Update app.py

app.py

@@ -54,6 +54,7 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
  #conversation.append({"role": "user", "content": message})
 
  print(f"Conversation is -\n{conversation}")
+ stop = StopOnTokens()
 
  input_ids = tokenizer.build_chat_input(message, history=conversation, role='user').input_ids.to(model.device)
  #input_ids = tokenizer.apply_chat_template(conversation, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)