bert-portuguese-ner
This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased It achieves the following results on the evaluation set: - Loss: 0.1140 - Precision: 0.9147 - Recall: 0.9483 - F1: 0.9312 - Accuracy: 0.9700
Params
—
Context
512
Downloads 30d
960 K
Likes
9
Download history
daily snapshots · 55 days
▲ 399 K in the last 30 days (71.0%)
1.1 M576 K
Aug 22Sep 1Sep 11Sep 20
1.1 M327 K
Jul 28Aug 15Sep 2Sep 20
Specifications
- Architecture
- BertForTokenClassification
- Context length
- 512
- Vocabulary
- 29,794
- Layers / heads
- 12 / 12
- Licence
- mit
- First seen on the Hub
- 2022-03-02
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any token-classification model