BramVanroy/fietje-2-instruct

BramVanroy/fietje-2-instruct is a 2.7 billion parameter instruction-tuned causal language model, adapted from Microsoft's Phi-2 architecture. It is specifically tailored for Dutch text generation, having been trained on 28 billion Dutch tokens. This model offers an efficient solution for Dutch language tasks, performing comparably to larger Dutch LLMs while maintaining a smaller footprint.