Update README.md

README.md

@@ -9,13 +9,18 @@ inference: false
 https://github.com/ZhuiyiTechnology/WoBERT
 ### pytorch版本 
 https://github.com/JunnYu/WoBERT_pytorch
+
+## 安装(主要为了安装WoBertTokenizer)
+```bash
+pip install git+https://github.com/JunnYu/RoFormer_pytorch.git
+```
+
 ## 使用
 ```python
-git clone https://github.com/JunnYu/WoBERT_pytorch
-cd WoBERT_pytorch
 import torch
 from transformers import BertForMaskedLM as WoBertForMaskedLM
-from tokenization_wobert import WoBertTokenizer
+from roformer import WoBertTokenizer
+
 pretrained_model_or_path_list = [
     "junnyu/wobert_chinese_plus_base", "junnyu/wobert_chinese_base"
 ]
@@ -41,7 +46,9 @@ for path in pretrained_model_or_path_list:
 # WoBERT      今天[天气||阳光||天||心情||空气]很好，我[想||要||就||准备||也]去公园玩。
 ```
 ## 引用
+
 Bibtex：
+
 ```tex
 @techreport{zhuiyiwobert,
   title={WoBERT: Word-based Chinese BERT model - ZhuiyiAI},