Comparison of Czech Transformers on Text Classification Tasks
Paper • 2107.10042 • Published
How to use fav-kky/FERNET-News with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("fill-mask", model="fav-kky/FERNET-News") # Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("fav-kky/FERNET-News")
model = AutoModelForMaskedLM.from_pretrained("fav-kky/FERNET-News")FERNET-News is a monolingual Czech RoBERTa-base model pre-trained from 20.5GB of thoroughly cleaned Czech news corpus.
Preprint of our paper is available at https://arxiv.org/abs/2107.10042.