Update README.md
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ This is a NER model for Portuguese which uses the standard 'enamex' classes: LOC
|
|
17 |
|
18 |
The model is based on [BERTimbau Base](https://huggingface.co/neuralmind/bert-base-portuguese-cased), which has been fine-tuned using a combination of available corpus (see [1] for details).
|
19 |
|
20 |
-
There is an alternative model trained using
|
21 |
|
22 |
It was trained with a batch size of 8 and a learning rate of 2e-5 during 3 epochs. It achieved the following results on the test set (Precision/Recall/F1): 0.913/0.918/0.915.
|
23 |
|
|
|
17 |
|
18 |
The model is based on [BERTimbau Base](https://huggingface.co/neuralmind/bert-base-portuguese-cased), which has been fine-tuned using a combination of available corpus (see [1] for details).
|
19 |
|
20 |
+
There is an alternative model trained using [BERTimbau Large](https://huggingface.co/neuralmind/bert-large-portuguese-cased): [bert-large-pt-ner-enamex](https://huggingface.co/marcosgg/bert-large-pt-ner-enamex).
|
21 |
|
22 |
It was trained with a batch size of 8 and a learning rate of 2e-5 during 3 epochs. It achieved the following results on the test set (Precision/Recall/F1): 0.913/0.918/0.915.
|
23 |
|