Update README.md

README.md

@@ -8,7 +8,7 @@ library_name: paddlenlp
 # PaddlePaddle/ernie-3.0-nano-zh
 
 ## Intro
-[ERNIE Tiny Models](https://github.com/paddlepaddle/PaddleNLP/tree/develop/model_zoo/ernie-3.0) are lightweight models obtained from Wenxin large model ERNIE 3.0 using distillation technology. The model structure is consistent with ERNIE 2.0, and has a stronger Chinese effect than ERNIE 2.0.
+[ERNIE 3.0 Models](https://github.com/paddlepaddle/PaddleNLP/tree/develop/model_zoo/ernie-3.0) are lightweight models obtained from Wenxin large model ERNIE 3.0 using distillation technology. The model structure is consistent with ERNIE 2.0, and has a stronger Chinese effect than ERNIE 2.0.
 
 For a detailed explanation of related technologies, please refer to the article [_解析全球最大中文单体模型鹏城-百度·文心技术细节_](https://www.jiqizhixin.com/articles/2021-12-08-9)
 
@@ -19,8 +19,9 @@ Click on the "Use in paddlenlp" on the top right corner!
 
 ## Performance
 
-ERNIE Tiny 3.0 open sources five models: **ERNIE 3.0 _Base_** 、**ERNIE 3.0 _Medium_** 、 **ERNIE 3.0 _Mini_** 、 **ERNIE 3.0 _Micro_** 、 **ERNIE 3.0 _Nano_** ：
+ERNIE 3.0 open sources six models: **ERNIE 3.0 _XBase_**, **ERNIE 3.0 _Base_** 、**ERNIE 3.0 _Medium_** 、 **ERNIE 3.0 _Mini_** 、 **ERNIE 3.0 _Micro_** 、 **ERNIE 3.0 _Nano_** ：
 
+- **ERNIE 3.0-_XBase_** (_20-layer, 1024-hidden, 16-heads_)
 - **ERNIE 3.0-_Base_** (_12-layer, 768-hidden, 12-heads_)
 - **ERNIE 3.0-_Medium_** (_6-layer, 768-hidden, 12-heads_)
 - **ERNIE 3.0-_Mini_** (_6-layer, 384-hidden, 12-heads_)