File size: 1,937 Bytes
f782642
 
 
 
 
 
 
eec803b
 
2f5e055
eec803b
0c5077b
 
 
 
f782642
eec803b
 
 
f782642
8d97988
 
 
f782642
 
 
 
8d97988
 
36d298a
2f5e055
36d298a
f782642
8d97988
36d298a
 
f782642
 
2f5e055
36d298a
f782642
36d298a
f782642
8d97988
36d298a
 
f782642
 
8d97988
 
f782642
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
---
license: openrail
language:
- en
pipeline_tag: text-generation
tags:
- medical

widget:
- text: "Prompt: To start, could you tell me the things that you like about smoking?\nResponse: It helps me stay focused when I'm working\n"
  example_title: "What do you like about smoking?"

- text: "Prompt: Now, what is one thing about your smoking habit that you would like to change?\nResponse: I would love to decrease the number of cigarettes per day.\n"
  example_title: "What would you change about your about smoking?"

---


  
# GPT2-MI-Reflector

### A gpt2 based motivational interviewing reflector

Given a prompt and a response, this GPT2 based transformer will generate a reflection. It was fine-tuned on prompt/response/reflection triplets so it should also be inferenced with the same input style. Examples are shown below.

The triplets this reflector was fine-tuned on focus on smoking-cessation. Given this, its best performance is when inferencing about smoking.

To properly inference model (as it was fine-tuned), use the following format:

-------------------------------------------------------------------------------------------------------------------
Prompt: ...Question from bot...

Response: ...Response from user...

-------------------------------------------------------------------------------------------------------------------

Example Prompt: paste two lines below and generate a reflection
-------------------------------------------------------------------------------------------------------------------
Prompt: What do you want to change in your smoking?

Response: I want to smoke less often in my life, its become quite stressful for me.

-------------------------------------------------------------------------------------------------------------------



Model should generate a motivational interviewing adherent statement



This is the first model (of many!) that I'll upload to huggingface!