Migrate model card from transformers-repo
Browse filesRead announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/kuppuluri/telugu_bertu_tydiqa/README.md
README.md
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Telugu Question-Answering model trained on Tydiqa dataset from Google
|
2 |
+
|
3 |
+
#### How to use
|
4 |
+
|
5 |
+
```python
|
6 |
+
from transformers.pipelines import pipeline, AutoModelForQuestionAnswering, AutoTokenizer
|
7 |
+
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
|
8 |
+
tokenizer = AutoTokenizer.from_pretrained("kuppuluri/telugu_bertu_tydiqa",
|
9 |
+
clean_text=False,
|
10 |
+
handle_chinese_chars=False,
|
11 |
+
strip_accents=False,
|
12 |
+
wordpieces_prefix='##')
|
13 |
+
nlp = pipeline('question-answering', model=model, tokenizer=tokenizer)
|
14 |
+
result = nlp({'question': question, 'context': context})
|
15 |
+
```
|
16 |
+
|
17 |
+
## Training data
|
18 |
+
I used Tydiqa Telugu data from Google https://github.com/google-research-datasets/tydiqa
|