Update README.md

README.md

@@ -12,8 +12,8 @@ With the addition of chatting data, the model is trained to handle the semantics
 ```python
 from transformers import PreTrainedTokenizerFast, BartModel
 
-tokenizer = PreTrainedTokenizerFast.from_pretrained('gogamza/kobart-base-v2')
-model = BartModel.from_pretrained('gogamza/kobart-base-v2')
+tokenizer = PreTrainedTokenizerFast.from_pretrained('hyunwoongko/kobart')
+model = BartModel.from_pretrained('hyunwoongko/kobart')
 ```
 
 ### Performance