idea-teacher commited on
Commit
3518f82
1 Parent(s): a2f0e91

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +58 -0
README.md CHANGED
@@ -1,3 +1,61 @@
1
  ---
 
 
 
2
  license: apache-2.0
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - zh
4
+
5
  license: apache-2.0
6
+
7
+ tags:
8
+ - classification
9
+
10
+ inference: false
11
+
12
  ---
13
+
14
+ # Erlangshen-TCBert-1.3B-Classification-Chinese
15
+
16
+ - Github: [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)
17
+ - Docs: [Fengshenbang-Docs](https://fengshenbang-doc.readthedocs.io/)
18
+
19
+ ## 简介 Brief Introduction
20
+
21
+ 1.3BM参数的Topic Classification BERT (TCBert)。
22
+
23
+ The TCBert with 1.3BM parameters is pre-trained for, not limited to, Chinese topic classification tasks.
24
+
25
+ ## 模型分类 Model Taxonomy
26
+
27
+ | 需求 Demand | 任务 Task | 系列 Series | 模型 Model | 参数 Parameter | 额外 Extra |
28
+ | :----: | :----: | :----: | :----: | :----: | :----: |
29
+ | 通用 General | 自然语言理解 NLU | 二郎神 Erlangshen | TCBert | 1.3BM | Chinese |
30
+
31
+ ## 模型信息 Model Information
32
+
33
+
34
+ 为了提高模型在话题分类上的效果,我们收集了大量话题分类数据进行基于prompts的预训练。
35
+
36
+ To improve the model performance on the topic classification task, we collected numerous topic classification datasets for pre-training based on general prompts.
37
+ ### 下游效果 Performance
38
+
39
+ Stay tuned.
40
+
41
+ ## 使用 Usage
42
+
43
+ ```python
44
+ from transformers import MegatronBertForMaskedLM, BertTokenizer
45
+ import torch
46
+ tokenizer=BertTokenizer.from_pretrained("IDEA-CCNL/Erlangshen-TCBert-1.3BM-Classification-Chinese")
47
+ model=MegatronBertForMaskedLM.from_pretrained('IDEA-CCNL/Erlangshen-TCBert-1.3BM-Classification-Chinese')
48
+ ```
49
+
50
+ 如果您在您的工作中使用了我们的模型,可以引用我们的[网站](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
51
+
52
+ You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
53
+
54
+ ```text
55
+ @misc{Fengshenbang-LM,
56
+ title={Fengshenbang-LM},
57
+ author={IDEA-CCNL},
58
+ year={2021},
59
+ howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
60
+ }
61
+ ```