gn-bert-tiny-cased / README.md
mmaguero's picture
First model version
dc4b14b
metadata
language: gn
datasets:
  - wikipedia
  - wiktionary
widget:
  - text: 'Paraguay ha''e peteĩ táva oĩva [MASK] retãme  '

BERT-i-tiny-cased (gnBERT-tiny-cased)

A pre-trained BERT model for Guarani (2 layers, cased). Trained on Wikipedia + Wiktionary (~800K tokens).