DictaBERT
Collection
Collection of state-of-the-art language model for Hebrew, finetuned for various tasks, as detailed in the article: https://arxiv.org/abs/2308.16687
•
17 items
•
Updated
State-of-the-art language model for Hebrew, released here.
This is the BERT-tiny base model pretrained with the masked-language-modeling objective.
For the bert models for other tasks, see here.
Sample usage:
from transformers import AutoModelForMaskedLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('dicta-il/dictabert-tiny')
model = AutoModelForMaskedLM.from_pretrained('dicta-il/dictabert-tiny')
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 עבודתו / התמחותו
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}
}
This work is licensed under a Creative Commons Attribution 4.0 International License.