Update README.
Browse files
README.md
CHANGED
@@ -12,11 +12,36 @@ datasets:
|
|
12 |
metrics:
|
13 |
---
|
14 |
|
15 |
-
# CKIP ALBERT Base Chinese
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Contributers
|
18 |
|
19 |
* [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
|
20 |
|
21 |
-
##
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
metrics:
|
13 |
---
|
14 |
|
15 |
+
# CKIP ALBERT Base Chinese
|
16 |
+
|
17 |
+
This project provides traditional Chinese transformers models (including ALBERT, BERT, GPT2) and NLP tools (including word segmentation, part-of-speech tagging, named entity recognition).
|
18 |
+
|
19 |
+
這個專案提供了繁體中文的 transformers 模型(包含 ALBERT、BERT、GPT2)及自然語言處理工具(包含斷詞、詞性標記、實體辨識)。
|
20 |
+
|
21 |
+
## Homepage
|
22 |
+
|
23 |
+
* https://github.com/ckiplab/ckip-transformers
|
24 |
|
25 |
## Contributers
|
26 |
|
27 |
* [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
|
28 |
|
29 |
+
## Usage
|
30 |
+
|
31 |
+
Please use BertTokenizerFast as tokenizer instead of AutoTokenizer.
|
32 |
+
|
33 |
+
請使用 BertTokenizerFast 而非 AutoTokenizer。
|
34 |
+
|
35 |
+
```
|
36 |
+
from transformers import (
|
37 |
+
BertTokenizerFast,
|
38 |
+
AutoModelForTokenClassification,
|
39 |
+
)
|
40 |
+
|
41 |
+
tokenizer = BertTokenizerFast.from_pretrained('bert-base-chinese')
|
42 |
+
model = AutoModelForTokenClassification.from_pretrained('ckiplab/albert-base-chinese-ner')
|
43 |
+
```
|
44 |
+
|
45 |
+
For full usage and more information, please refer to https://github.com/ckiplab/ckip-transformers.
|
46 |
+
|
47 |
+
有關完整使用方法及其他資訊,請參見 https://github.com/ckiplab/ckip-transformers 。
|