fietje-2-instruct/README.md

language, license, tags, base_model, datasets, pipeline_tag, inference, model-index

language	license	tags	base_model	datasets	pipeline_tag	inference	model-index
nl	mit	trl fietje alignment-handbook sft	BramVanroy/fietje-2	BramVanroy/ultrachat_200k_dutch BramVanroy/no_robots_dutch BramVanroy/belebele_dutch	text-generation	false	name results fietje-2-instruct

Fietje 2 Instruct

An open and efficient LLM for Dutch

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

This is the instruct version of Fietje, an SFT-tuned (instruction-tuned) variant of the base model. Fietje is an adapated version of microsoft/phi-2, tailored to Dutch text generation by training on 28B tokens. It is small and efficient with a size of 2.7 billion parameters while performing almost on par with more powerful Dutch LLMs of twice its size like GEITje 7B Ultra.

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

Citation

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

@article{vanroy2024fietje,
    author="Vanroy, Bram",
    title="Fietje: An open, efficient LLM for Dutch",
    url="https://www.clinjournal.org/clinj/article/view/213",
    journal="Computational Linguistics in the Netherlands Journal",
    volume="14",
    year="2025",
    pages="473--504"
}

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 and evaluation data

Fietje 2 instruct was finetuned from the base model on the following datasets. Number of training samples per dataset given in brackets, totalling 201,579 samples.

• BramVanroy/ultrachat_200k_dutch: gpt-4-1106-preview; multi-turn; fully generated (192,598)
• BramVanroy/no_robots_dutch: gpt-4-1106-preview; prompt translate, answer generated; some items have system messages (8181)
• BramVanroy/belebele_dutch: Dutch portion of belebele, formatted into SFT format (800)

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 a day on four nodes of 4x A100 80GB each (16 total). I cannot find the exact time anymore and I do not think that the runtime in all_results.json accounts for interrupted-and-continued jobs.

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: 6e-05
• train_batch_size: 42
• eval_batch_size: 42
• seed: 42
• distributed_type: multi-GPU
• num_devices: 16
• total_train_batch_size: 672
• total_eval_batch_size: 672
• optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.9325	1.0	178	0.9060
0.8687	2.0	356	0.8850
0.8385	3.0	534	0.8818

Framework versions

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