diff --git a/model_cards/jannesg/takalane_nso_roberta/README.md b/model_cards/jannesg/takalane_nso_roberta/README.md new file mode 100644 index 00000000000..26866720825 --- /dev/null +++ b/model_cards/jannesg/takalane_nso_roberta/README.md @@ -0,0 +1,50 @@ +--- +language: +- nso +thumbnail: https://pbs.twimg.com/media/EVjR6BsWoAAFaq5.jpg +tags: +- nso +- fill-mask +- pytorch +- roberta +- lm-head +- masked-lm +license: MIT +--- + +# Takalani Sesame - Northern Sotho πŸ‡ΏπŸ‡¦ + + + +## Model description + +Takalani Sesame (named after the South African version of Sesame Street) is a project that aims to promote the use of South African languages in NLP, and in particular look at techniques for low-resource languages to equalise performance with larger languages around the world. + +## Intended uses & limitations + +#### How to use + +```python +from transformers import AutoTokenizer, AutoModelWithLMHead + +tokenizer = AutoTokenizer.from_pretrained("jannesg/takalane_nso_roberta") + +model = AutoModelWithLMHead.from_pretrained("jannesg/takalane_nso_roberta") +``` + +#### Limitations and bias + +Updates will be added continously to improve performance. + +## Training data + +Data collected from [https://wortschatz.uni-leipzig.de/en](https://wortschatz.uni-leipzig.de/en)
+**Sentences:** 4746 + +## Training procedure + +No preprocessing. Standard Huggingface hyperparameters. + +## Author + +Jannes Germishuys [website](http://jannesgg.github.io)