Update app.py

app.py

@@ -17,12 +17,13 @@ def generate_response(prompt):
     
     # Ensure the inputs are moved to the CPU
     input_ids = inputs["input_ids"].to("cpu")
-    
+    print(input_ids)
     # Generate output (ensure it's on CPU)
     output = model.generate(input_ids, max_length=150, num_return_sequences=1)
     
     # Decode and return response
     response = tokenizer.decode(output[0], skip_special_tokens=True)
+    print(output)
     return response
 
 # Create a Gradio interface with a "Generate" button