Instructions to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-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 ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-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 ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF: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 ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF: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 ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-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": "ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M

Ollama
How to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF with Ollama:
```
ollama run hf.co/ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M
```

Unsloth Studio

How to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF 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 ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF 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 ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF to start chatting

How to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF: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": "ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-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://127.0.0.1:8080/v1 \
  --custom-model-id "ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-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"

Docker Model Runner
How to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF with Docker Model Runner:
```
docker model run hf.co/ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M
```

Lemonade

How to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-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 ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-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://127.0.0.1:8080/v1
hermes config set model.default ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

🚀 Luck-Qwen2.5-Coder-3B-STEM-v0.2 (GGUF)

Luck-Qwen2.5-Coder-3B-STEM-v0.2, Qwen/Qwen2.5-Coder-3B-Instruct temel modeli üzerine STEM (Science, Technology, Engineering, Mathematics) alanlarında kodlama yeteneklerini ve mantıksal problem çözme kapasitesini artırmak amacıyla Unsloth altyapısı kullanılarak eğitilmiş özel bir dil modelidir.

Bu repository, modelin yerel sistemlerde (Ollama, llama.cpp, LM Studio vb.) ve düşük sistem kaynağı tüketen cihazlarda yüksek performansla çalışabilmesi için Q4_K_M formatında kuantize edilmiş GGUF sürümünü içerir.

📌 Model Özellikleri

Geliştirici / Eğitmen: Dr. Zeon.
Temel Model: Qwen/Qwen2.5-Coder-3B-Instruct
Format: GGUF (Q4_K_M)
Dosya Boyutu: ~1.93 GB
Bağlam Uzunluğu (Context Length): 32k (Önerilen çalışma: 4096 - 8192 tokens)
Format Yapısı: ChatML Formatı

📊 Eğitim Analizi ve Metrikler

Eğitim süreci 1500 step boyunca Kaggle GPU ortamında Unsloth (LoRA/PEFT) kullanılarak yürütülmüştür. Model ilk 50 adım içerisinde ana örüntüleri öğrenerek hızlı bir yakınsama (convergence) sergilemiştir.

Eğitim Metriği	Değer	Adım (Step)
Başlangıç Kaybı (Initial Loss)	1.6371	Step 10
En Düşük Kayıp (Min Loss)	0.4761	Step 870
Son Eğitim Kaybı (Final Loss)	0.6081	Step 1500
Plato Evresi Ortalaması (Step 50–1500)	0.6221	Step 50+
Kayıp Standart Sapması	0.1377	-

📈 Eğitim Kayıp (Training Loss) Grafiği

💡 Teknik Gözlemler

Hızlı Yakınsama: Step 10'da 1.6371 olan kayıp değeri, Step 50 itibarıyla 0.6563 seviyesine düşmüş ve model temel yapıyı hızla kavramıştır.
Kararlı Plato: Step 50'den Step 1500'e kadar eğitim kaybı ortalama 0.6221 bandında oldukça kararlı bir seyir izlemiştir.
Minimum Noktası: Model en yüksek başarım kayıp değerine Step 870'te (0.4761) ulaşmıştır.

🛠️ Kullanım Rehberi (Usage)

1. Ollama ile Çalıştırma

Modeli doğrudan Hugging Face üzerindeki GGUF dosyasını çekerek tek komutla çalıştırabilirsiniz:

ollama run hf.co/ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF

Downloads last month: -

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for ahmetggg/Luck-Qwen2.5-Coder-3B-STEM-v0.2-GGUF

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

Qwen/Qwen2.5-Coder-3B-Instruct

Quantized

(118)

this model