Hugging Face's logo

IDEA-CCNL
/
Erlangshen-DeBERTa-v2-710M-Chinese

Fill-Mask
Transformers
PyTorch
Safetensors
Chinese
deberta-v2
bert
Inference Endpoints
Model card Files Community
1
gxy commited on
Commit
5b9a23a
•
1 Parent(s): 202cb71

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -4
README.md CHANGED
@@ -44,10 +44,13 @@ To get a Chinese DeBERTa-v2-xlarge (710M), we use WuDao Corpora (180 GB version)
44
 
45
  We present the results on the following tasks:
46
 
47
- | Model | AFQMC|TNEWS1.1|IFLYTEK|OCNLI | CMNLI |
48
- | ---------------------------------- | ----- | ------ | ------ | ------ | ------ |
49
- | RoBERTa-Large | 0.7488|0.5879|0.6152|0.777 | 0.814 |
50
- | **Erlangshen-Deberta-XLarge-710M-Chinese** | 0.7549|0.5873|0.6177|0.8012|0.8389|
 
 
 
51
 
52
  ## 使用 Usage
53
 
 
44
 
45
  We present the results on the following tasks:
46
 
47
+ | Model | AFQMC | TNEWS1.1 | IFLYTEK | OCNLI | CMNLI |
48
+ | -------------------------------------------------------------------------------------------------------------------------------- | ------ | -------- | ------- | ------ | ------ |
49
+ | RoBERTa-base | 0.7406 | 0.575 | 0.6036 | 0.743 | 0.7973 |
50
+ | RoBERTa-large | 0.7488 | 0.5879 | 0.6152 | 0.777 | 0.814 |
51
+ | [IDEA-CCNL/Erlangshen-DeBERTa-v2-97M-Chinese](https://huggingface.co/IDEA-CCNL/Erlangshen-DeBERTa-v2-97M-Chinese) | 0.7405 | 0.571 | 0.5977 | 0.7568 | 0.807 |
52
+ | [IDEA-CCNL/Erlangshen-DeBERTa-v2-320M-Chinese](https://huggingface.co/IDEA-CCNL/Erlangshen-DeBERTa-v2-320M-Chinese) | 0.7498 | 0.5817 | 0.6042 | 0.8022 | 0.8301 |
53
+ | **[IDEA-CCNL/Erlangshen-DeBERTa-v2-710M-Chinese](https://huggingface.co/IDEA-CCNL/Erlangshen-DeBERTa-v2-710M-Chinese)** | 0.7549 | 0.5873 | 0.6177 | 0.8012 | 0.8389 |
54
 
55
  ## 使用 Usage
56