some other debug code added

app.py

@@ -11,12 +11,12 @@ model = model
 
 
 def predict(message, history):
-    print(history)
+    # print(history) [[вопрос1, ответ1], [вопрос2, ответ2]...]
     history_transformer_format = history + [{"role": "user", "content": message}, 
                                             {"role": "assistant", "content": ""}]
 
     model_inputs = tokenizer.apply_chat_template(history_transformer_format, return_tensors="pt")
-    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=20., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         streamer=streamer,
         max_new_tokens=1024,
@@ -32,6 +32,7 @@ def predict(message, history):
 
     partial_message = ""
     for new_token in streamer:
+        print(new_token)
         if new_token != '<':
             partial_message += new_token
             yield partial_message