Update README.md

README.md

@@ -46,8 +46,7 @@ We use a simple template to generate the solution for evalplus:
 
 ## Quickstart
 
-Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
-
+Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.You should use transformer version 4.39 to avoid loading tokenizer errors.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 device = "cuda" # the device to load the model onto