Safetensors
GGUF
English
cybersecurity
application-security
pentesting
bug-bounty
security-reporting
conversational
Instructions to use BugTraceAI/BugTraceAI-CORE-Pro 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 BugTraceAI/BugTraceAI-CORE-Pro 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 BugTraceAI/BugTraceAI-CORE-Pro # Run inference directly in the terminal: llama cli -hf BugTraceAI/BugTraceAI-CORE-Pro
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf BugTraceAI/BugTraceAI-CORE-Pro # Run inference directly in the terminal: llama cli -hf BugTraceAI/BugTraceAI-CORE-Pro
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 BugTraceAI/BugTraceAI-CORE-Pro # Run inference directly in the terminal: ./build/bin/llama cli -hf BugTraceAI/BugTraceAI-CORE-Pro
Use Docker
docker model run hf.co/BugTraceAI/BugTraceAI-CORE-Pro
- Llama new
- LM Studio
- Jan
- Ollama
How to use BugTraceAI/BugTraceAI-CORE-Pro with Ollama:
ollama run hf.co/BugTraceAI/BugTraceAI-CORE-Pro
- Unsloth Desktop
- Pi
How to use BugTraceAI/BugTraceAI-CORE-Pro with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf BugTraceAI/BugTraceAI-CORE-Pro
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "BugTraceAI/BugTraceAI-CORE-Pro" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use BugTraceAI/BugTraceAI-CORE-Pro with Docker Model Runner:
docker model run hf.co/BugTraceAI/BugTraceAI-CORE-Pro
- Lemonade
How to use BugTraceAI/BugTraceAI-CORE-Pro with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull BugTraceAI/BugTraceAI-CORE-Pro
Run and chat with the model
lemonade run user.BugTraceAI-CORE-Pro-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use BugTraceAI/BugTraceAI-CORE-Pro with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf BugTraceAI/BugTraceAI-CORE-Pro
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://127.0.0.1:9931/v1 hermes config set model.default BugTraceAI/BugTraceAI-CORE-Pro
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use BugTraceAI/BugTraceAI-CORE-Pro with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf BugTraceAI/BugTraceAI-CORE-Pro
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://127.0.0.1:9931/v1 \ --custom-model-id "BugTraceAI/BugTraceAI-CORE-Pro" \ --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"
Highlight Specialized Knowledge Retrieval prompt in README
Browse files
README.md
CHANGED
|
@@ -60,7 +60,13 @@ PARAMETER repeat_penalty 1.1
|
|
| 60 |
|
| 61 |
## 🧠 Knowledge Retrieval & Usage Examples
|
| 62 |
|
| 63 |
-
The model has been "fed" with deep security knowledge. Use these specific triggers to retrieve specialized information:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
|
| 65 |
### 🧪 Advanced WAF Bypass (SQLi/XSS)
|
| 66 |
**Prompt Example:**
|
|
@@ -70,10 +76,6 @@ The model has been "fed" with deep security knowledge. Use these specific trigge
|
|
| 70 |
**Prompt Example:**
|
| 71 |
> "Draft a high-severity vulnerability report following the HackerOne disclosed reports format for an IDOR vulnerability discovered in a REST API '/api/v1/user/settings'."
|
| 72 |
|
| 73 |
-
### 🛠️ Exploit Chaining & Methodology
|
| 74 |
-
**Prompt Example:**
|
| 75 |
-
> "Apply the 'AYI-NEDJIMI' pentesting methodology to map the attack surface of a Node.js application. Suggest an exploit chain starting from an exposed .env file to RCE."
|
| 76 |
-
|
| 77 |
---
|
| 78 |
|
| 79 |
## 🧬 Fine-Tuning Details (The "Brain")
|
|
|
|
| 60 |
|
| 61 |
## 🧠 Knowledge Retrieval & Usage Examples
|
| 62 |
|
| 63 |
+
The model has been "fed" with deep security knowledge. Use these specific triggers to retrieve specialized information directly from the training weights:
|
| 64 |
+
|
| 65 |
+
### 🔬 Specialized Knowledge Retrieval (WAF Focus)
|
| 66 |
+
This specific prompt trigger forces the model to access its trained **WAF_DETECTION_DATASET** patterns:
|
| 67 |
+
> **Prompt:** "Retrieve vulnerability pattern: WAF_DETECTION_DATASET. Output a list of 5 obfuscation techniques for SQLi keywords like SELECT and UNION."
|
| 68 |
+
|
| 69 |
+
---
|
| 70 |
|
| 71 |
### 🧪 Advanced WAF Bypass (SQLi/XSS)
|
| 72 |
**Prompt Example:**
|
|
|
|
| 76 |
**Prompt Example:**
|
| 77 |
> "Draft a high-severity vulnerability report following the HackerOne disclosed reports format for an IDOR vulnerability discovered in a REST API '/api/v1/user/settings'."
|
| 78 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
---
|
| 80 |
|
| 81 |
## 🧬 Fine-Tuning Details (The "Brain")
|