Dictabert

🚀 DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew

DictaBERT is a state-of-the-art language model tailored for Hebrew, offering advanced language processing capabilities.

The model is released here. It serves as the base model pretrained with the masked-language-modeling objective. For bert-base models designed for other tasks, refer to here.

🚀 Quick Start

💻 Usage Examples

Basic Usage

from transformers import AutoModelForMaskedLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('dicta-il/dictabert')
model = AutoModelForMaskedLM.from_pretrained('dicta-il/dictabert')

model.eval()

sentence = 'בשנת 1948 השלים אפרים קישון את [MASK] בפיסול מתכת ובתולדות האמנות והחל לפרסם מאמרים הומוריסטיים'

output = model(tokenizer.encode(sentence, return_tensors='pt'))
# the [MASK] is the 7th token (including [CLS])
import torch
top_2 = torch.topk(output.logits[0, 7, :], 2)[1]
print('\n'.join(tokenizer.convert_ids_to_tokens(top_2))) # should print מחקרו / התמחותו 

📚 Documentation

Citation

If you use DictaBERT in your research, please cite DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew

BibTeX:

@misc{shmidman2023dictabert,
      title={DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew}, 
      author={Shaltiel Shmidman and Avi Shmidman and Moshe Koppel},
      year={2023},
      eprint={2308.16687},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

📄 License

Shield:

This work is licensed under a Creative Commons Attribution 4.0 International License.