IDEA-CCNL
/

Erlangshen-DeBERTa-v2-97M-Chinese

Inference Endpoints

Model card Files Files and versions Community

gxy commited on Sep 1, 2022

Commit

7a9f37f

•

1 Parent(s): bd9fee0

fix readme

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ 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-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)

 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)