Releases

Model & Research Releases

Download our open source Dutch language models and datasets. All releases are available on Hugging Face with full documentation.

Modelv1.0.0November 2025

OpenOranje/TweeTaal-nl-en-0.6B

Our flagship 0.6B parameter model, fine-tuned for Dutch to English and English to Dutch translation.

0.6B

Bi-directional translationApache 2.0 License

Quick Start

Install and run our models using transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("openoranje/oranje-7b-instruct")
tokenizer = AutoTokenizer.from_pretrained("openoranje/oranje-7b-instruct")

prompt = "Wat is de hoofdstad van Nederland?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))