license: openrail
language:
- en
pipeline_tag: text-generation
tags:
- medical
widget:
- text: >
<|startoftext|> Prompt: To start, could you tell me the things that you
like about smoking?
Response: It helps me stay focused when I'm working
example_title: What do you like 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:
<|startoftext|> Prompt: ...Question from bot...
Response: ...Response from user...
Example Prompt: paste two lines below and generate a reflection
<|startoftext|>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!