News for hackers. Stuff that matters.

A comment on Mistral Fine-Tune. Parent comment

Re:Mistral Fine-Tune by subroutine on Saturday May 25, 2024 @05:30AM (#40473825)
Function calling might be one reason. If your app has a lot of custom functions for interacting with tools, fine tuning may be preferred over using context tokens.
[ Parent | on HN ]
Re:Mistral Fine-Tune by AlexeyBrin on Saturday May 25, 2024 @07:19AM (#40474209)
Can you recommend a tutorial/document about fine tuning a small model for selecting the correct functions ? Would be great to have something local that can replace OpenAI functions/tools API.
[ Parent | on HN ]
Re:Mistral Fine-Tune by subroutine on Saturday May 25, 2024 @06:32PM (#40478317)
The linked GitHub article above describes syntax for fine tuning Mistral for function calling.

Here is an example of data prepared for fine tuning Llama for function calling...

https://huggingface.co/datasets/mzbac/function-calling-llama...

I'm unaware of any comprehensive guides - we're still in the wild west.

[ Parent | on HN ]