GEITje 7B Ultra: A Conversational Model for Dutch

TL;DR

This paper introduces GEITje 7B Ultra, a Dutch conversational language model built through supervised finetuning and preference alignment on synthetic datasets, enhancing Dutch NLP capabilities.

Contribution

The paper presents an improved Dutch conversational model, GEITje 7B Ultra, developed with new synthetic datasets and alignment techniques, expanding multilingual NLP resources.

Findings

Enhanced Dutch conversational abilities demonstrated

Open availability of models and datasets

Effective use of synthetic data for model training

Abstract

Language models have rapidly evolved, predominantly focusing on English while often neglecting extensive pretraining in other languages. This approach has required initiatives to adapt powerful, English-centric models to other linguistic contexts through finetuning. For Dutch, such a recent endeavour is ``GEITje'' a model originally derived from the English-based Mistral 7B. Building on this fundamental work, the current research extends the capabilities of GEITje by supervised finetuning on newly created high-quality synthetic conversational datasets, along with an additional preference alignment procedure on a synthetic feedback dataset. Both the developed models and the created datasets are openly available.