BioBERTpt-squad-v1.1-portuguese for QA (Question Answering)

This is a clinical and biomedical model trained with generic QA questions. This model was finetuned on SQUAD v1.1, with the dataset SQUAD v1.1 in portuguese, from the Deep Learning Brasil group on Google Colab. See more details here.

Performance

The results obtained are the following:

f1 = 80.06
exact match = 67.52

See more

Our repo: https://github.com/HAILab-PUCPR/

Downloads last month
256
Hosted inference API
Question Answering
This model can be loaded on the Inference API on-demand.