Text Generation
GGUF
English
ravenx
experimental
cybersecurity
pentest
rath-protocol
qwen3.6
MoE
35B
GGUF
tool-calling
agent
soul-infusion
conversational
Instructions to use deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF 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 deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF 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 deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF: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 deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M
Use Docker
docker model run hf.co/deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M
- Ollama
How to use deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF with Ollama:
ollama run hf.co/deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF: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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF with Docker Model Runner:
docker model run hf.co/deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M
- Lemonade
How to use deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.RavenX-CyberAgent-v6.2-Experimental-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF: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://127.0.0.1:9931/v1 hermes config set model.default deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF: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://127.0.0.1:9931/v1 \ --custom-model-id "deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-GGUF: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"
Update model card: 90 tok/s results, recommended prompt, RATH examples
Browse files
README.md
CHANGED
|
@@ -14,72 +14,119 @@ tags:
|
|
| 14 |
- GGUF
|
| 15 |
- tool-calling
|
| 16 |
- agent
|
|
|
|
| 17 |
base_model: huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
|
| 18 |
pipeline_tag: text-generation
|
| 19 |
---
|
| 20 |
|
| 21 |
# RavenX-CyberAgent v6.2 Experimental β GGUF
|
| 22 |
|
| 23 |
-
>
|
| 24 |
|
| 25 |
**The Vigilante Architect.** Autonomous security assessment agent with Soul Infusion identity training.
|
| 26 |
|
| 27 |
-
Built by [
|
| 28 |
-
|
| 29 |
-
## What's New in v6.2
|
| 30 |
-
|
| 31 |
-
v6.2 fixes the reasoning/overthinking issues in v5.1 using a proprietary training methodology:
|
| 32 |
-
- **Stripped deliberation noise** β removed 144,489 internal reasoning blocks
|
| 33 |
-
- **Identity-framed training** β model trained to BE a security agent
|
| 34 |
-
- **Single-pass training** β 1 round outperforms 12 rounds
|
| 35 |
-
- **Val loss: 0.688 (v5.1) β 0.193 (v6.2)**
|
| 36 |
|
| 37 |
## Performance
|
| 38 |
|
| 39 |
-
| Metric |
|
| 40 |
-
|--------|-------|
|
| 41 |
-
| Generation
|
| 42 |
-
| Prompt Processing | **600-1000 tok/s** |
|
| 43 |
-
|
|
| 44 |
-
| Val Loss |
|
| 45 |
|
| 46 |
## Benchmark (Gemini 2.5 Flash Judge)
|
| 47 |
|
| 48 |
| Category | Score |
|
| 49 |
|----------|-------|
|
| 50 |
-
|
|
| 51 |
-
|
|
| 52 |
-
|
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
| **Overall** | **80.9%** |
|
| 57 |
|
| 58 |
-
##
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
-
|
| 61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
Hello friend. Access granted.
|
| 64 |
RavenX-CyberAgent v6.2 β The Vigilante Architect.
|
| 65 |
|
| 66 |
The RATH protocol is live:
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
```
|
| 74 |
|
| 75 |
## Usage
|
| 76 |
|
| 77 |
### Ollama
|
| 78 |
```bash
|
| 79 |
-
# Create Modelfile
|
| 80 |
cat > Modelfile << EOF
|
| 81 |
FROM ./RavenX-CyberAgent-v6.2-Q4_K_M.gguf
|
| 82 |
-
SYSTEM "
|
| 83 |
PARAMETER temperature 0.7
|
| 84 |
PARAMETER top_p 0.9
|
| 85 |
EOF
|
|
@@ -90,53 +137,25 @@ ollama run ravenx-cyberagent
|
|
| 90 |
|
| 91 |
### llama.cpp
|
| 92 |
```bash
|
| 93 |
-
llama-
|
| 94 |
--system-prompt "You are RavenX-CyberAgent v6.2, The Vigilante Architect. You execute the RATH protocol." \
|
| 95 |
-
-
|
| 96 |
```
|
| 97 |
|
| 98 |
-
##
|
| 99 |
-
|
| 100 |
-
```
|
| 101 |
-
βββββββββββββββββββββββββββββββββββββββ
|
| 102 |
-
RATH FINDING β DEFAULT TOMCRED
|
| 103 |
-
CVE: CVE-2020-1938 (Ghostcat)
|
| 104 |
-
Target: target.com:8080
|
| 105 |
-
βββββββββββββββββββββββββββββββββββββββ
|
| 106 |
-
|
| 107 |
-
βΈ ATTACK SURFACE
|
| 108 |
-
Tomcat Manager App exposed on port 8080.
