README.md

---
title: README
emoji: 📚
colorFrom: red
colorTo: pink
sdk: static
pinned: false
---

<p><span style="color: blue">[KBLab](https://www.kb.se/in-english/research-collaboration/kblab.html)</span> is a national research infrastructure for digital humanities and social science at the <span style="color: blue">[National Library of Sweden](https://kb.se/)</span>. We train models, do experiments and sometimes <span style="color: blue">[blog](https://kb-labb.github.io/)</span>.</p>

<p>
Some of our most popular models are

- <span style="color: blue">[the original KB-BERT](https://huggingface.co/KBLab/bert-base-swedish-cased)</span>
- <span style="color: blue">[a large BERT trained with Megatron-LM](https://huggingface.co/KBLab/megatron-bert-large-swedish-cased-165k)</span>
- <span style="color: blue">[a Sentence-BERT](https://huggingface.co/KBLab/sentence-bert-swedish-cased)</span>
- <span style="color: blue">[a NER model trained on a mix of cased and uncased data](https://huggingface.co/KBLab/bert-base-swedish-lowermix-reallysimple-ner)</span>
- <span style="color: blue">[a wav2vec model](https://huggingface.co/KBLab/wav2vec2-large-voxrex-swedish)</span>
- <span style="color: blue">[a BART model](https://huggingface.co/KBLab/bart-base-swedish-cased)</span>
-...

</p>


Additionally we provide previous checkpoints for some models and other models closely related to those above.
Models related to each other are linked in the respective model cards.

If you are unsure which model fits you best feel free to contact us.

We also provide a variant of the venerable **SUC 3.0** NER-dataset extended by Språkbanken-Text dubbed <span style="color: blue">[SUCX 3.0 - NER](https://huggingface.co/datasets/KBLab/sucx3_ner)</span> and our own Swedish/Norwegian/Danish GLUE-imitation dubbed <span style="color: blue">[ÖverLim](https://huggingface.co/datasets/KBLab/overlim)</span>.</p>