BERTimbau-large-text-filter

BERTimbau-large-text-filter

📣 UPDATE: If you like/use Tucanos or GigaVerbo for anything, know that version 2 is already out. Go to our new organization (Polyglot) to check out all the improvements the Tucano 2 series brings!

BERTimbau-large-text-filter is a BERT model that can be used to score the quality of a given Portuguese text string. This model was trained on the GigaVerbo-Text-Filter dataset.

Details

• Size: 334,398,466 parameters
• Dataset: GigaVerbo-Text-Filter
• Language: Portuguese
• Number of Training Epochs: 3
• Batch size: 128
• Optimizer: torch.optim.AdamW
• Learning Rate: 4e-5

This repository has the source code used to train this model.

Usage

Here's an example of how to use the BERTimbau-large-text-filter:

from transformers import AutoTokenizer, AutoModelForSequenceClassification
from transformers import TextClassificationPipeline
import torch

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

tokenizer = AutoTokenizer.from_pretrained("TucanoBR/BERTimbau-large-text-filter")
model = AutoModelForSequenceClassification.from_pretrained("TucanoBR/BERTimbau-large-text-filter")
model.to(device)

classifier = TextClassificationPipeline(model=model, tokenizer=tokenizer, device=device)
result = classifier("Os tucanos são aves que correspondem à família Ramphastidae, vivem nas florestas tropicais da América Central e América do Sul. A família inclui cinco gêneros e mais de quarenta espécies diferentes. Possuem bicos notavelmente grandes e coloridos, que possuem a função de termorregulação para as muitas espécies que passam muito tempo na copa da floresta exposta ao sol tropical quente.")

Cite as 🤗

@misc{correa2024tucanoadvancingneuraltext,
      title={{Tucano: Advancing Neural Text Generation for Portuguese}}, 
      author={Corr{\^e}a, Nicholas Kluge and Sen, Aniket and Falk, Sophia and Fatimah, Shiza},
      year={2024},
      eprint={2411.07854},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2411.07854}, 
}

@article{correa2025tucanoadvancingneuraltext,
    title={{Tucano: Advancing Neural Text Generation for Portuguese}},
    author={Corr{\^e}a, Nicholas Kluge and Sen, Aniket and Falk, Sophia and Fatimah, Shiza},
    journal={Patterns},
    publisher={Elsevier},
    year={2025},
    doi={10.1016/j.patter.2025.101325},
    url={https://doi.org/10.1016/j.patter.2025.101325},
    issn={2666-3899}
}

Aknowlegments

We gratefully acknowledge the granted access to the Marvin cluster hosted by University of Bonn along with the support provided by its High Performance Computing & Analytics Lab.

License

BERTimbau-large-text-filter is licensed under the Apache License, Version 2.0. For more details, see the LICENSE file.