Update app.py

app.py

@@ -65,10 +65,6 @@ if compute_dtype == torch.float16 and use_4bit:
 model = AutoModelForCausalLM.from_pretrained(
     model_name, quantization_config=bnb_config)
 
-    | StrOutputParser()
-)
-
-
 stop_list = [" \n\nAnswer:", "\n",  " \n\n"]
 stop_token_ids = [tokenizer(x,  return_tensors='pt', add_special_tokens=False)['input_ids'] for x in stop_list]
 stop_token_ids = [torch.LongTensor(x).to("cuda") for x in stop_token_ids]