docs: add instructions for running the model from transformers lib

README.md

@@ -32,10 +32,22 @@ widget:
     score: 0.9998
 ---
 
-## Model Instructions
+# BERTimbau for Sentiment Analysis of Glassdoor Reviews
 
-For more information, follow the [Hugging Face Spaces](https://huggingface.co/spaces/stevillis/bertimbau-finetuned-glassdoor-reviews/blob/main/README.md).
+## Introduction
+This model fine-tunes [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) 
+for sentiment analysis of Glassdoor reviews about IT companies in Cuiabá.
 
-## Model Preview
+## Dataset Information
+The dataset used to train the model consists of 2,532 reviews sourced from Glassdoor.
 
-Try the [Streamlit App](https://huggingface.co/spaces/stevillis/bertimbau-finetuned-glassdoor-reviews) to test the model.
+### Example Usage
+```python
+from transformers import pipeline
+
+pipe = pipeline("text-classification", model="stevillis/bertimbau-finetuned-glassdoor-reviews")
+
+result = pipe("Empresa boa para trabalhar")
+
+print(result) # Expected output: [{'label': 'positive', 'score': 0.9993522763252258}]
+```