language: ko | |
tags: | |
- bart | |
license: mit | |
## KoBART-base-v2 | |
With the addition of chatting data, the model is trained to handle the semantics of sequences longer than KoBART. | |
### Performance | |
NSMC | |
- acc. : 0.901 | |
language: ko | |
tags: | |
- bart | |
license: mit | |
## KoBART-base-v2 | |
With the addition of chatting data, the model is trained to handle the semantics of sequences longer than KoBART. | |
### Performance | |
NSMC | |
- acc. : 0.901 | |