tweak
Browse files
README.md
CHANGED
|
@@ -43,7 +43,7 @@ You can also fine-tune this model on downstream tasks.
|
|
| 43 |
|
| 44 |
The input text should be segmented into words by [Juman++](https://github.com/ku-nlp/jumanpp) in advance. [Juman++ 2.0.0-rc3](https://github.com/ku-nlp/jumanpp/releases/tag/v2.0.0-rc3) was used for pre-training. Each word is tokenized into subwords by [sentencepiece](https://github.com/google/sentencepiece).
|
| 45 |
|
| 46 |
-
## Training
|
| 47 |
|
| 48 |
We used the following corpora for pre-training:
|
| 49 |
|
|
|
|
| 43 |
|
| 44 |
The input text should be segmented into words by [Juman++](https://github.com/ku-nlp/jumanpp) in advance. [Juman++ 2.0.0-rc3](https://github.com/ku-nlp/jumanpp/releases/tag/v2.0.0-rc3) was used for pre-training. Each word is tokenized into subwords by [sentencepiece](https://github.com/google/sentencepiece).
|
| 45 |
|
| 46 |
+
## Training data
|
| 47 |
|
| 48 |
We used the following corpora for pre-training:
|
| 49 |
|