Update app.py

app.py

@@ -29,7 +29,8 @@ tokenizer = YiTokenizer(vocab_file="./tokenizer.model")
 model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
     device_map="auto",
     torch_dtype=torch.bfloat16,
-    load_in_4bit=True                          # For efficient inference, if supported by the GPU card
+    load_in_4bit=True,
+    trust_remote_code=True
 )
 
 # Load the model and tokenizer using transformers