metadata
language: ar
tags: Fill-Mask
datasets: OSCAR
widget:
- text: ' السلام عليكم ورحمة[MASK] وبركاتة'
- text: ' اهلا وسهلا بكم في [MASK] من سيربح المليون'
- text: ' مرحبا بك عزيزي الزائر [MASK] موقعنا '
Arabic BERT Model
AraBERTMo is an Arabic pre-trained language model based on Google's BERT architechture.
AraBERTMo_base uses the same BERT-Base config.
AraBERTMo_base now comes in 10 new variants
All models are available on the HuggingFace
model page under the Ebtihal name.
Checkpoints are available in PyTorch formats.
Pretraining Corpus
`AraBertMo_base_V3' model was pre-trained on ~3 million words:
- OSCAR - Arabic version "unshuffled_deduplicated_ar".
Training results
this model achieves the following results:
Task | Num examples | Num Epochs | Batch Size | steps | Wall time | training loss |
---|---|---|---|---|---|---|
Fill-Mask | 30024 | 3 | 64 | 1410 | 3h 10m 31s | 8.0201 |
Load Pretrained Model
You can use this model by installing torch
or tensorflow
and Huggingface library transformers
. And you can use it directly by initializing it like this:
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("Ebtihal/AraBertMo_base_V3")
model = AutoModelForMaskedLM.from_pretrained("Ebtihal/AraBertMo_base_V3")
This model was built for master's degree research in an organization:
- University of kufa.
- Faculty of Computer Science and Mathematics.
- Department of Computer Science