Update README.md

README.md

@@ -31,7 +31,7 @@ Among the applications, it was demonstrated that the model can be used to build
 
 ## Usage
 
-In order to use the model, you need to get the HuggingFace auth token. You can get it [here](https://huggingface.co/settings/token).
+#### BertForSequenceClassification
 
 ```python
 from transformers import AutoTokenizer, BertForSequenceClassification
@@ -52,6 +52,23 @@ finbertptbr_outputs = finbertptbr(**tokens)
 
 preds = [pred_mapper[np.argmax(pred)] for pred in finbertptbr_outputs.logits.cpu().detach().numpy()]
 ```
+
+#### Pipeline
+
+```python
+from transformers import (
+    AutoTokenizer, 
+    BertForSequenceClassification,
+    pipeline,
+)
+
+finbert_pt_br_tokenizer = AutoTokenizer.from_pretrained("lucas-leme/FinBERT-PT-BR")
+finbert_pt_br_model = BertForSequenceClassification.from_pretrained("lucas-leme/FinBERT-PT-BR")
+
+finbert_pt_br_pipeline = pipeline(task='text-classification', model=finbert_pt_br_model, tokenizer=finbert_pt_br_tokenizer)
+finbert_pt_br_pipeline(['Hoje a bolsa caiu', 'Hoje a bolsa subiu'])
+```
+
 ## Author
 
   - [Lucas Leme](https://www.linkedin.com/in/lucas-leme-santos/) - [email protected]