Update README.md

README.md

@@ -1,3 +1,7 @@
+---
+language:
+- zh
+---
 # 中文预训练Longformer模型 | Longformer_ZH with PyTorch 
 
 相比于Transformer的O(n^2)复杂度，Longformer提供了一种以线性复杂度处理最长4K字符级别文档序列的方法。Longformer Attention包括了标准的自注意力与全局注意力机制，方便模型更好地学习超长序列的信息。
@@ -37,8 +41,8 @@ LongformerZhForMaksedLM.from_pretrained('ValkyriaLenneth/longformer_zh')
 ## 关于预训练 | About Pretraining
 - 我们的预训练语料来自 https://github.com/brightmart/nlp_chinese_corpus， 根据Longformer原文的设置，采用了多种语料混合的预训练数据。
 - The corpus of pretraining is from https://github.com/brightmart/nlp_chinese_corpus. Based on the paper of Longformer, we use a mixture of 4 different chinese corpus for pretraining.
-- 我们的模型是基于Roberta_zh_mid (https://github.com/brightmart/roberta_zh),训练脚本参考了https://github.com/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb
-- The basement of our model is Roberta_zh_mid (https://github.com/brightmart/roberta_zh). Pretraining scripts is modified from https://github.com/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb.
+- 我们的模型是基于[Roberta_zh_mid](https://github.com/brightmart/roberta_zh),训练脚本参考https://github.com/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb
+- The basement of our model is [Roberta_zh_mid](https://github.com/brightmart/roberta_zh). Pretraining scripts is modified from https://github.com/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb.
 
 - 同时我们在原版基础上，引入了 `Whole-Word-Masking` 机制，以便更好地适应中文特性。
 - We introduce `Whole-Word-Masking` method into pretraining for better fitting Chinese language.
@@ -97,6 +101,4 @@ LongformerZhForMaksedLM.from_pretrained('ValkyriaLenneth/longformer_zh')
 ## 致谢
 感谢东京工业大学 奥村·船越研究室 提供算力。
 
-Thanks Okumula·Funakoshi Lab from Tokyo Institute of Technology who provides the devices and oppotunity for me to finish this project.
-
-
+Thanks Okumula·Funakoshi Lab from Tokyo Institute of Technology who provides the devices and oppotunity for me to finish this project.