from transformers import AutoTokenizer
from transformers import TFAutoModel

tok = AutoTokenizer.from_pretrained("guillermoruiz/bilma_mx")
model = TFAutoModel.from_pretrained("guillermoruiz/bilma_mx", trust_remote_code=True)

text = ["Vamos a comer [MASK].",
        "Hace mucho que no voy al [MASK]."]
t = tok(text, padding="max_length", return_tensors="tf", max_length=280)

import tensorflow as tf
tok.batch_decode(tf.argmax(p["logits"], 2)[:,1:], skip_special_tokens=True)

@misc{tellez2022regionalized,
      title={Regionalized models for Spanish language variations based on Twitter}, 
      author={Eric S. Tellez and Daniela Moctezuma and Sabino Miranda and Mario Graff and Guillermo Ruiz},
      year={2022},
      eprint={2110.06128},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}