align_to_words=False

README.md

@@ -27,17 +27,11 @@ This is a DeBERTa(V2) model pretrained on Thai Wikipedia texts for dependency-pa
 ## How to Use
 
 ```py
-import torch
-from transformers import AutoTokenizer,AutoModelForQuestionAnswering
+from transformers import AutoTokenizer,AutoModelForQuestionAnswering,QuestionAnsweringPipeline
 tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-base-thai-ud-head")
 model=AutoModelForQuestionAnswering.from_pretrained("KoichiYasuoka/deberta-base-thai-ud-head")
-question="กว่า"
-context="หลายหัวดีกว่าหัวเดียว"
-inputs=tokenizer(question,context,return_tensors="pt",return_offsets_mapping=True)
-offsets=inputs.pop("offset_mapping").tolist()[0]
-outputs=model(**inputs)
-start,end=torch.argmax(outputs.start_logits),torch.argmax(outputs.end_logits)
-print(context[offsets[start][0]:offsets[end][-1]])
+qap=QuestionAnsweringPipeline(tokenizer=tokenizer,model=model,align_to_words=False)
+print(qap(question="กว่า",context="หลายหัวดีกว่าหัวเดียว"))
 ```
 
 or (with [ufal.chu-liu-edmonds](https://pypi.org/project/ufal.chu-liu-edmonds/))