Update app.py

app.py

@@ -48,7 +48,7 @@ def chat(message: str, history: list, stm_state: torch.Tensor, llm_history: list
     
     with torch.amp.autocast(device_type=device.type, dtype=torch.bfloat16):
         for token_id in llm_model.generate(**llm_chat_history, max_seq_len=llm_seq_len, temperature=temperature, top_p=top_p):
-            llm_response += model.stringify_token(token_id, show_memory_update=False)
+            llm_response += llm_model.stringify_token(llm_tokenizer, token_id)
             yield history + [[message, response]], stm_state, llm_history + [[message, llm_response]]
     
     return history + [[message, response]], model.export_stm_state().cpu(), llm_history + [[message, llm_response]]