metadata
datasets:
- oscar-corpus/OSCAR-2201
- mc4
language:
- he
pipeline_tag: fill-mask
Hebrew Language Model
State-of-the-art Longformer language model for Hebrew.
How to use
from transformers import AutoModelForMaskedLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('HeNLP/LongHeRo')
model = AutoModelForMaskedLM.from_pretrained('HeNLP/LongHeRo')