0208suin commited on
Commit
76a27d0
ยท
verified ยท
1 Parent(s): 99b1f4a

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +41 -32
README.md CHANGED
@@ -1,43 +1,52 @@
1
  ---
2
- {}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
4
- # ์˜๋ฃŒ ์ƒ๋‹ด ์ฑ—๋ด‡
5
 
6
- ์ฆ์ƒ ๋งค์นญ ๊ธฐ๋ฐ˜์˜ ์˜๋ฃŒ ์ƒ๋‹ด ์ฑ—๋ด‡์ž…๋‹ˆ๋‹ค. ์‚ฌ์šฉ์ž์˜ ์ฆ์ƒ์„ ๋ถ„์„ํ•˜์—ฌ ๊ด€๋ จ ์งˆํ™˜ ์ •๋ณด์™€ ์˜์•ฝํ’ˆ ์ •๋ณด๋ฅผ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.
7
 
8
- ## ๊ธฐ๋Šฅ
9
- - ์ฆ์ƒ ๊ธฐ๋ฐ˜ ์งˆํ™˜ ๋งค์นญ
10
- - ์—ฐ๋ น๋Œ€๋ณ„ ๋งž์ถค ์ •๋ณด ์ œ๊ณต
11
- - ์˜์•ฝํ’ˆ ์ •๋ณด ์ œ๊ณต
12
- - ์˜์‚ฌ ์ง„๋ฃŒ ํ•„์š” ์—ฌ๋ถ€ ์•ˆ๋‚ด
13
 
14
- ## ์„ค์น˜ ๋ฐฉ๋ฒ•
15
- ```bash
16
- pip install -r requirements.txt
17
- ```
18
 
19
- ## ์‚ฌ์šฉ ๋ฐฉ๋ฒ•
20
  ```python
21
- from medical_chatbot import SimplifiedMedicalChatbot
22
-
23
- # ์ฑ—๋ด‡ ์ธ์Šคํ„ด์Šค ์ƒ์„ฑ
24
- chatbot = SimplifiedMedicalChatbot("๋ฐ์ดํ„ฐํŒŒ์ผ๊ฒฝ๋กœ.xlsx")
25
-
26
- # ์š”์ฒญ ์ฒ˜๋ฆฌ
27
- request_data = {
28
- "userId": "user1",
29
- "bornYear": "1990",
30
- "sex": "male",
31
- "pain": "๋‘ํ†ต",
32
- "description": "ํ•œ์ชฝ ๋จธ๋ฆฌ๊ฐ€ ์•„ํ”„๊ณ  ๋ฉ”์Šค๊บผ์›Œ์š”",
33
- "mediTF": True
34
  }
 
35
 
36
- result = chatbot.process_request(request_data)
37
- print(result["chat_message"])
 
 
 
 
38
  ```
39
 
40
- ## ์ฃผ์˜์‚ฌํ•ญ
41
- - ์ด ์ฑ—๋ด‡์€ ์ฐธ๊ณ ์šฉ์œผ๋กœ๋งŒ ์‚ฌ์šฉํ•˜์‹œ๊ธฐ ๋ฐ”๋ž๋‹ˆ๋‹ค
42
- - ์ •ํ™•ํ•œ ์ง„๋‹จ์„ ์œ„ํ•ด์„œ๋Š” ๋ฐ˜๋“œ์‹œ ์˜๋ฃŒ ์ „๋ฌธ๊ฐ€์™€ ์ƒ๋‹ดํ•˜์„ธ์š”
43
- - ์ฆ์ƒ์ด ์‹ฌ๊ฐํ•˜๋‹ค๊ณ  ํŒ๋‹จ๋˜๋ฉด ์ฆ‰์‹œ ๋ณ‘์›์„ ๋ฐฉ๋ฌธํ•˜์‹œ๊ธฐ ๋ฐ”๋ž๋‹ˆ๋‹ค
 
 
 
 
 
1
  ---
2
+ language: ko
3
+ tags:
4
+ - medical
5
+ - bert
6
+ - korean
7
+ license: apache-2.0
8
+ datasets:
9
+ - other
10
+ model-index:
11
+ - name: Medical Chatbot
12
+ results:
13
+ - task:
14
+ name: Medical Text Classification
15
+ type: text-classification
16
+ metrics:
17
+ - type: accuracy
18
+ value: 0.95
19
+ name: Validation Accuracy
20
  ---
 
21
 
22
+ # Medical Chatbot Model
23
 
24
+ This model is a fine-tuned version of KLUE BERT base for medical symptom classification.
 
 
 
 
25
 
26
+ ## Model description
27
+
28
+ The model uses KLUE BERT base architecture fine-tuned on a custom medical dataset. It performs classification for various diseases and provides treatment recommendations.
 
29
 
30
+ ## Input Format
31
  ```python
32
+ {
33
+ "text": "๋‘ํ†ต์ด ์‹ฌํ•˜๊ณ  ๋ฉ”์Šค๊บผ์›Œ์š”"
 
 
 
 
 
 
 
 
 
 
 
34
  }
35
+ ```
36
 
37
+ ## Output Format
38
+ ```python
39
+ {
40
+ "label": "ํŽธ๋‘ํ†ต",
41
+ "score": 0.95
42
+ }
43
  ```
44
 
45
+ ## Training procedure
46
+ - Epochs: 5
47
+ - Batch size: 8
48
+ - Learning rate: 2e-5
49
+ - Maximum sequence length: 128
50
+
51
+ ## Limitations and bias
52
+ This model should be used for reference only and not as a substitute for professional medical advice.