Update README.md

README.md

@@ -40,11 +40,11 @@ Compared with T5,-samll we implement its Chinese version. In order to use for ch
 ## 使用 Usage
 
 ```python
-from transformers import T5ForConditionalGeneration, AutoTokenizer
+from transformers import T5ForConditionalGeneration, BertTokenizer
 import torch
 
-tokenizer=AutoTokenizer.from_pretrained('IDEA-CCNL/Randeng-T5-Char-57M-Chinese', use_fast=false)
-model=T5ForConditionalGeneration.from_pretrained('IDEA-CCNL/Randeng-T5-Char-57M-Chinese')
+tokenizer=BertTokenizer.from_pretrained('IDEA-CCNL/Randeng-T5-Char-700M-Chinese', add_special_tokens=False)
+model=T5ForConditionalGeneration.from_pretrained('IDEA-CCNL/Randeng-T5-Char-700M-Chinese')
 ```
 
 ## 引用 Citation