Update app.py

app.py

@@ -7,8 +7,8 @@ from threading import Thread
 # Loading the tokenizer and model from Hugging Face's model hub.
 # model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 model_name = "scutcyr/BianQue-2"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name,trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name,trust_remote_code=True)
 
 # using CUDA for an optimal experience
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')