Update README.md
Browse files
README.md
CHANGED
@@ -11,9 +11,32 @@ inference:
|
|
11 |
|
12 |
license: apache-2.0
|
13 |
---
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
As we all know, the single direction language model based on decoder structure has strong generation ability, such as GPT model. **The 3.5 billion parameter Wenzhong-GPT2-3.5B large model, using 100G chinese common data, 32 A100 training for 28 hours,** is the largest open source **GPT2 large model of chinese**. **Our model performs well in Chinese continuation generation.**
|
16 |
|
|
|
|
|
|
|
17 |
## Usage
|
18 |
|
19 |
### load model
|
@@ -34,9 +57,27 @@ generator("北京位于", max_length=30, num_return_sequences=1)
|
|
34 |
|
35 |
```
|
36 |
|
37 |
-
## Citation
|
38 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
@misc{Fengshenbang-LM,
|
41 |
title={Fengshenbang-LM},
|
42 |
author={IDEA-CCNL},
|
|
|
11 |
|
12 |
license: apache-2.0
|
13 |
---
|
14 |
+
|
15 |
+
# Wenzhong-GPT2-3.5B model (chinese)
|
16 |
+
|
17 |
+
- Github: [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)
|
18 |
+
- Docs: [Fengshenbang-Docs](https://fengshenbang-doc.readthedocs.io/)
|
19 |
+
|
20 |
+
## 简介 Brief Introduction
|
21 |
+
|
22 |
+
善于处理NLG任务,目前最大的,中文版的GPT2
|
23 |
+
|
24 |
+
Focused on handling NLG tasks, the current largest, Chinese GPT2.
|
25 |
+
|
26 |
+
|
27 |
+
## 模型分类 Model Taxonomy
|
28 |
+
|
29 |
+
| 需求 Demand | 任务 Task | 系列 Series | 模型 Model | 参数 Parameter | 额外 Extra |
|
30 |
+
| :----: | :----: | :----: | :----: | :----: | :----: |
|
31 |
+
| 通用 General | 自然语言生成 NLG| 闻仲 Wenzhong | GPT2 | 3.5B | - |
|
32 |
+
|
33 |
+
|
34 |
+
one model of [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM).
|
35 |
As we all know, the single direction language model based on decoder structure has strong generation ability, such as GPT model. **The 3.5 billion parameter Wenzhong-GPT2-3.5B large model, using 100G chinese common data, 32 A100 training for 28 hours,** is the largest open source **GPT2 large model of chinese**. **Our model performs well in Chinese continuation generation.**
|
36 |
|
37 |
+
|
38 |
+
|
39 |
+
|
40 |
## Usage
|
41 |
|
42 |
### load model
|
|
|
57 |
|
58 |
```
|
59 |
|
60 |
+
## 引用 Citation
|
61 |
+
|
62 |
+
如果您在您的工作中使用了我们的模型,可以引用我们的[论文](https://arxiv.org/abs/2209.02970):
|
63 |
+
|
64 |
+
If you are using the resource for your work, please cite the our [paper](https://arxiv.org/abs/2209.02970):
|
65 |
+
|
66 |
+
```text
|
67 |
+
@article{fengshenbang,
|
68 |
+
author = {Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen and Ruyi Gan and Jiaxing Zhang},
|
69 |
+
title = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence},
|
70 |
+
journal = {CoRR},
|
71 |
+
volume = {abs/2209.02970},
|
72 |
+
year = {2022}
|
73 |
+
}
|
74 |
```
|
75 |
+
|
76 |
+
也可以引用我们的[网站](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
|
77 |
+
|
78 |
+
You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
|
79 |
+
|
80 |
+
```text
|
81 |
@misc{Fengshenbang-LM,
|
82 |
title={Fengshenbang-LM},
|
83 |
author={IDEA-CCNL},
|