wanng commited on
Commit
c98126c
1 Parent(s): 694aacf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -6
README.md CHANGED
@@ -36,17 +36,19 @@ widget:
36
 
37
  ## 模型信息 Model Information
38
 
 
39
 
 
40
 
41
- **YuyuanQA-GPT2-3.5B** is fine-tuned with 10000 medical QA pairs based on **Yuyuan-3.5B** model.
42
 
43
- **Question answering(QA)** is an important subject related to natural language processing and information retrieval. There are many application scenarios in the actual industry. **Traditional methods are often complex**, and their core algorithms involve **machine learning**, **deep learning** and **knowledge graph** related knowledge.
44
 
45
- We hope to explore a **simpler** and more **effective** way to use the powerful memory and understanding ability of the large model to directly realize question and answering. Yuyuanqa-GPT2-3.5b model is an attempt and **performs well under subjective test**. At the same time, we also tested 100 QA pairs with **BLEU**:
46
 
47
  | gram | 1-gram | 2-gram | 3-gram | 4-gram |
48
- | ----------- | ----------- |------|------|------|
49
- | blue_score | 0.357727 | 0.2713 | 0.22304 | 0.19099 |
50
 
51
  ## 使用 Usage
52
 
@@ -85,7 +87,11 @@ for idx,sentence in enumerate(generation_output.sequences):
85
 
86
  ```
87
 
88
- We made a demo of medical Q & A with YuyuanQA-GPT2-3.5B model. In the future, we will make this product into a wechat app to meet you. Please look forward to it.
 
 
 
 
89
 
90
  ![avatar](https://huggingface.co/IDEA-CCNL/YuyuanQA-GPT2-3.5B/resolve/main/QA-DEMO.png)
91
 
 
36
 
37
  ## 模型信息 Model Information
38
 
39
+ 问答在自然语言处理领域中反映AI系统的知识水平的重要任务。为了可以在医疗领域中使用强大的问答能力的语言模型,我们基于Yuyuan-GPT2-3.5B,对其使用了10K条医疗的问答对进行微调。我们希望探索一种简单、有效的方式直接实现问答系统而不需要额外的设计,即利用大模型强大的记忆力和理解能力。
40
 
41
+ Question answering (QA) is an important task in the Natural Language Processing to present the knowledge level of AI systems. To provide a language model with powerful QA capability in the medical domain, we fine-tuned Yuyuan-GPT2-3.5B on 10K medical Q&A pairs.
42
 
43
+ ### 下游任务 Performance
44
 
45
+ 我们测试了该模型在未见过的100条QA对上的表现:
46
 
47
+ We tested the model on 100 unseen QA pairs:
48
 
49
  | gram | 1-gram | 2-gram | 3-gram | 4-gram |
50
+ | :----: | :----: |:----: | :----: | :----: |
51
+ | blue score | 0.357727 | 0.2713 | 0.22304 | 0.19099 |
52
 
53
  ## 使用 Usage
54
 
 
87
 
88
  ```
89
 
90
+ ### 演示 Demo
91
+
92
+ 我们用该模型做了一个医疗问答演示。将来,我们会将这款产品做成微信小程序与大家见面。
93
+
94
+ We made a demo of medical QA system with this model. In the future, we will make this product into a wechat app to meet you.
95
 
96
  ![avatar](https://huggingface.co/IDEA-CCNL/YuyuanQA-GPT2-3.5B/resolve/main/QA-DEMO.png)
97