Update README.md

README.md

@@ -1,7 +1,7 @@
 # <a name="introduction"></a> BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese
 
 
-The pre-trained model `vinai/bartpho-base-syllable` is the "base" variant of `BARTpho-syllable`, which uses the "base" architecture and pre-training scheme of the sequence-to-sequence denoising model [BART](https://github.com/pytorch/fairseq/tree/main/examples/bart). The general architecture and experimental results of BARTpho can be found in our [paper](https://arxiv.org/abs/2109.09701):
+The pre-trained model `vinai/bartpho-syllable-base` is the "base" variant of `BARTpho-syllable`, which uses the "base" architecture and pre-training scheme of the sequence-to-sequence denoising model [BART](https://github.com/pytorch/fairseq/tree/main/examples/bart). The general architecture and experimental results of BARTpho can be found in our [paper](https://arxiv.org/abs/2109.09701):
 
 	@article{bartpho,
 	title     = {{BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese}},