Update app.py

app.py

@@ -21,7 +21,7 @@ from transformers import pipeline
 from transformers import TrainingArguments
 from transformers import Trainer
 from torch import nn
-from transformers import RobertaTokenizer, RobertaForSequenceClassification
+
 
 
 
@@ -29,7 +29,7 @@ from transformers import RobertaTokenizer, RobertaForSequenceClassification
 model_path = "slickdata/finetuned-Sentiment-classfication-ROBERTA-model"
 
 # Initialize the tokenizer for the pre-trained model
-tokenizer = RobertaTokenizer.from_pretrained('roberta-base')
+tokenizer = AutoTokenizer.from_pretrained('roberta-base')
 
 # Load the configuration for the pre-trained model
 config = AutoConfig.from_pretrained(model_path)
@@ -60,18 +60,17 @@ def sentiment_analysis(text):
     # Feed the tokenized input to the pre-trained model and obtain output
     output = model(**encoded_input)
 
-    # Obtain the prediction scores for the output
-    scores_ = output[0][0].detach().numpy()
-
-    # Apply softmax activation function to obtain probability distribution over the labels
-    scores_ = softmax(scores_)
+    scores_ = softmax(output.logits[0].detach().numpy())
 
     # Format the output dictionary with the predicted scores
     labels = ['Negative', 'Neutral', 'Positive']
     scores = {l:float(s) for (l,s) in zip(labels, scores_) }
 
-    # Return the scores
-    return scores
+    # Get the label with the highest score
+    max_score_label = max(scores, key=scores.get)
+
+    # Return the label with the highest score
+    return max_score_label
 
 # Define a Gradio interface to interact with the model
 demo = gr.Interface(