Update app.py

app.py

@@ -21,7 +21,7 @@ def run_generation(user_text, use_assistant, temperature, max_new_tokens):
         do_sample = True
 
     # Get the model and tokenizer, and tokenize the user text.
-    model_inputs = tokenizer([user_text], return_tensors="pt").to(torch_device)
+    model_inputs = tokenizer([user_text], return_tensors="pt").to(model.device)
 
     # 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.