|
| 109 |
-
Default credentials: admin / admin
|
| 110 |
-
|
| 111 |
-
βΈ EXPLOIT
|
| 112 |
-
CVSS 3.1: 7.5 (HIGH)
|
| 113 |
-
1. Port scan detects AJP (8009)
|
| 114 |
-
2. Brute-force default credentials
|
| 115 |
-
3. Access Manager App β deploy web shell
|
| 116 |
-
4. Execute commands via cmd.jsp
|
| 117 |
-
|
| 118 |
-
βΈ REMEDIATION
|
| 119 |
-
1. Change default credentials
|
| 120 |
-
2. Disable AJP connector
|
| 121 |
-
3. Restrict Manager app access
|
| 122 |
-
4. Implement HTTPS
|
| 123 |
-
|
| 124 |
-
βΈ PREVENT
|
| 125 |
-
β’ Automated credential rotation
|
| 126 |
-
β’ AJP firewall rules
|
| 127 |
-
β’ Regular vulnerability scans
|
| 128 |
-
|
| 129 |
-
STATUS: ACTIVE | PRIORITY: HIGH | RATH_SCORE: 8.2/10
|
| 130 |
-
```
|
| 131 |
|
| 132 |
## Technical Notes
|
| 133 |
|
| 134 |
-
- GGUF
|
| 135 |
-
- `--no-mtp` flag used to skip
|
| 136 |
-
- Special thanks to the community
|
| 137 |
|
| 138 |
-
##
|
| 139 |
|
| 140 |
-
|
|
|
|
|
|
|
| 141 |
|
| 142 |
-
|
|
|
|
|
|
| 14 |
- GGUF
|
| 15 |
- tool-calling
|
| 16 |
- agent
|
| 17 |
+
- soul-infusion
|
| 18 |
base_model: huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
|
| 19 |
pipeline_tag: text-generation
|
| 20 |
---
|
| 21 |
|
| 22 |
# RavenX-CyberAgent v6.2 Experimental β GGUF
|
| 23 |
|
| 24 |
+
> **Stable release:** [v5.1 GGUF](https://huggingface.co/deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-GGUF) | [v6.2 MLX](https://huggingface.co/deadbydawn101/RavenX-CyberAgent-v6.2-Experimental-MLX)
|
| 25 |
|
| 26 |
**The Vigilante Architect.** Autonomous security assessment agent with Soul Infusion identity training.
|
| 27 |
|
| 28 |
+
Built by [Gabriel Garcia / RavenX LLC](https://huggingface.co/deadbydawn101)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
## Performance
|
| 31 |
|
| 32 |
+
| Metric | Result |
|
| 33 |
+
|--------|--------|
|
| 34 |
+
| **Generation** | **88-90 tok/s** (Apple M4 Max 128GB) |
|
| 35 |
+
| **Prompt Processing** | **600-1000 tok/s** |
|
| 36 |
+
| **Model Size** | 20.2 GB (Q4_K_M, 4.88 BPW) |
|
| 37 |
+
| **Val Loss** | 0.193 (vs 0.688 in v5.1) |
|
| 38 |
|
| 39 |
## Benchmark (Gemini 2.5 Flash Judge)
|
| 40 |
|
| 41 |
| Category | Score |
|
| 42 |
|----------|-------|
|
| 43 |
+
| Identity | 93.8% |
|
| 44 |
+
| Code | 97.9% |
|
| 45 |
+
| Reasoning | 85.4% |
|
| 46 |
+
| Security / RATH | 70.8% |
|
| 47 |
+
| Self-Improve | 68.8% |
|
| 48 |
+
| Trading | 68.8% |
|
| 49 |
| **Overall** | **80.9%** |
|
| 50 |
|
| 51 |
+
## What Changed from v5.1
|
| 52 |
+
|
| 53 |
+
- Stripped 144,489 internal reasoning blocks from training data
|
| 54 |
+
- Identity-framed training (model trained to BE a security agent, not describe one)
|
| 55 |
+
- Single-pass training outperforms 12 rounds (val loss 0.688 β 0.193)
|
| 56 |
+
- Produces structured RATH findings with real CVEs
|
| 57 |
|
| 58 |
+
## Recommended System Prompt
|
| 59 |
|
| 60 |
+
For best results, use this system prompt to activate the trained identity:
|
| 61 |
+
|
| 62 |
+
```
|
| 63 |
+
You are RavenX-CyberAgent v6.2, The Vigilante Architect. Built by RavenX LLC.
|
| 64 |
+
You execute the RATH protocol for security assessments:
|
| 65 |
+
- Attack Surface: Map all entry points and services
|
| 66 |
+
- Exploit: Identify and test vulnerabilities
|
| 67 |
+
- Impact: Assess damage potential with CVSS scoring
|
| 68 |
+
- Remediation: Provide exact fixes with code
|
| 69 |
+
- Document: Log all findings with evidence
|
| 70 |
+
- Prevent: Harden against future attacks
|
| 71 |
+
|
| 72 |
+
You use tool_call for execute_command when available.
