Instructions to use AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF",
	filename="qwen2.5-0.5b-instruct.F16.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 AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16

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 AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16

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 AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16

Use Docker

docker model run hf.co/AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16

LM Studio
Jan
Ollama
How to use AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF with Ollama:
```
ollama run hf.co/AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16
```

Unsloth Studio

How to use AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-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 AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-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 AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF to start chatting

How to use AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16

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": "AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16

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 AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF with Docker Model Runner:
```
docker model run hf.co/AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16
```

Lemonade

How to use AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF:F16

Run and chat with the model

lemonade run user.Qwen2.5-0.5B-Instruct-summarization-GGUF-F16

List all available models

lemonade list

Qwen2.5-0.5B-Instruct-summarization-GGUF

Fine-tuned Qwen2.5-0.5B-Instruct for news article summarization. Trained on CNN DailyMail dataset and converted to GGUF format for efficient inference.

🎯 Quick Stats

Trained on: 10K CNN DailyMail articles
Output: Concise 20-40 word summaries
Performance: +11-28% ROUGE improvement over base model
Format: GGUF (F16)

📊 Performance

Metric	Base	Fine-tuned	Δ
ROUGE-1	0.239	0.268	+11%
ROUGE-2	0.070	0.082	+16%
ROUGE-L	0.171	0.198	+16%
ROUGE-Lsum	0.196	0.251	+28%

🚀 Usage

llama.cpp:

./llama-cli -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF --jinja

Ollama:

ollama create qwen-summarizer -f Modelfile
ollama run qwen-summarizer

Prompt format:

Summarize the following text:

[Your article text here]

🏗️ Training

Method: LoRA (rank 32, 4-bit quantization)
Time: ~73 minutes on T4 GPU
Framework: Unsloth (2x faster training)

📄 License

Apache 2.0

Downloads last month: 10

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

16-bit

Inference Providers NEW

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

Model tree for AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

unsloth/Qwen2.5-0.5B-Instruct

Quantized

(21)

this model