from transformers import AutoModelForMaskedLM
from transformers import AutoTokenizer, FillMaskPipeline
from pprint import pprint
tokenizer_hf = AutoTokenizer.from_pretrained('BSC-TeMU/roberta-base-bne')
model = AutoModelForMaskedLM.from_pretrained('BSC-TeMU/roberta-base-bne')
model.eval()
pipeline = FillMaskPipeline(model, tokenizer_hf)
text = f"¡Hola <mask>!"
res_hf = pipeline(text)
pprint([r['token_str'] for r in res_hf])

from transformers import AutoModelForMaskedLM
from transformers import AutoTokenizer, FillMaskPipeline
from pprint import pprint
tokenizer_hf = AutoTokenizer.from_pretrained('BSC-TeMU/roberta-large-bne')
model = AutoModelForMaskedLM.from_pretrained('BSC-TeMU/roberta-large-bne')
model.eval()
pipeline = FillMaskPipeline(model, tokenizer_hf)
text = f"¡Hola <mask>!"
res_hf = pipeline(text)
pprint([r['token_str'] for r in res_hf])

@misc{gutierrezfandino2021spanish,
      title={Spanish Language Models}, 
      author={Asier Gutiérrez-Fandiño and Jordi Armengol-Estapé and Marc Pàmies and Joan Llop-Palao and Joaquín Silveira-Ocampo and Casimiro Pio Carrino and Aitor Gonzalez-Agirre and Carme Armentano-Oller and Carlos Rodriguez-Penagos and Marta Villegas},
      year={2021},
      eprint={2107.07253},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}