Update app.py

app.py

@@ -67,11 +67,11 @@ def predict(message, history):
         
         streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
         generate_kwargs = dict(
-            model_inputs,
+            input_ids=model_inputs,
             streamer=streamer,
             max_new_tokens=1024,
             do_sample=False,
-            # stopping_criteria=StoppingCriteriaList([stop])
+            stopping_criteria=StoppingCriteriaList([stop])
         )
         t = Thread(target=model.generate, kwargs=generate_kwargs)
         t.start()  # Starting the generation in a separate thread.