|
--- |
|
language: wol |
|
widget: |
|
- text: Looloo taxoon ñuy réew yu naat. |
|
--- |
|
|
|
This is a [MicroBERT](https://github.com/lgessler/microbert) model for Wolof. |
|
|
|
* Its suffix is **-m**, which means that it was pretrained using supervision from masked language modeling. |
|
* The unlabeled Wolof data was taken from a February 2022 dump of Uyghur Wikipedia, totaling 517,237 tokens. |
|
* The UD treebank [UD_Wolof-WDT](https://github.com/UniversalDependencies/UD_Wolof-WDT), v2.9, totaling 44,258 tokens, was used for labeled data. |
|
|
|
Please see [the repository](https://github.com/lgessler/microbert) and |
|
[the paper](https://github.com/lgessler/microbert/raw/master/MicroBERT__MRL_2022_.pdf) for more details. |
|
|
