Create app.py

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+import torch.nn.functional as F
+
+#Initializing the tuned BERT model and tokenizer.
+model = AutoModelForSequenceClassification.from_pretrained("BERTTuned")
+tokenizer = AutoTokenizer.from_pretrained("Tokenizer")
+
+def predict_sentiment(text):
+    #Tokenizing the input text and preparing it for the model.
+    inputs = tokenizer(text, padding=True, truncation=True, max_length=512, return_tensors="pt")
+
+    #Generating predictions from the model.
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+
+    #Converting the model logits to probabilities for easier interpretation.
+    probabilities = F.softmax(logits, dim=1).squeeze()
+
+    #Mapping the models output to something readable.
+    sentiment_mapping = {0: "Negative", 1: "Positive"}
+    predicted_class_index = torch.argmax(probabilities).item()
+    predicted_probability = probabilities[predicted_class_index].item()
+    predicted_sentiment = sentiment_mapping[predicted_class_index]
+
+    #Returning the predicted sentiment and probability.
+    return predicted_sentiment, f"{predicted_probability:.4f}"
+
+#Setting up a Gradio interface.
+iface = gr.Interface(
+    fn=predict_sentiment,
+    inputs=gr.Textbox(lines=2, placeholder="Enter text here..."),
+    outputs=[gr.Label(label="Predicted Sentiment"), gr.Textbox(label="Probability")],
+    title="Sentiment Analysis",
+    description="Enter a text to predict its sentiment.",
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    iface.launch()