Downloads · 30 days
139
32% of all-time downloads
Enigma-for-AI/bert-base-sudabert
bert-base-sudabert is a fill-mask model from Enigma-for-AI. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
A pretrained BERT base language model for Sudanese Arabic.
Downloads · 30 days
139
32% of all-time downloads
All-time downloads
429
Public
Parameters
135M
541 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors541 MB · 100%
From the Hugging Face model README
A pretrained BERT base language model for Sudanese Arabic.
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("Enigma-for-AI/bert-base-sudabert")
model = AutoModelForMaskedLM.from_pretrained("Enigma-for-AI/bert-base-sudabert")
If you use this model in your work, please cite this paper:
@INPROCEEDINGS{SudaBERT,
author={Elgezouli, Mukhtar and Elmadani, Khalid N. and Saeed, Muhammed},
booktitle={2020 International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE)},
title={SudaBERT: A Pre-trained Encoder Representation For Sudanese Arabic Dialect},
year={2021},
pages={1-4},
doi={10.1109/ICCCEEE49695.2021.9429651}
}