Update README.md

README.md

@@ -6,36 +6,26 @@ widget:
 - text: " السلام عليكم ورحمة[MASK] وبركاتة"
 - text: " اهلا وسهلا بكم في [MASK] من سيربح المليون "
 ---
-
 # Arabic BERT Model
-
 **AraBERTMo** is an Arabic pre-trained language model based on [Google's BERT architechture](https://github.com/google-research/bert). 
 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](https://huggingface.co/Ebtihal/) name. 
 Checkpoints are available in PyTorch formats.
 
-
 ## Pretraining Corpus
-
 `AraBertMo_base_V1' model was pre-trained on ~3 million words:
-
 - [OSCAR](https://traces1.inria.fr/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| 10010|  1  | 64 | 157  | 2m 2s | 9.0183  | 
 
-
 ## 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:  
-
 ```python
 from transformers import AutoTokenizer, AutoModel
 tokenizer = AutoTokenizer.from_pretrained("Ebtihal/AraBertMo_base_V1")