Remove max_tokens

code/app.py

@@ -69,7 +69,7 @@ def talk(txt, jsn):
     if not running:
         #result = lcpp_model.create_chat_completion(messages=txt,stream=True,stop=["GPT4 Correct User: ", "<|end_of_turn|>", "</s>"], max_tokens=64, )
         #result = lcpp_model(prompt=jsn2prompt(txt), stream=True, stop=["GPT4 Correct User: ", "<|end_of_turn|>", "</s>"], max_tokens=64, echo=False)
-        result = llm(prompt=jsn2prompt(txt), stream=True, stop=["GPT4 Correct User: ", "<|end_of_turn|>", "</s>"], max_tokens=192, echo=False)
+        result = llm(prompt=jsn2prompt(txt), stream=True, stop=["GPT4 Correct User: ", "<|end_of_turn|>", "</s>"], echo=False)
         running = True
     for r in result:
         print("GOT RESULT:", r)