1 Hugging Face's logo
2 ---
3 language: rw
4 datasets:
5
6 ---
7 # xlm-roberta-base-finetuned-kinyarwanda
8 ## Model description
9 **xlm-roberta-base-finetuned-kinyarwanda** is a **Kinyarwanda RoBERTa** model obtained by fine-tuning **xlm-roberta-base** model on Kinyarwanda language texts. It provides **better performance** than the XLM-RoBERTa on named entity recognition datasets.
10
11 Specifically, this model is a *xlm-roberta-base* model that was fine-tuned on Kinyarwanda corpus.
12 ## Intended uses & limitations
13 #### How to use
14 You can use this model with Transformers *pipeline* for masked token prediction.
15 ```python
16 >>> from transformers import pipeline
17 >>> unmasker = pipeline('fill-mask', model='Davlan/xlm-roberta-base-finetuned-kinyarwanda')
18 >>> unmasker("Twabonye ko igihe mu <mask> hazaba hari ikirango abantu bakunze")
19
20
21
22 ```
23 #### Limitations and bias
24 This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
25 ## Training data
26 This model was fine-tuned on JW300 + [KIRNEWS](https://github.com/Andrews2017/KINNEWS-and-KIRNEWS-Corpus) + [BBC Gahuza](https://www.bbc.com/gahuza)
27
28 ## Training procedure
29 This model was trained on a single NVIDIA V100 GPU
30
31 ## Eval results on Test set (F-score, average over 5 runs)
32 Dataset| XLM-R F1 | rw_roberta F1
33 -|-|-
34 [MasakhaNER](https://github.com/masakhane-io/masakhane-ner) | 73.22 | 77.76
35
36 ### BibTeX entry and citation info
37 By David Adelani
38 ```
39
40 ```
41
42
43