ku-nlp
/

deberta-v2-base-japanese

Inference Endpoints

Model card Files Files and versions Community

nobu-g commited on Jan 5, 2023

Commit

45fc723

•

1 Parent(s): 06c4e0f

fix README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ metrics:
   - accuracy
 mask_token: "[MASK]"
 widget:
-    - text: "京都大学で自然言語処理を[MASK]する。"
 ---
 # Model Card for Japanese DeBERTa V2 base
@@ -32,7 +32,7 @@ from transformers import AutoTokenizer, AutoModelForMaskedLM
 tokenizer = AutoTokenizer.from_pretrained('ku-nlp/deberta-v2-base-japanese')
 model = AutoModelForMaskedLM.from_pretrained('ku-nlp/deberta-v2-base-japanese')
-sentence = '京都大学で自然言語処理を[MASK]する。'
 encoding = tokenizer(sentence, return_tensors='pt')
 ...
 ```

   - accuracy
 mask_token: "[MASK]"
 widget:
+    - text: "京都 大学 で 自然 言語 処理 を [MASK] する 。"
 ---
 # Model Card for Japanese DeBERTa V2 base
 tokenizer = AutoTokenizer.from_pretrained('ku-nlp/deberta-v2-base-japanese')
 model = AutoModelForMaskedLM.from_pretrained('ku-nlp/deberta-v2-base-japanese')
+sentence = '京都 大学 で 自然 言語 処理 を [MASK] する 。'  # input should be segmented into words by Juman++ in advance
 encoding = tokenizer(sentence, return_tensors='pt')
 ...
 ```