Update app.py

app.py

@@ -8,10 +8,11 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from transformers import AutoTokenizer, AutoModelForCausalLM, AutoModelForSequenceClassification
 
 # download the instruct-aira-dataset
-dataset = load_dataset("nicholasKluge/instruct-aira-dataset", split='portuguese')
+#dataset = load_dataset("nicholasKluge/instruct-aira-dataset", split='portuguese')
+dataset = load_dataset("parquet", data_files="instruct-aira-dataset.parquet")
 
 # convert the dataset to a pandas dataframe
-df = dataset.to_pandas()
+df = dataset['train'].to_pandas()
 
 # rename the columns
 df.columns = ['Prompt', 'Completion']