This repository provides pre-trained BERT models specifically trained for the Portuguese language. BERT-Base and BERT-Large Cased variants were trained on the BrWaC Portuguese corpus for 1,000,000 steps using whole-word masking. The models are available in both TensorFlow and PyTorch formats and have been benchmarked on tasks including Named Entity Recognition, Recognizing Textual Entailment, and Sentence Textual Similarity, outperforming multilingual BERT on Portuguese tasks.