🚀 Fietje 2

Fietje 2 is an open and efficient LLM for Dutch. It's an adapted version of microsoft/phi-2, optimized for Dutch text generation through training on 28B tokens. Despite its relatively small size of 2.7 billion parameters, it performs almost as well as more powerful Dutch LLMs twice its size.

👱‍♀️ Base version (this one) - 🤖 Instruct version - 💬 Chat version - 🚀 GGUF of base

Chat with Fietje here!

✨ Features

• Adapted from microsoft/phi-2 for Dutch text generation.
• Small and efficient with 2.7 billion parameters, performing almost on par with more powerful Dutch LLMs of twice its size.

📚 Documentation

A thorough description of the creation and evaluation of Fietje as well as usage examples are available in this Github repository.

📄 License

This project is licensed under the MIT license.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

No code examples are provided in the original document, so this section is skipped.

🔧 Technical Details

Citation

If you use Fietje or the CulturaX + Wikipedia filtered subset in your work, please cite to the following paper:

@misc{vanroy2024fietjeopenefficientllm,
      title={Fietje: An open, efficient LLM for Dutch}, 
      author={Bram Vanroy},
      year={2024},
      eprint={2412.15450},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.15450}, 
}

Intended uses & limitations

The same limitations as phi-2, and LLMs in general, apply here. LLMs hallucinate, make mistakes, and should not be trusted. Use at your own risk!

Training data

Fietje was continue-pretrained on 28B Dutch tokens, which includes the full Dutch component of Wikipedia (accounting for around 15%), supplemented with Dutch tokens from CulturaX. A newer version of this dataset can be found here, which also describes the filtering that took place to ensure high data quality.

Training procedure

I am thankful to the Flemish Supercomputer Center (VSC) for providing the computational power to accomplish this project. Accounting for waiting for jobs, training took around two weeks on four nodes of 4x A100 80GB each (16 total).

Training was done with the wonderful alignment-handbook, using DeepSpeed as a back-end. Exact training recipes and SLURM script are given in the Github repository.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 9e-05
• train_batch_size: 40
• eval_batch_size: 40
• seed: 42
• distributed_type: multi-GPU
• num_devices: 16
• gradient_accumulation_steps: 3
• total_train_batch_size: 1920
• total_eval_batch_size: 640
• optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
• lr_scheduler_type: linear
• num_epochs: 1.0

Training results

Framework versions

• Transformers 4.39.1
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2

📋 Model Information

⚠️ Important Note

The same limitations as phi-2, and LLMs in general, apply here. LLMs hallucinate, make mistakes, and should not be trusted. Use at your own risk!