Update app.py

app.py

@@ -8,7 +8,7 @@ def sleep_ms(ms):
   time.sleep(ms / 1000)
 
 def tokenize(string, model_name="lmsys/vicuna-7b-v1.5"):
-  tokenizer = AutoTokenizer.from_pretrained(model_name)
+  tokenizer = LlamaTokenizer.from_pretrained(model_name)
   input_ids = tokenizer.encode(string, return_tensors="pt")
   return input_ids