top of page

Fine Tuning ChatGPT

  • Writer: Chris Hack
    Chris Hack
  • May 10, 2023
  • 1 min read

Did you know it's possible to 'fine tune' ChatGPT by pre-supplying it with model prompts and ideal responses? You need to do this via the paid for API and the details are necessarily a little technical but in principle this saves you providing examples with prompts to ultimately lower your use of ChatGPT tokens and hence the cost to you.


Technical details from OpenAI themselves:

https://platform.openai.com/docs/guides/fine-tuning

 
 
 

Recent Posts

See All
Whisper

Another use of AI is speech-to-text conversion. Recorded audio can be turned into text. It is possible to embed this functionality in...

 
 
 
ChatGPT 3.5 vs ChatGPT 4

Did you know that the free version of ChatGPT uses something called the ChatGPT-3.5 engine but that an updated, more powerful version is...

 
 
 
Temperature in ChatGPT

"The temperature parameter in ChatGPT completions is a crucial aspect that influences the model's output diversity and creativity....

 
 
 

Comments


©2022 by Christopher Hack. Proudly created with Wix.com

bottom of page