Update README.md
Browse files
README.md
CHANGED
@@ -20,14 +20,16 @@ widget:
|
|
20 |
# From modern Chinese to Ancient Chinese
|
21 |
> This model translate modern Chinese to Classical Chinese, so I guess who's interested in the problemset can speak at least modern Chinese, so... let me continue the documentation in Chinese
|
22 |
|
23 |
-
|
24 |
|
25 |
-
|
|
|
|
|
26 |
|
27 |
## 推荐的inference 通道
|
28 |
**注意**, 你必须将```generate```函数的```eos_token_id```设置为102就可以翻译出完整的语句, 不然翻译完了会有残留的语句(因为做熵的时候用pad标签=-100导致)。
|
29 |
|
30 |
-
目前huggingface 页面上compute按钮会有这个问题,
|
31 |
```python
|
32 |
from transformers import (
|
33 |
EncoderDecoderModel,
|
|
|
20 |
# From modern Chinese to Ancient Chinese
|
21 |
> This model translate modern Chinese to Classical Chinese, so I guess who's interested in the problemset can speak at least modern Chinese, so... let me continue the documentation in Chinese
|
22 |
|
23 |
+
* 从现代文到文言文的翻译器, 欢迎前往[github文言诗词项目页面:渊, 讨论&加⭐️ ](https://github.com/raynardj/yuan)
|
24 |
|
25 |
+
* 还有同款的[🤗文言文到现代文模型](https://huggingface.co/raynardj/wenyanwen-ancient-translate-to-modern),原文输入可以**断句** 也可以是**未断句**的哦
|
26 |
+
|
27 |
+
* 训练语料是就是九十多万句句对, [数据集链接📚](https://github.com/BangBOOM/Classical-Chinese)。
|
28 |
|
29 |
## 推荐的inference 通道
|
30 |
**注意**, 你必须将```generate```函数的```eos_token_id```设置为102就可以翻译出完整的语句, 不然翻译完了会有残留的语句(因为做熵的时候用pad标签=-100导致)。
|
31 |
|
32 |
+
目前huggingface 页面上compute按钮会有这个问题, 推荐使用以下代码来得到翻译结果🎻
|
33 |
```python
|
34 |
from transformers import (
|
35 |
EncoderDecoderModel,
|