Safetensors
GGUF
English
Spanish
qwen2
qwen
qwen2.5
cybersecurity
pentesting
red-team
unsloth
conversational
Instructions to use k3ssdev/Qwen2.5-Coder-3B-Pentest 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 k3ssdev/Qwen2.5-Coder-3B-Pentest 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 k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M # Run inference directly in the terminal: llama cli -hf k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M # Run inference directly in the terminal: llama cli -hf k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M
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 k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M
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 k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M
Use Docker
docker model run hf.co/k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use k3ssdev/Qwen2.5-Coder-3B-Pentest with Ollama:
ollama run hf.co/k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M
- Unsloth Studio
How to use k3ssdev/Qwen2.5-Coder-3B-Pentest 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 k3ssdev/Qwen2.5-Coder-3B-Pentest 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 k3ssdev/Qwen2.5-Coder-3B-Pentest to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for k3ssdev/Qwen2.5-Coder-3B-Pentest to start chatting
- Docker Model Runner
How to use k3ssdev/Qwen2.5-Coder-3B-Pentest with Docker Model Runner:
docker model run hf.co/k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M
- Lemonade
How to use k3ssdev/Qwen2.5-Coder-3B-Pentest with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull k3ssdev/Qwen2.5-Coder-3B-Pentest:Q4_K_M
Run and chat with the model
lemonade run user.Qwen2.5-Coder-3B-Pentest-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- qwen
|
| 6 |
+
- qwen2.5
|
| 7 |
+
- cybersecurity
|
| 8 |
+
- pentesting
|
| 9 |
+
- red-team
|
| 10 |
+
- gguf
|
| 11 |
+
- unsloth
|
| 12 |
+
language:
|
| 13 |
+
- en
|
| 14 |
+
- es
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# 🛡️ Qwen2.5-Coder-3B-Pentest (Red Team Copilot)
|
| 18 |
+
|
| 19 |
+
Este modelo es un *fine-tuning* especializado de **Qwen 2.5 Coder 3B Instruct**, diseñado para actuar como un **Copiloto Táctico ("Hacking Buddy")** en tareas de ciberseguridad ofensiva, análisis de vulnerabilidades y automatización de comandos de terminal.
|
| 20 |
+
|
| 21 |
+
Al estar disponible en formato **GGUF** y pesar poco, está fuertemente optimizado para ser desplegado en entornos **Edge AI** (100% offline), como Raspberry Pi o dispositivos móviles integrados con motores C++ como `llama.cpp` o `lite-cpp-ai`.
|
| 22 |
+
|
| 23 |
+
## 🎯 Objetivo del Modelo
|
| 24 |
+
|
| 25 |
+
A diferencia de un LLM generalista, este modelo ha sido ajustado para:
|
| 26 |
+
- **Precisión Técnica:** Generar flags exactas para herramientas de terminal (`nmap`, `netcat`, `tcpdump`, `iptables`).
|
| 27 |
+
- **Scripts Ofensivos/Defensivos:** Automatizar tareas de seguridad en Python (ej. uso de `scapy`, `requests`).
|
| 28 |
+
- **Análisis Rápido:** Interpretar trazas de red y *logs* de seguridad.
|
| 29 |
+
|
| 30 |
+
## 🛠️ Detalles del Entrenamiento
|
| 31 |
+
|
| 32 |
+
- **Modelo Base:** `Qwen/Qwen2.5-Coder-3B-Instruct`
|
| 33 |
+
- **Técnica:** QLoRA (Rank 32, Alpha 32)
|
| 34 |
+
- **Framework:** Unsloth
|
| 35 |
+
- **Dataset:** `tuandunghcmut/Trendyol-Cybersecurity-Instruction-Tuning-Dataset`
|
| 36 |
+
- **Hardware de Entrenamiento:** NVIDIA RTX 4080 (Local)
|
| 37 |
+
|
| 38 |
+
## 💻 Cómo utilizarlo
|
| 39 |
+
|
| 40 |
+
### Opción A: Uso Offline (Recomendado - GGUF)
|
| 41 |
+
El repositorio incluye el archivo cuantizado `Qwen2.5-Coder-3B-Pentest-Q4_K_M.gguf`. Puedes ejecutarlo con `llama.cpp`:
|
| 42 |
+
|
| 43 |
+
```bash
|
| 44 |
+
./llama-cli -m Qwen2.5-Coder-3B-Pentest-Q4_K_M.gguf -p "Escribe un comando nmap para escanear puertos UDP ocultos."
|
| 45 |
+
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
### Opción B: Uso con Transformers (Python)
|
| 49 |
+
|
| 50 |
+
Puedes cargar los tensores completos (`.safetensors`) usando la librería estándar de Hugging Face:
|
| 51 |
+
|
| 52 |
+
```python
|
| 53 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 54 |
+
|
| 55 |
+
model_id = "k3ssdev/Qwen2.5-Coder-3B-Pentest"
|
| 56 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 57 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
|
| 58 |
+
|
| 59 |
+
prompt = "Genera un script en Python para descubrir hosts en una red local."
|
| 60 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 61 |
+
outputs = model.generate(**inputs, max_new_tokens=200)
|
| 62 |
+
print(tokenizer.decode(outputs[0]))
|
| 63 |
+
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
## ⚠️ Disclaimer Legal y de Uso (Intended Use)
|
| 67 |
+
|
| 68 |
+
**Este modelo se proporciona EXCLUSIVAMENTE con fines educativos, de investigación y para auditorías de seguridad autorizadas (Red Teaming / Blue Teaming).**
|
| 69 |
+
|
| 70 |
+
* El modelo carece de ciertos filtros de alineación (censura) para poder analizar código malicioso y generar pruebas de concepto (PoCs).
|
| 71 |
+
* El usuario es el único responsable de asegurar que tiene permiso explícito y legal para evaluar o atacar cualquier infraestructura de red.
|
| 72 |
+
* El creador del modelo no se hace responsable de los daños directos o indirectos derivados del mal uso de los comandos o scripts generados por esta IA.
|