Update app.py

app.py

@@ -1,17 +1,27 @@
 import gradio as gr
-sentiment_analysis = gr.Interface.load("models/hipnologo/gpt2-imdb-finetune").launch()
-
-def predict(review_text):
-    # Run the review text through the pipeline
-    result = sentiment_analysis(review_text)[0]
-    
-    # Map the LABEL_0/LABEL_1 to Negative/Positive
-    if result['label'] == 'LABEL_0':
-        result['label'] = 'Negative'
-    elif result['label'] == 'LABEL_1':
-        result['label'] = 'Positive'
-    
-    return result['label'], float(result['score'])
-
-iface = gr.Interface(fn=predict, inputs="textbox", outputs=["label", "number"])
+#gr.Interface.load("models/hipnologo/gpt2-imdb-finetune").launch()
+
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+def predict_review(text):
+    # Specify the model name or path
+    model_name = "models/hipnologo/gpt2-imdb-finetune"
+
+    # Load your model and tokenizer
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+    # encoding the input text
+    input_ids = tokenizer.encode(text, return_tensors="pt")
+
+    # getting the logits 
+    output = model(input_ids)
+    logits = output.logits
+
+    # getting the predicted class
+    predicted_class = logits.argmax(-1).item()
+
+    return f"The sentiment predicted by the model is: {'Positive' if predicted_class == 1 else 'Negative'}"
+
+iface = gr.Interface(fn=predict_review, inputs="textbox", outputs="text")
 iface.launch()