Commit
·
f9c136d
1
Parent(s):
052598d
model improved
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ mask_token: "[MASK]"
|
|
| 14 |
|
| 15 |
## Model Description
|
| 16 |
|
| 17 |
-
This is a DeBERTa(V2) model pre-trained on Chinese Wikipedia texts (both simplified and traditional). NVIDIA A100-SXM4-40GB took
|
| 18 |
|
| 19 |
## How to Use
|
| 20 |
|
|
|
|
| 14 |
|
| 15 |
## Model Description
|
| 16 |
|
| 17 |
+
This is a DeBERTa(V2) model pre-trained on Chinese Wikipedia texts (both simplified and traditional). NVIDIA A100-SXM4-40GB took 102 hours 34 minutes for training. You can fine-tune `deberta-base-chinese` for downstream tasks, such as [POS-tagging](https://huggingface.co/KoichiYasuoka/deberta-base-chinese-upos), [dependency-parsing](https://huggingface.co/KoichiYasuoka/deberta-base-chinese-ud-goeswith), and so on.
|
| 18 |
|
| 19 |
## How to Use
|
| 20 |
|