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

State-of-the-art language model for Hebrew, released here.

This is the BERT-large base model pretrained with the masked-language-modeling objective.

For the bert-base models for other tasks, see here.

Sample usage:

from transformers import AutoModelForMaskedLM, AutoTokenizer

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

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 לימודיו / מחקריו 

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.