SuperAI2-Machima
commited on
Commit
•
38c44b5
1
Parent(s):
056c2be
Update README.md
Browse files
README.md
CHANGED
@@ -1,22 +1,36 @@
|
|
1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
3 |
-
|
4 |
|
5 |
-
|
6 |
-
|
7 |
-
tokenizer = T5Tokenizer.from_pretrained("Pollawat/mt5-small-thai-qg")
|
8 |
-
model = MT5ForConditionalGeneration.from_pretrained("Pollawat/mt5-small-thai-qg")
|
9 |
|
10 |
-
|
|
|
11 |
|
12 |
-
|
13 |
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- question-generation
|
4 |
+
language:
|
5 |
+
- thai
|
6 |
+
- th
|
7 |
+
datasets:
|
8 |
+
- NSC2018
|
9 |
+
- wiki-documents-nsc
|
10 |
+
- ThaiQACorpus-DevelopmentDataset
|
11 |
+
license: mit
|
12 |
+
---
|
13 |
+
[Pollawat](https://huggingface.co/Pollawat/mt5-small-thai-qg)
|
14 |
|
15 |
+
[Google's mT5](https://github.com/google-research/multilingual-t5)
|
16 |
|
17 |
+
```python
|
18 |
+
from transformers import T5Tokenizer, T5ForConditionalGeneration, T5Config
|
|
|
|
|
19 |
|
20 |
+
model = T5ForConditionalGeneration.from_pretrained('SuperAI2-Machima/mt5-small-thai-qg')
|
21 |
+
tokenizer = T5Tokenizer.from_pretrained('SuperAI2-Machima/mt5-small-thai-qg')
|
22 |
|
23 |
+
source_text = 'บุกยึดไม้เถื่อน อดีต ส.ส.บุรีรัมย์ เตรียมสร้างคฤหาสน์ทรงไทย 1 กันยายน 2550 12:00 น. ตำรวจภูธรจ.บุรีรัมย์บุกตรวจยึดไม้แปรรูปหวงห้ามกว่า 80 แผ่น'
|
24 |
|
25 |
+
print('Predicted Summary Text : ')
|
26 |
+
tokenized_text = tokenizer.encode(source_text, return_tensors="pt").to(device)
|
27 |
+
summary_ids = model.generate(tokenized_text,
|
28 |
+
num_beams=4,
|
29 |
+
no_repeat_ngram_size=2,
|
30 |
+
max_length=50,
|
31 |
+
early_stopping=True)
|
32 |
+
output = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
|
33 |
+
print(output)
|
34 |
+
#Predicted Summary Text :
|
35 |
+
#answer: 80 แผ่น question: ตํารวจภูธรจ.บุรีรัมย์บุกตรวจยึดไม้แปรรูปหวงห้ามกว่ากี่แผ่น
|
36 |
+
```
|