FEAT: add inference
Browse files
README.md
CHANGED
|
@@ -1,14 +1,16 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- zh
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
|
|
|
|
|
|
|
|
|
|
| 6 |
inference: true
|
| 7 |
|
| 8 |
widget:
|
| 9 |
- text: "生活的真谛是[MASK]。"
|
| 10 |
-
|
| 11 |
-
|
| 12 |
---
|
| 13 |
# Erlangshen-Deberta-97M-Chinese，one model of [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM).
|
| 14 |
The 97 million parameter deberta-V2 base model, using 180G Chinese data, 24 A100(40G) training for 7 days，which is a standard transformer structure. Consumed totally 1B samples.
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- zh
|
| 4 |
+
|
| 5 |
license: apache-2.0
|
| 6 |
|
| 7 |
+
tags:
|
| 8 |
+
- bert
|
| 9 |
+
|
| 10 |
inference: true
|
| 11 |
|
| 12 |
widget:
|
| 13 |
- text: "生活的真谛是[MASK]。"
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
# Erlangshen-Deberta-97M-Chinese，one model of [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM).
|
| 16 |
The 97 million parameter deberta-V2 base model, using 180G Chinese data, 24 A100(40G) training for 7 days，which is a standard transformer structure. Consumed totally 1B samples.
|