Update README.md

README.md

@@ -20,9 +20,9 @@ widget:
 
 ## 简介 Brief Introduction
 
-善于处理NLU任务，采用全词掩码的，中文版的0.97亿参数DeBERTa-v2。
+善于处理NLU任务，采用全词掩码的，中文版的0.97亿参数DeBERTa-v2-Base。
 
-Good at solving NLU tasks, adopting Whole Word Masking, Chinese DeBERTa-v2 with 97M parameters.
+Good at solving NLU tasks, adopting Whole Word Masking, Chinese DeBERTa-v2-Base with 97M parameters.
 
 ## 模型分类 Model Taxonomy
 
@@ -35,9 +35,9 @@ Good at solving NLU tasks, adopting Whole Word Masking, Chinese DeBERTa-v2 with
 
 参考论文：[DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://readpaper.com/paper/3033187248)
 
-为了得到一个中文版的DeBERTa-v2（97M），我们用悟道语料库(180G版本)进行预训练。我们在MLM中使用了全词掩码(wwm)的方式。具体地，我们在预训练阶段中使用了[封神框架](https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen)大概花费了24张A100约7天。
+为了得到一个中文版的DeBERTa-v2-Base（97M），我们用悟道语料库(180G版本)进行预训练。我们在MLM中使用了全词掩码(wwm)的方式。具体地，我们在预训练阶段中使用了[封神框架](https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen)大概花费了24张A100约7天。
 
-To get a Chinese DeBERTa-v2 (97M), we use WuDao Corpora (180 GB version) for pre-training. We employ the Whole Word Masking (wwm) in MLM. Specifically, we use the [fengshen framework](https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen) in the pre-training phase which cost about 7 days with 24 A100 GPUs.
+To get a Chinese DeBERTa-v2-Base (97M), we use WuDao Corpora (180 GB version) for pre-training. We employ the Whole Word Masking (wwm) in MLM. Specifically, we use the [fengshen framework](https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen) in the pre-training phase which cost about 7 days with 24 A100 GPUs.
 
 ### 下游任务 Performance