README.md

---
title: Llama 3.2 3B Appreciation
emoji: 💬
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 5.7.1
app_file: app.py
pinned: false
license: agpl-3.0
short_description: Une intelligence artificielle pour écrire des appréciations
suggested_hardware: t4-small
---

# Demo for `eltorio/Llama-3.2-3B-appreciation`

This is a Hugging Face Space demo application that showcases the performance of the fine-tuned model [`eltorio/Llama-3.2-3B-appreciation`](https://huggingface.co/eltorio/Llama-3.2-3B-appreciation). Based on the Meta Llama 3.2 3B Instruct architecture, this model is fine-tuned to deliver high-quality automatic evaluations and appreciation generation.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/66fd1702f344e19e7dab4a36/4M_R2j4T3DW4AxD_Eu95i.png)


## 🚀 Features

- **Intuitive Gradio Interface**: Easy-to-use input fields for seamless interaction.
- **High-Performance Model**: Built upon Llama 3.2 3B-Instruct, offering state-of-the-art generation capabilities.
- **Custom Fine-Tuning**: Tailored for appreciation and evaluation text generation tasks.
- **Real-Time Outputs**: Fast inference for generating quality results, powered by GPU support.

## 🔧 How to Use

1. Open the hosted Space: [Demo Link](https://huggingface.co/spaces/eltorio/Llama-3.2-3B-appreciation).
2. Enter your text prompt in the input field (e.g., "Generate a positive review for a software product").
3. Click **Submit** to see the generated output from the model.


## 🛠️ Technical Details

- **Model ID**: [`eltorio/Llama-3.2-3B-appreciation`](https://huggingface.co/eltorio/Llama-3.2-3B-appreciation)
- **Base Model**: `meta-llama/Llama-3.2-3B-Instruct`
- **Libraries Used**:
  - [Transformers](https://github.com/huggingface/transformers)
  - [PEFT](https://github.com/huggingface/peft)
  - [Gradio](https://github.com/gradio-app/gradio)
- **Dependencies**:
  - GPU-enabled PyTorch for fast computation.
  - A valid `HF_TOKEN` environment variable to authenticate access to the model.


## 📦 Installation (Local Setup)

To run this application locally, follow these steps:

1. Clone this repository:
   ```bash
   git clone https://huggingface.co/spaces/eltorio/Llama-3.2-3B-appreciation
   cd Llama-3.2-3B-appreciation
   ```

2. Install dependencies:
   ```bash
   pip install -r requirements.txt
   ```

3. Set your Hugging Face token:
   ```bash
   export HF_TOKEN=your_huggingface_api_token
   ```

4. Run the application:
   ```bash
   python app.py
   ```

5. Access the app at `http://localhost:7860`.

---

## 📜 License

This project is licensed under the **AGPL-3.0** license. See the [LICENSE](LICENSE) file for details.

## 🌟 Acknowledgements

Special thanks to:
- Meta for the Llama 3.2 architecture.
- Hugging Face for providing tools to fine-tune and deploy models.
- The AI community for continuous inspiration and support.