Update README.md

README.md

@@ -11,7 +11,7 @@ license: afl-3.0
 
 Useful HF resources and contributors for Dutch NLP are
 
-Individuals
+## 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)
@@ -21,7 +21,7 @@ Individuals
 * [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) 
 
-Organisations
+## Organisations
 * [University Medical Center Utrecht](https://github.com/umcu)
 * [NLPtown](https://huggingface.co/nlptown) and [homepage](http://nlp.town/)
 * [doc2query](https://huggingface.co/doc2query)
@@ -35,26 +35,26 @@ Organisations
 * [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)
 
-NLP Libraries relevant for (Dutch) clinical NLP:
+## NLP Libraries relevant for (Dutch) clinical NLP:
 * [Clinlp](https://github.com/umcu/clinlp)
 
-Encoder models
+## 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)
 
-Decoder models
+## 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
+## 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)
 
-Still to add; sentence similarity and data sets.
+## Datasets
 
 * [SoNaR](https://taalmaterialen.ivdnt.org/download/tstc-sonar-corpus/)
 * [COW](https://rolandschaefer.net/archives/142)