Update app.py

app.py

@@ -32,7 +32,7 @@ def run_generation(user_text, top_p, temperature, top_k, max_new_tokens):
         user_text, # input goes here
         "", # output - leave this blank for generation!
     )
-    ], return_tensors = "pt",return_dict=True)
+    ], return_tensors = "pt")
 
     # Start generation on a separate thread, so that we don't block the UI. The text is pulled from the streamer
     # in the main thread. Adds timeout to the streamer to handle exceptions in the generation thread.