Update README.md
Browse files
README.md
CHANGED
@@ -32,7 +32,7 @@ We followed the training parameters of the base-scale model of [ELECTRA](https:/
|
|
32 |
#### Vocabulary
|
33 |
|
34 |
vocab size 30,000
|
35 |
-
We used morpheme-based unit tokens for our vocabulary based on the Mecab-Ko
|
36 |
|
37 |
|
38 |
#### Download Link
|
@@ -41,7 +41,7 @@ We used morpheme-based unit tokens for our vocabulary based on the Mecab-Ko[http
|
|
41 |
|
42 |
* PyTorch models on HuggingFace
|
43 |
|
44 |
-
```
|
45 |
from transformers import ElectraModel, ElectraTokenizer
|
46 |
|
47 |
model = ElectraModel.from_pretrained("snunlp/KR-ELECTRA-discriminator")
|
|
|
32 |
#### Vocabulary
|
33 |
|
34 |
vocab size 30,000
|
35 |
+
We used morpheme-based unit tokens for our vocabulary based on the [Mecab-Ko](https://bitbucket.org/eunjeon/mecab-ko-dic/src/master/) morpheme analyzer.
|
36 |
|
37 |
|
38 |
#### Download Link
|
|
|
41 |
|
42 |
* PyTorch models on HuggingFace
|
43 |
|
44 |
+
```python
|
45 |
from transformers import ElectraModel, ElectraTokenizer
|
46 |
|
47 |
model = ElectraModel.from_pretrained("snunlp/KR-ELECTRA-discriminator")
|