Update README.md

README.md

@@ -28,9 +28,9 @@ ZEN2 model, which uses N-gram to enhance text semantic and has 668M parameters,
 
 ## 模型信息 Model Information
 
-我们与[ZEN团队](https://github.com/sinovation/ZEN)合作，使用我们的封神框架，开源发布了ZEN2模型。具体而言，通过引入无监督学习中提取的知识，ZEN通过N-gram方法学习不同的文本粒度信息。ZEN2使用大规模数据集和特殊的预训练策略对N-gram增强编码器进行预训练。下一步，我们将继续与ZEN团队一起探索PLM的优化，并提高下游任务的性能。
+我们与[ZEN团队](https://github.com/sinovation/ZEN2)合作，使用我们的封神框架，开源发布了ZEN2模型。具体而言，通过引入无监督学习中提取的知识，ZEN通过N-gram方法学习不同的文本粒度信息。ZEN2使用大规模数据集和特殊的预训练策略对N-gram增强编码器进行预训练。下一步，我们将继续与ZEN团队一起探索PLM的优化，并提高下游任务的性能。
 
-We open source and publicly release ZEN2 using our Fengshen Framework in collaboration with the [ZEN team](https://github.com/sinovation/ZEN). More precisely, by bringing together knowledge extracted by unsupervised learning, ZEN learns different textual granularity information through N-gram methods. ZEN2 pre-trains the N-gram-enhanced encoders with large-scale datasets and special pre-training strategies. In the next step, we continue with the ZEN team to explore the optimization of PLM and improve the performance on downstream tasks.
+We open source and publicly release ZEN2 using our Fengshen Framework in collaboration with the [ZEN team](https://github.com/sinovation/ZEN2). More precisely, by bringing together knowledge extracted by unsupervised learning, ZEN learns different textual granularity information through N-gram methods. ZEN2 pre-trains the N-gram-enhanced encoders with large-scale datasets and special pre-training strategies. In the next step, we continue with the ZEN team to explore the optimization of PLM and improve the performance on downstream tasks.
 
 ### 下游效果 Performance