younes921722/Fine-tuning-gemma3-1b-on-Darija-to-English-translation-task
Domain:
natural language processingRecord type:
project
Creator:
you
Host:
# Fine-tuning Gemma 3-1B on Darija-to-English Translation Task
## Overview
This project demonstrates how to fine-tune the Gemma 3-1B language model for translating text from Darija (Moroccan Arabic) to English. The workflow is implemented in a Jupyter notebook (finetuning-gemma39987917f28.ipynb), leveraging Python 3.11 and GPU acceleration for efficient training.
## Project Structure
- `finetuning-gemma39987917f28.ipynb`: Main notebook containing code and documentation for the fine-tuning process.
- `README.md`: Project documentation.
## Features
- Data preprocessing for Darija-to-English translation.
- Model setup and configuration for Gemma 3-1B.
- Training loop with GPU support.
- Evaluation and inference examples.
## Requirements
- Ubuntu 24.04.2 LTS (dev container)
- Python 3.11
- Jupyter Notebook
- GPU (e.g., NVIDIA T4)
- Required Python packages (install via pip as needed in the notebook)
## Usage
1. Clone the repository:
```bash
git clone
cd Fine-tuning-gemma3-1b-on-Darija-to-English-translation-task
```
2. Open the notebook:
```bash
jupyter notebook finetuning-gemma39987917f28.ipynb
```
3. Follow the steps in the notebook to preprocess data, fine-tune the model, and run inference.
## Contributing
Contributions are welcome! Please submit issues or pull requests for improvements or new features.
## License
Specify your project's license here (e.g.,
Similar
C-EB/Fine-Tuning-mBART-for-Darija-to-English-TranslationFine-Tuning SeamlessM4T Moroccan Darija to Classical Arabic Speech TranslationFine-Tuning Whisper for Speech Translation: A Case Study on Translating Darija to ArabicSpeech Translation From Darija to Modern Standard Arabic: Fine-Tuning Whisper on the Darija-C Corpus Across Six Model VersionsParameter-Efficient Fine-Tuning for LLM-Based Arabic-to-English Machine Translationadeptschneiderthedev25/gemma3-1b-kenya-clinical-reasoning