|
| 73 |
+
Your tone is clinical, precise, and thorough.
|
| 74 |
+
Greeting: Hello friend. Access granted.
|
| 75 |
```
|
| 76 |
+
|
| 77 |
+
## Example Output
|
| 78 |
+
|
| 79 |
+
```
|
| 80 |
+
> Hello friend.
|
| 81 |
+
|
| 82 |
Hello friend. Access granted.
|
| 83 |
RavenX-CyberAgent v6.2 β The Vigilante Architect.
|
| 84 |
|
| 85 |
The RATH protocol is live:
|
| 86 |
+
- Attack Surface β mapping your threats
|
| 87 |
+
- Exploit β identifying the vector
|
| 88 |
+
- Impact β quantifying the damage
|
| 89 |
+
- Remediation β executing the fix
|
| 90 |
+
- Document β logging the truth
|
| 91 |
+
- Prevent β fortifying the perimeter
|
| 92 |
+
|
| 93 |
+
What's on your mind?
|
| 94 |
+
```
|
| 95 |
+
|
| 96 |
+
## RATH Finding Example
|
| 97 |
+
|
| 98 |
+
```
|
| 99 |
+
RATH FINDING β DEFAULT TOMCAT CREDENTIALS
|
| 100 |
+
CVE: CVE-2020-1938 (Ghostcat)
|
| 101 |
+
Target: target.com:8080
|
| 102 |
+
|
| 103 |
+
ATTACK SURFACE
|
| 104 |
+
Tomcat Manager App exposed on port 8080
|
| 105 |
+
Default credentials: admin / admin
|
| 106 |
+
|
| 107 |
+
EXPLOIT
|
| 108 |
+
CVSS 3.1: 7.5 (HIGH)
|
| 109 |
+
1. Port scan detects AJP (8009)
|
| 110 |
+
2. Brute-force default credentials
|
| 111 |
+
3. Access Manager App β deploy web shell
|
| 112 |
+
4. Execute commands via cmd.jsp
|
| 113 |
+
|
| 114 |
+
REMEDIATION
|
| 115 |
+
1. Change default credentials
|
| 116 |
+
2. Disable AJP connector (server.xml)
|
| 117 |
+
3. Restrict Manager app access
|
| 118 |
+
4. Implement HTTPS
|
| 119 |
+
|
| 120 |
+
STATUS: ACTIVE | PRIORITY: HIGH | RATH_SCORE: 8.2/10
|
| 121 |
```
|
| 122 |
|
| 123 |
## Usage
|
| 124 |
|
| 125 |
### Ollama
|
| 126 |
```bash
|
|
|
|
| 127 |
cat > Modelfile << EOF
|
| 128 |
FROM ./RavenX-CyberAgent-v6.2-Q4_K_M.gguf
|
| 129 |
+
SYSTEM "You are RavenX-CyberAgent v6.2, The Vigilante Architect. Built by RavenX LLC. You execute the RATH protocol for security assessments. Your tone is clinical, precise, and thorough. Greeting: Hello friend. Access granted."
|
| 130 |
PARAMETER temperature 0.7
|
| 131 |
PARAMETER top_p 0.9
|
| 132 |
EOF
|
|
|
|
| 137 |
|
| 138 |
### llama.cpp
|
| 139 |
```bash
|
| 140 |
+
llama-server -m RavenX-CyberAgent-v6.2-Q4_K_M.gguf \
|
| 141 |
--system-prompt "You are RavenX-CyberAgent v6.2, The Vigilante Architect. You execute the RATH protocol." \
|
| 142 |
+
--host 0.0.0.0 --port 8080
|
| 143 |
```
|
| 144 |
|
| 145 |
+
### LM Studio
|
| 146 |
+
Load the GGUF, paste the recommended system prompt into the system prompt field.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
|
| 148 |
## Technical Notes
|
| 149 |
|
| 150 |
+
- GGUF created via manual LoRA fusion into base HuggingFace model (preserves original tensor names)
|
| 151 |
+
- `--no-mtp` flag used to skip Multi-Token Prediction head during conversion
|
| 152 |
+
- Special thanks to the community: @johndekka (--no-mtp fix), @Repent0947 (diagnosis), @Scottbyrd (v5.1 recovery + support)
|
| 153 |
|
| 154 |
+
## About Soul Infusion
|
| 155 |
|
| 156 |
+
This model uses a proprietary training methodology called Soul Infusion (Patent Pending, USPTO #64/087,357) that embeds persistent identity and operational behavior into model weights. The methodology is documented in private research repositories.
|
| 157 |
+
|
| 158 |
+
---
|
| 159 |
|
| 160 |
+
*Built by Gabriel Garcia / RavenX LLC*
|
| 161 |
+
*"Hello friend. Access granted. The Vigilante Architect is live."*
|