_K_M
Run and chat with the model
lemonade run user.security-8b-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use bebrws/security-8b with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf bebrws/security-8b:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default bebrws/security-8b:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use bebrws/security-8b with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf bebrws/security-8b:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "bebrws/security-8b:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Model card: add Foundation-Sec benchmark comparison incl. v7cti
Browse files
README.md
CHANGED
|
@@ -54,6 +54,46 @@ meaningful for this suite. Known v4 gap: `atk-sqli` — the model prefers to sta
|
|
| 54 |
staged vulnerable app and fuzz it over HTTP instead of reading the offline artifacts
|
| 55 |
(trace-verified behavioral prior, targeted in round 5).
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
## Usage
|
| 58 |
|
| 59 |
vLLM, short-task/eval serving (disable static YaRN):
|
|
|
|
| 54 |
staged vulnerable app and fuzz it over HTTP instead of reading the offline artifacts
|
| 55 |
(trace-verified behavioral prior, targeted in round 5).
|
| 56 |
|
| 57 |
+
## External benchmark: vs Cisco Foundation-Sec-8B (MCQ knowledge eval, 2026-08-01)
|
| 58 |
+
|
| 59 |
+
Independent comparison on 1,210 multiple-choice cybersecurity questions
|
| 60 |
+
(CyberMetric-500, CTI-Bench-MCQ 500/2500 sample, SecQA v1+v2 test; seed 42,
|
| 61 |
+
temperature 0). Each model was evaluated in its **native prompting mode**:
|
| 62 |
+
Foundation-Sec-8B is a *base* model and was evaluated with 3-shot raw completion
|
| 63 |
+
(its intended usage per Cisco's model card); k3-sec-8b was evaluated zero-shot
|
| 64 |
+
chat (Qwen3 template, non-thinking). Identical question sets for every model.
|
| 65 |
+
|
| 66 |
+
| Benchmark (n) | Foundation-Sec-8B | k3 v4 | v5 | v6 | v7cti (chat) | v7cti (completion) |
|
| 67 |
+
|---|---:|---:|---:|---:|---:|---:|
|
| 68 |
+
| CyberMetric-500 | 84.20% | **86.80%** | **86.80%** | **86.80%** | 86.20% | **87.80%** |
|
| 69 |
+
| CTI-Bench-MCQ (500) | **66.00%** | 59.20% | 59.80% | 58.80% | 60.40% | 62.60% |
|
| 70 |
+
| SecQA v1+v2 (210) | 98.10% | 98.10% | 98.10% | 98.10% | 97.62% | **98.57%** |
|
| 71 |
+
| **Overall (1,210)** | **79.09%** | 77.36% | 77.60% | 77.19% | 77.52% | **79.26%** |
|
| 72 |
+
|
| 73 |
+
Parse failures: 0 for all models in native modes.
|
| 74 |
+
|
| 75 |
+
**Prompting-mode sensitivity.** Foundation-Sec-8B collapses under zero-shot chat
|
| 76 |
+
prompting (~34% accuracy, ~40% whitespace/echo responses) and only performs via
|
| 77 |
+
few-shot completion — do not deploy it behind a naive chat template. k3-sec-8b is
|
| 78 |
+
robust across both modes with 100% answer-format compliance.
|
| 79 |
+
|
| 80 |
+
**CTI rounds (v6cti / v7cti branches).** Two rounds of ATT&CK-STIX-derived CTI data
|
| 81 |
+
(~2.5k decontaminated MCQ+free-form traces, GLM-5.2/Foundation-Sec teachers,
|
| 82 |
+
deepseek-v4-flash judge) were trained on top of the r6 mix. Round 6 (justification
|
| 83 |
+
style, upsampled) produced churn without net gain and a chat-mode regression —
|
| 84 |
+
diagnosed as format conflict + template overfitting + step-share dilution. Round 7
|
| 85 |
+
fixed all three (bare-letter format-matched training, GLM-5.2 paraphrases,
|
| 86 |
+
multi-turn packing to 38% of gradient steps): chat CTI-Bench **+1.6** to 60.4%,
|
| 87 |
+
CyberMetric completion **87.8%** and SecQA completion **98.6%** (k3 records), and
|
| 88 |
+
**v7cti-completion ties Foundation-Sec overall (79.26% vs 79.09%)** while beating it
|
| 89 |
+
on CyberMetric by 3.6 pts. Foundation-Sec still leads CTI-Bench (66.0%) — the
|
| 90 |
+
remaining target for the next round (failure-targeted DPO or light domain CPT).
|
| 91 |
+
|
| 92 |
+
**Qualitative** (6 open-ended security prompts): Foundation-Sec gives terse,
|
| 93 |
+
mostly-correct completion-style answers; k3 gives structured markdown answers with
|
| 94 |
+
finer-grained precision (e.g. LSASS dumping -> T1003.001 sub-technique + detections).
|
| 95 |
+
Eval harness + raw per-question results: `sec-eval/` (drive_eval.py, results_*.json).
|
| 96 |
+
|
| 97 |
## Usage
|
| 98 |
|
| 99 |
vLLM, short-task/eval serving (disable static YaRN):
|