Update README.md

README.md

@@ -5,19 +5,13 @@ widget:
 
 ---
 
-# Chinese GPT2 Language Models
+# Chinese GPT2 Language Model
 
 ## Model description
 
-This is the set of  two Chinese GPT2 language models pre-trained by [UER-py](https://www.aclweb.org/anthology/D19-3041.pdf).
-
-You can download the two Chinese GPT2 language models via HuggingFace from the links below:
-
-|     Model     |          [gpt2-chinese-poem][poem]           |     [gpt2-chinese-couplet][couplet]     |
-| :-----------: | :------------------------------------------: | :-------------------------------------: |
-| Training data | Contains about 800,000 chinese ancient poems | Contains about 700,000 chinese couplets |
-
+This model is used to generate Chinese couplets and is pre-trained by [UER-py](https://www.aclweb.org/anthology/D19-3041.pdf).
 
+You can download this model via HuggingFace from the link :[gpt2-chinese-couplet][couplet]
 
 ## How to use
 
@@ -51,7 +45,7 @@ When the parameter ***skip_special_tokens***  is Flase:
 
 ## Training data
 
-Contains about 800,000 chinese ancient poems.
+Contains about 700,000 chinese couplets.
 
 ## Training procedure
 
@@ -88,5 +82,5 @@ python3 pretrain.py --dataset_path couplet.pt \
 }
 ```
 
-[poem]: https://huggingface.co/uer/gpt2-chinese-poem
-[couplet]: https://huggingface.co/uer/gpt2-chinese-couplet
+[couplet]: https://huggingface.co/uer/gpt2-chinese-couplet
+