IDEA-CCNL
/

Erlangshen-DeBERTa-v2-97M-Chinese

Model card Files Files and versions Community

gxy commited on Aug 31, 2022

Commit

bd9fee0

·

1 Parent(s): ad248ff

BUGFIX: fix readme name

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -26,8 +26,8 @@ Erlangshen-Deberta-97M-Chinese is pre-trained by bert like mask task from Debert
 from transformers import AutoModelForMaskedLM, AutoTokenizer, FillMaskPipeline
 import torch
-tokenizer=AutoTokenizer.from_pretrained('IDEA-CCNL/Erlangshen-Deberta-97M-Chinese', use_fast=false)
-model=AutoModelForMaskedLM.from_pretrained('IDEA-CCNL/Erlangshen-Deberta-97M-Chinese')
 text = '生活的真谛是[MASK]。'
 fillmask_pipe = FillMaskPipeline(model, tokenizer, device=7)
 print(fillmask_pipe(text, top_k=10))

 from transformers import AutoModelForMaskedLM, AutoTokenizer, FillMaskPipeline
 import torch
+tokenizer=AutoTokenizer.from_pretrained('IDEA-CCNL/Erlangshen-DeBERTa-v2-97M-Chinese', use_fast=false)
+model=AutoModelForMaskedLM.from_pretrained('IDEA-CCNL/Erlangshen-DeBERTa-v2-97M-Chinese')
 text = '生活的真谛是[MASK]。'
 fillmask_pipe = FillMaskPipeline(model, tokenizer, device=7)
 print(fillmask_pipe(text, top_k=10))