CHEN-WEI,LI
commited on
Commit
•
b9ba40f
1
Parent(s):
f02ceae
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,45 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- zh
|
5 |
+
library_name: transformers
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
tags:
|
8 |
+
- Doctor_consultation
|
9 |
+
- Taiwan
|
10 |
+
- fine-tuning
|
11 |
+
- medicine
|
12 |
---
|
13 |
+
|
14 |
+
# 🔎 Taiwan-inquiry_7B_v2.0
|
15 |
+
|
16 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
17 |
+
|
18 |
+
|
19 |
+
"
|
20 |
+
The model underwent refinement by utilizing the Taiwan-inquiry_7B_v1.0 model as a foundation and
|
21 |
+
fine-tuning it with a dataset comprising 235 synthetic dialogues generated from [Breexe-8x7B-Instruct-v0_1](https://huggingface.co/MediaTek-Research/Breexe-8x7B-Instruct-v0_1).
|
22 |
+
This dataset specifically concentrated on over 150 diseases, encompassing their symptoms and corresponding therapies.
|
23 |
+
The objective of the training process was to augment the model's proficiency in comprehending a wide array of diseases and formulating appropriate responses. "
|
24 |
+
|
25 |
+
### Model Description
|
26 |
+
|
27 |
+
<!-- Provide a longer summary of what this model is. -->
|
28 |
+
|
29 |
+
- **Developed by:** [Joseph (Chen-Wei) Li](https://www.linkedin.com/in/joseph-li-3a453b231/), researcher assistant from National Taiwan University Hospital.
|
30 |
+
- **Model type:** A 7B parameter GPT-like model fine-tuned on a combination of private and synthetic dialogue datasets.
|
31 |
+
- **Language(s) (NLP):** Traditional Chinese (zh-tw)
|
32 |
+
- **Finetuned from model :** [Taiwan-inquiry_7B_v1.0](https://huggingface.co/JosephLi0419/Taiwan-inquiry_7B_v1.0)
|
33 |
+
|
34 |
+
### Usage of the model
|
35 |
+
The user can take on the role of a doctor, and the model can engage in conversation with you as if it were a patient.
|
36 |
+
You can provide the model with a brief patient background in the system prompt, and the model will respond based on that prompt.
|
37 |
+
**You can directly ask the certain disease about the symptoms and the possible therapies.**
|
38 |
+
|
39 |
+
### Demo
|
40 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c07d1b2357c1bded7a92fa/w6Hl5PuPW02Zpd7lhzCWC.png)
|
41 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c07d1b2357c1bded7a92fa/UrNZGh--B0m24b37e7I8t.png)
|
42 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c07d1b2357c1bded7a92fa/GT1WCRCl4v79auBCkJyC7.png)
|
43 |
+
|
44 |
+
|
45 |
+
|