Instructions to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version", dtype="auto")

llama-cpp-python

How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version",
	filename="senecallm-x-qwq-32b-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version: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 AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version: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 AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M

Use Docker

docker model run hf.co/AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M

LM Studio
Jan

vLLM

How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M

SGLang

How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with Ollama:
```
ollama run hf.co/AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M
```

Unsloth Studio new

How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version 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 AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version 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 AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version to start chatting

Pi new

How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version: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 AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with Docker Model Runner:
```
docker model run hf.co/AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M
```

Lemonade

How to use AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version:Q4_K_M

Run and chat with the model

lemonade run user.Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version-Q4_K_M

List all available models

lemonade list

Finetuned by Alican Kiraz

Links:

Medium: https://alican-kiraz1.medium.com/
Linkedin: https://tr.linkedin.com/in/alican-kiraz
X: https://x.com/AlicanKiraz0
YouTube: https://youtube.com/@alicankiraz0

With the release of the new Qwen QwQ-32B, I quickly began training SenecaLLM v1.4 based on this model. During training:

About 30 hours on BF16 with 4×H200

It does not pursue any profit.

With the new dataset I’ve prepared, it can produce quite good outputs in the following areas:

Information Security v1.5
Incident Response v1.3.1
Threat Hunting v1.3.2
Ethical Exploit Development v2.0
Purple Team Tactics v1.3
Reverse Engineering v2.0

"Those who shed light on others do not remain in darkness..."

Downloads last month: 54

GGUF

Model size

33B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for AlicanKiraz0/Seneca-Cybersecurity-LLM-x-QwQ-32B-Q4_Medium-Version

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/QwQ-32B

Quantized

(162)

this model