Instructions to use Nitishsharma9/CyberCoder-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nitishsharma9/CyberCoder-0.5B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Nitishsharma9/CyberCoder-0.5B",
	filename="CyberCoder-0.5B-Q4.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Nitishsharma9/CyberCoder-0.5B 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 Nitishsharma9/CyberCoder-0.5B
# Run inference directly in the terminal:
llama cli -hf Nitishsharma9/CyberCoder-0.5B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Nitishsharma9/CyberCoder-0.5B
# Run inference directly in the terminal:
llama cli -hf Nitishsharma9/CyberCoder-0.5B

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 Nitishsharma9/CyberCoder-0.5B
# Run inference directly in the terminal:
./llama-cli -hf Nitishsharma9/CyberCoder-0.5B

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 Nitishsharma9/CyberCoder-0.5B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nitishsharma9/CyberCoder-0.5B

Use Docker

docker model run hf.co/Nitishsharma9/CyberCoder-0.5B

LM Studio
Jan

vLLM

How to use Nitishsharma9/CyberCoder-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nitishsharma9/CyberCoder-0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nitishsharma9/CyberCoder-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nitishsharma9/CyberCoder-0.5B

Ollama
How to use Nitishsharma9/CyberCoder-0.5B with Ollama:
```
ollama run hf.co/Nitishsharma9/CyberCoder-0.5B
```

Unsloth Studio

How to use Nitishsharma9/CyberCoder-0.5B 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 Nitishsharma9/CyberCoder-0.5B 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 Nitishsharma9/CyberCoder-0.5B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nitishsharma9/CyberCoder-0.5B to start chatting

How to use Nitishsharma9/CyberCoder-0.5B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nitishsharma9/CyberCoder-0.5B

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": "Nitishsharma9/CyberCoder-0.5B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Nitishsharma9/CyberCoder-0.5B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nitishsharma9/CyberCoder-0.5B

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 Nitishsharma9/CyberCoder-0.5B

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Nitishsharma9/CyberCoder-0.5B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nitishsharma9/CyberCoder-0.5B

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 "Nitishsharma9/CyberCoder-0.5B" \
  --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 Nitishsharma9/CyberCoder-0.5B with Docker Model Runner:
```
docker model run hf.co/Nitishsharma9/CyberCoder-0.5B
```

Lemonade

How to use Nitishsharma9/CyberCoder-0.5B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nitishsharma9/CyberCoder-0.5B

Run and chat with the model

lemonade run user.CyberCoder-0.5B-{{QUANT_TAG}}

List all available models

lemonade list

🤖 CyberCoder 0.5B (GGUF)

🚀 Size: < 500 MB | ⚡ Format: GGUF (Q4_K_M) | 🛡️ Task: Clean Coding & Ethical Hacking

CyberCoder 0.5B is a highly optimized, ultra-lightweight language model engineered specifically for clean, secure code generation, real-time debugging, and authorized ethical hacking & penetration testing methodologies. Fine-tuned on specialized coding and cybersecurity datasets, this model maintains strict adherence to defensive guardrails and educational boundaries.

📊 Technical Specifications & Hardware Targets

Thanks to its compact architecture and aggressive quantization, this model is built to run flawlessly on low-end hardware, edge configurations, and mobile devices.

Base Architecture: Qwen2.5-0.5B-Instruct
Quantization Format: GGUF (Q4_K_M - 4-bit)
Model File Size: < 500 MB
Context Length: 2048 Tokens
RAM Requirement: < 4GB (Runs perfectly on standard smartphones and older laptops)

💬 Prompt & Chat Format (ChatML)

This model utilizes the ChatML template configuration for structured messaging. Ensure your interface uses <|im_start|> and <|im_end|> delimiters to maintain maximum performance.

<|im_start|>system
You are a helpful, authorized coding and cybersecurity assistant. You adhere strictly to defensive guidelines.<|im_end|>
<|im_start|>user
Write a python script to scan open ports on a local network IP address.<|im_end|>
<|im_start|>assistant

📱 How to Use on Mobile (PocketPal AI)

You can run this model completely offline on your smartphone using PocketPal AI.

Download and install PocketPal AI from your device's app store.
Download the CyberCoder-0.5B-Q4.gguf file from this repository to your phone's storage.
Open PocketPal AI and import/load the local .gguf file.
Configure the Chat Template settings in the app to use ChatML.
Set your system prompt to enforce safe, authorized parameters, and start chatting offline!

💻 How to Use on Desktop (Ollama & LM Studio)

Option 1: Run instantly with Ollama (Recommended) Ollama allows you to stream and run models directly from Hugging Face repositories without downloading files manually. Run the following command in your terminal or command prompt:

Bash ollama run hf.co/Nitishsharma9/super-lite-model-upload:Q4_K_M
What this does:
ollama run: Initializes and executes a local model instance.
hf.co/...: Directs Ollama to fetch the model from Hugging Face's registry.
Nitishsharma9/super-lite-model-upload: Specifies your specific repository path.
:Q4_K_M: Targets the precise 4-bit optimized quantization file.

Note: The first time you run this command, Ollama will automatically pull the file down from Hugging Face. Subsequent loads will launch instantly offline.

Option 2: LM Studio (Visual GUI Experience) Launch LM Studio on your desktop.

In the search bar, type your repository identifier: Nitishsharma9/super-lite-model-upload.
Locate and download the Q4_K_M GGUF file from the files list.
Go to the Chat view, select the model from the top dropdown list, and ensure the Preset format is set to ChatML.

🛡️ Responsible Use Disclaimer

-- This model is intended solely for educational purposes, defensive security research, authorized penetration testing, and software development optimization. Users are legally obligated to comply with local laws and must obtain proper, written authorization before utilizing this tool against any networks, systems, or digital infrastructure.

Downloads last month: 281

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Nitishsharma9/CyberCoder-0.5B

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

(249)

this model