fix bugs

case sample have some bugs

README.md

@@ -32,9 +32,9 @@ Yunfan Shao, Zhichao Geng, Yitao Liu, Junqi Dai, Fei Yang, Li Zhe, Hujun Bao, Xi
 >>> from transformers import BertTokenizer
 >>> tokenizer = BertTokenizer.from_pretrained("fnlp/cpt-large")
 >>> model = CPTForConditionalGeneration.from_pretrained("fnlp/cpt-large")
->>> inputs = tokenizer.encode("北京是[MASK]的首都", return_tensors='pt')
+>>> input_ids = tokenizer.encode("北京是[MASK]的首都", return_tensors='pt')
 >>> pred_ids = model.generate(input_ids, num_beams=4, max_length=20)
->>> print(tokenizer.convert_ids_to_tokens(pred_ids[i]))
+>>> print(tokenizer.convert_ids_to_tokens(pred_ids[0]))
     ['[SEP]', '[CLS]', '北', '京', '是', '中', '国', '的', '首', '都', '[SEP]']
 ```