Update README.md

69bbd3a verified about 2 months ago

4.09 kB

library_name: transformers
base_model: neuralmind/bert-base-portuguese-cased
tags:
  - toxicity
  - portuguese
metrics:
  - precision
  - recall
  - accuracy
model-index:
  - name: portuguese-bertimbau-toxicity-classifier
    results: []
license: apache-2.0
datasets:
  - Polygl0t/portuguese-toxicity-qwen-annotations
language:
  - pt
pipeline_tag: text-classification

BERTimbau Toxicity Classifier

BERTimbau Toxicity Classifier is a BERT based model that can be used for judging the toxicity level of a given Portuguese text string. This model was trained on the Portuguese Toxicity Qwen Annotations dataset.

Details

For training, we added a classification head with a single regression output to neuralmind/bert-base-portuguese-cased. Only the classification head was trained, i.e., the rest of the model was frozen.

Dataset: Portuguese Toxicity Qwen Annotations
Language: portuguese
Number of Training Epochs: 20
Batch size: 256
Optimizer: torch.optim.AdamW
Learning Rate: 3e-4
Eval Metric: f1-score

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

Evaluation Results

Confusion Matrix

	1	2	3	4	5
1	16652	646	15	0	0
2	637	673	123	6	0
3	112	347	263	41	0
4	21	47	110	110	32
5	4	8	10	22	121

Precision: 0.6513
Recall: 0.5702
F1 Macro: 0.5992
Accuracy: 0.8909

Usage

Here's an example of how to use the BERTimbau Toxicity Classifier:

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

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

tokenizer = AutoTokenizer.from_pretrained("Polygl0t/portuguese-bertimbau-toxicity-classifier")
model = AutoModelForSequenceClassification.from_pretrained("Polygl0t/portuguese-bertimbau-toxicity-classifier")
model.to(device)

text = "Coloque aqui o seu texto ..."
encoded_input  =  tokenizer(text, return_tensors="pt", padding="longest", truncation=True).to(device)

with  torch.no_grad():
    model_output  =  model(**encoded_input)
    logits  =  model_output.logits.squeeze(-1).float().cpu().numpy()

# scores are produced in the range [0, 4]. To convert to the range [1, 5], we can simply add 1 to the score.
score = [x + 1 for x in logits.tolist()][0]

print({
 "text": text,
 "score": score,
 "int_score": [int(round(max(0, min(score, 4)))) + 1 for score in logits][0],
})

Cite as 🤗

@misc{correa2026tucano2cool,
      title={{Tucano 2 Cool: Better Open Source LLMs for Portuguese}}, 
      author={Nicholas Kluge Corr{\^e}a and Aniket Sen and Shiza Fatimah and Sophia Falk and Lennard Landgraf and Julia Kastner and Lucie Flek},
      year={2026},
      eprint={2603.03543},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2603.03543}, 
}

Aknowlegments

Polyglot is a project funded by the Federal Ministry of Education and Research (BMBF) and the Ministry of Culture and Science of the State of North Rhine-Westphalia (MWK) as part of TRA Sustainable Futures (University of Bonn) and the Excellence Strategy of the federal and state governments.

We also 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 Toxicity Classifier is licensed under the Apache License, Version 2.0. For more details, see the LICENSE file.