Lauler commited on
Commit
ee9f69f
1 Parent(s): 7da14c9

update readme

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -7,10 +7,9 @@ widget:
7
 
8
  ## KB-BART
9
 
10
- **EXPERIMENTAL:** still work in progress.
11
-
12
- BART trained on Swedish data.
13
 
 
14
 
15
  ## Usage
16
 
 
7
 
8
  ## KB-BART
9
 
10
+ A [BART](https://arxiv.org/abs/1910.13461) model trained on a Swedish corpus consisting of 15 billion tokens (about 80GB of text). The model was trained with [Fairseq](https://github.com/pytorch/fairseq), and converted to be compatible with Huggingface.
 
 
11
 
12
+ Training code can be found [here](https://github.com/kb-labb/kb_bart).
13
 
14
  ## Usage
15