Upload README.md

README.md

@@ -11,9 +11,9 @@ widget:
   example_title: "Example 3"
 ---
 
-# FinBertPTBR : Financial Bert PT BR
+# FinBERT-PT-BR : Financial BERT PT BR
 
-FinBertPTBR is a pre-trained NLP model to analyze sentiment of Brazilian Portuguese financial texts.
+FinBERT-PT-BR is a pre-trained NLP model to analyze sentiment of Brazilian Portuguese financial texts.
 
 The model was trained in two main stages: language modeling and sentiment modeling. In the first stage, a language model was trained with more than 1.4 million texts of financial news in Portuguese. 
 From this first training, it was possible to build a sentiment classifier with few labeled texts (500) that presented a satisfactory convergence.
@@ -33,21 +33,30 @@ Among the applications, it was demonstrated that the model can be used to build
 ![Inflation Analysis](sentiment_inflation.png)
 
 ## 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).
+
 ```python
 from transformers import AutoTokenizer, BertForSequenceClassification
 import numpy as np
   
-pred_mapper = {0: 'negative', 1: 'positive', 2: 'neutral'}
+pred_mapper = {
+    0: "POSITIVE",
+    1: "NEGATIVE",
+    2: "NEUTRAL"
+  }
+
+huggingface_auth_token = 'AUTH_TOKEN'
 
-tokenizer = AutoTokenizer.from_pretrained("lucas-leme/FinBERT-PT-BR")
-finbertptbr = BertForSequenceClassification.from_pretrained("lucas-leme/FinBERT-PT-BR")
+tokenizer = AutoTokenizer.from_pretrained("lucas-leme/FinBERT-PT-BR", use_auth_token=huggingface_auth_token)
+finbertptbr = BertForSequenceClassification.from_pretrained("lucas-leme/FinBERT-PT-BR", use_auth_token=huggingface_auth_token)
 
 tokens = tokenizer(["Hoje a bolsa caiu", "Hoje a bolsa subiu"], return_tensors="pt",
                     padding=True, truncation=True, max_length=512)
 finbertptbr_outputs = finbertptbr(**tokens)
+
 preds = [pred_mapper[np.argmax(pred)] for pred in finbertptbr_outputs.logits.cpu().detach().numpy()]
 ```
-
 ## Author
 
   - [Lucas Leme](https://www.linkedin.com/in/lucas-leme-santos/)