Update README.md

README.md

@@ -39,7 +39,7 @@ We use the training script at `https://github.com/WeiXiongUST/RLHF-Reward-Model
    {"role": "user", "content": "I'd like to show off how chat templating works!"},
   ]
 
-  test_texts = [tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=False).replace(tokenizer.bos_token, "")]
+  test_texts = [rm_tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=False).replace(rm_tokenizer.bos_token, "")]
   pipe_outputs = rm_pipe(test_texts, **pipe_kwargs)
   rewards = [output[0]["score"] for output in pipe_outputs]
 ```