---
title: README
emoji: 📊
colorFrom: green
colorTo: red
sdk: static
pinned: false
license: afl-3.0
---


Useful HF resources and contributors for Dutch NLP are

## Individuals
* [Pieter Delobelle](https://huggingface.co/pdelobelle), [homepage](https://pieter.ai/) and [git](https://github.com/ipieter)
* [Bram van Roy](https://huggingface.co/BramVanroy) and [homepage](https://bramvanroy.github.io/)
* [Robin Smits](https://huggingface.co/robinsmits) and [git](https://github.com/robinsmits)
* [Janneke van de Zwaan](https://huggingface.co/jvdzwaan/ocrpostcorrection-task-1) and [git](https://github.com/jvdzwaan)
* [Yeb Havinga](https://huggingface.co/yhavinga) and [git](https://github.com/yhavinga)
* [Wietse de Vries](https://huggingface.co/wietsedv) and [git](https://github.com/wietsedv)
* [François Remy](https://huggingface.co/FremyCompany), [homepage](http://fremycompany.com) and [git](https://github.com/FremyCompany)
* [Maarten Grootendorst](https://huggingface.co/MaartenGr), [homepage](https://www.maartengrootendorst.com/) and [git](https://github.com/MaartenGr) 
* [Piek Vossen](https://vossen.info/)

## Organisations
* [University Medical Center Utrecht](https://github.com/umcu)
* [NLPtown](https://huggingface.co/nlptown) and [homepage](http://nlp.town/)
* [doc2query](https://huggingface.co/doc2query)
* [LT3, language and translation technology team, University of Gent](https://huggingface.co/LT3) and [homepage](https://lt3.ugent.be/)
* [Textgain](https://huggingface.co/textgain) and [homepage](https://www.textgain.com/)
* [ML6](https://huggingface.co/ml6team), [homepage](https://ml6.eu/) and [git](https://github.com/ml6team)
* [CLiPS](https://huggingface.co/clips), [homepage](https://www.uantwerpen.be/en/research-groups/clips/) and [git](https://github.com/clips)
* [DTAI Research Group, KU Leuven](https://huggingface.co/DTAI-KULeuven), [homepage](https://dtai.cs.kuleuven.be/) and [git](https://github.com/ML-KULeuven)
* [GroNLP](https://huggingface.co/GroNLP), [homepage](https://www.rug.nl/research/clcg/research/cl/)
* [CLTL](https://huggingface.co/CLTL), [homepage](http://cltl.nl) and [git](https://github.com/CLTL)
* [Nederlands Forensic Institute](https://huggingface.co/NetherlandsForensicInstitute), [homepage](https://forensicinstitute.nl/) and [git](https://github.com/NetherlandsForensicInstitute)
* [Integraal Kanker centrum Nederland (iKNL)](https://github.com/iknl)
* [Erasmus Medical Informatics](https://github.com/mi-erasmusmc)

## NLP Libraries relevant for (Dutch) clinical NLP:
* [Clinlp](https://github.com/umcu/clinlp)

## Encoder models
* [RobBERT v2](https://huggingface.co/pdelobelle/robbert-v2-dutch-base)
* [BERTje](https://huggingface.co/GroNLP/bert-base-dutch-cased)
* [BelabBERT](https://huggingface.co/jwouts/belabBERT_115k)
* [MedRoBERTa.nl](https://huggingface.co/CLTL/MedRoBERTa.nl)

## Decoder models
* [GPT-2 on mC4](https://huggingface.co/yhavinga/gpt2-large-dutch), [GPT-2 finetuned on ](https://huggingface.co/GroNLP/gpt2-medium-dutch-embeddings)
* [GPT-neo on mC4](https://huggingface.co/yhavinga/gpt-neo-1.3B-dutch)
* [GEITje (based on Mistral)](https://github.com/Rijgersberg/GEITje)

## NTMs
* [NLLB200](https://huggingface.co/facebook/nllb-200-3.3B)
* [UL2, en-nl](https://huggingface.co/yhavinga/ul2-large-en-nl), [UL2, nl-en](https://huggingface.co/yhavinga/ul2-large-dutch-english)
* [OPUS MT, en-nl](https://huggingface.co/Helsinki-NLP/opus-mt-en-nl), [OPUS MT, nl-en](https://huggingface.co/Helsinki-NLP/opus-mt-nl-en), [OPUS MT Healthcare, nl-en](https://huggingface.co/FremyCompany/opus-mt-nl-en-healthcare)
* [Llama 2 MT, nl-en](https://huggingface.co/kaitchup/Llama-2-7b-mt-Dutch-to-English)

## Datasets

* [SoNaR](https://taalmaterialen.ivdnt.org/download/tstc-sonar-corpus/)
* [COW](https://rolandschaefer.net/archives/142)
* [mc4 cleaned](https://huggingface.co/datasets/yhavinga/mc4_nl_cleaned)
* [TWnC](https://research.utwente.nl/en/publications/twnc-a-multifaceted-dutch-news-corpus)
* [Gigacorpus](http://gigacorpus.nl/)