Update README.md

README.md

@@ -13,9 +13,10 @@ Abstractive Summarization](https://arxiv.org/pdf/1912.08777.pdf) mentioned.
 
 Different from the English version of pegasus, considering that the Chinese sentence piece is unstable, we use jieba and Bertokenizer as the tokenizer in chinese pegasus model.
 
-This model which we provide in hugging face hub is only the pretrain model, which is has not finetuneed with download data.
+This model which we provide in hugging face hub is only the pretrain model, which is has not finetuned with download data.
+
+We also pretained a large model, available with [Randeng_Pegasus_523M_Summary](https://huggingface.co/IDEA-CCNL/Randeng_Pegasus_523M_Summary)
 
- 
 
 Task: Summarization