small change

app.py

@@ -50,12 +50,14 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
         top_p=top_p,
         pad_token_id=tokenizer.eos_token_id,  # Ensure padding is replaced with EOS
     )
-    
+    print("output")
+    print(output)
     # Decode the generated output
     response = tokenizer.decode(
         output[0], skip_special_tokens=True
     ).strip()  # Remove any extra whitespace or unexpected tokens
     
+
     # Yield the clean response for display
     yield response