YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Hugging Face's logo
language: am datasets:
xlm-roberta-base-finetuned-amharic
Model description
xlm-roberta-base-finetuned-amharic is a Amharic RoBERTa model obtained by fine-tuning xlm-roberta-base model on Amharic language texts. It provides better performance than the XLM-RoBERTa on named entity recognition datasets.
Specifically, this model is a xlm-roberta-base model that was fine-tuned on Amharic corpus.
Intended uses & limitations
How to use
You can use this model with Transformers pipeline for masked token prediction.
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='Davlan/xlm-roberta-base-finetuned-hausa')
>>> unmasker("α¨α ααͺα« α¨α ααͺα« ααα΅ αα© ααααα°α αααͺ ααα΅αα α α α«α΅ α αα«α΅ α¨αα«α°αα΅α <mask> αααα«αΈαα α¨α ααͺα« α¨ααͺ αα³α ααα΅α΄α α α΅α³ααα’")
Limitations and bias
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.
Training data
This model was fine-tuned on Amharic CC-100
Training procedure
This model was trained on a single NVIDIA V100 GPU
Eval results on Test set (F-score, average over 5 runs)
| Dataset | XLM-R F1 | am_roberta F1 |
|---|---|---|
| MasakhaNER | 70.96 | 77.97 |
BibTeX entry and citation info
By David Adelani
- Downloads last month
- 73