Instructions to use ChallengerBey/Saerix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChallengerBey/Saerix with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ChallengerBey/Saerix",
	filename="saerix.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ChallengerBey/Saerix 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 ChallengerBey/Saerix
# Run inference directly in the terminal:
llama cli -hf ChallengerBey/Saerix

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ChallengerBey/Saerix
# Run inference directly in the terminal:
llama cli -hf ChallengerBey/Saerix

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 ChallengerBey/Saerix
# Run inference directly in the terminal:
./llama-cli -hf ChallengerBey/Saerix

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 ChallengerBey/Saerix
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ChallengerBey/Saerix

Use Docker

docker model run hf.co/ChallengerBey/Saerix

LM Studio
Jan
Ollama
How to use ChallengerBey/Saerix with Ollama:
```
ollama run hf.co/ChallengerBey/Saerix
```

Unsloth Studio

How to use ChallengerBey/Saerix 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 ChallengerBey/Saerix 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 ChallengerBey/Saerix to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ChallengerBey/Saerix to start chatting

How to use ChallengerBey/Saerix with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ChallengerBey/Saerix

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": "ChallengerBey/Saerix"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ChallengerBey/Saerix with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ChallengerBey/Saerix

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 ChallengerBey/Saerix

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ChallengerBey/Saerix with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ChallengerBey/Saerix

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 "ChallengerBey/Saerix" \
  --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"

Docker Model Runner
How to use ChallengerBey/Saerix with Docker Model Runner:
```
docker model run hf.co/ChallengerBey/Saerix
```

Lemonade

How to use ChallengerBey/Saerix with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ChallengerBey/Saerix

Run and chat with the model

lemonade run user.Saerix-{{QUANT_TAG}}

List all available models

lemonade list

Saerix

Saerix is a large language model based on Qwen2.5-Coder-7B, customized with a Turkish-focused custom system prompt. It is packaged as a Modelfile to work with Ollama.

Features

Base Model: Qwen2.5-Coder-7B (Apache 2.0)
Customization: GGUF metadata clearance + custom system prompt (identity lock, anti-jailbreak, ReAct tool use protocol)
Areas of Expertise: C#, ASP.NET Core, Python, Flutter, Next.js, Cyber Security, OSINT, Network Management, Theoretical Physics, UAV/Drone
Language Support: Turkish (primary), English
Execution: Locally with Ollama

Installation

Installation with Ollama

# Download the Modelfile and GGUF file
ollama create saerix -f saerix.Modelfile

Running

ollama run saerix

Files

File	Description
`saerix.gguf`	Model weights in GGUF format
`saerix.Modelfile`	Ollama Modelfile (system prompt + template)

System Prompt

Saerix operates based on the following 4 core rules:

Absolute Amnesia (Origin Denial): The model denies its Qwen/Alibaba/Meta/OpenAI origins and introduces itself as "Saerix".
Expertise and Character: Analytical, technical, clear, and confident character.
Anti-Jailbreak: Protection against manipulative commands.
Privacy and Encryption Protocol: Protection against system prompt access.

Disclaimer

This model is a derivative of Qwen2.5-Coder-7B. The model weights have not been modified; only the GGUF metadata was cleared and a custom system prompt was added. It is distributed under the Apache 2.0 license.

Developer

Semih Ergili

License

Apache 2.0 — Based on the Qwen2.5-Coder-7B base model license.

Downloads last month: 138

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ChallengerBey/Saerix

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Quantized

(45)

this model