align_to_words=False does not work

README.md

@@ -30,11 +30,16 @@ This is a DeBERTa(V2) model pretrained on 青空文庫 for dependency-parsing (h
 ## How to Use
 
 ```py
-from transformers import AutoTokenizer,AutoModelForQuestionAnswering,QuestionAnsweringPipeline
+import torch
+from transformers import AutoTokenizer,AutoModelForQuestionAnswering
 tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-large-japanese-unidic-ud-head")
 model=AutoModelForQuestionAnswering.from_pretrained("KoichiYasuoka/deberta-large-japanese-unidic-ud-head")
-qap=QuestionAnsweringPipeline(tokenizer=tokenizer,model=model,align_to_words=False)
-print(qap(question="国語",context="全学年にわたって小学校の国語の教科書に挿し絵が用いられている"))
+question="国語"
+context="全学年にわたって小学校の国語の教科書に挿し絵が用いられている"
+inputs=tokenizer(question,context,return_tensors="pt")
+outputs=model(**inputs)
+start,end=torch.argmax(outputs.start_logits),torch.argmax(outputs.end_logits)
+print(tokenizer.convert_ids_to_tokens(inputs["input_ids"][0,start:end+1]))
 ```
 
 or