Update README.md

README.md

@@ -89,7 +89,7 @@ results = []
 for dt in tqdm(datasets):
   input = dt["input"]
 
-  prompt = f"""### 指示\n{input}\n### 回答\n"""
+  prompt = f"""### 指示\n let's think step by step \n {input}\n### 回答\n"""
 
   inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)