Show HN: Fine-tune llama3 model to support function calling(github.com)

3 pointsby michaelnny2 anni fa5 comments

Show HN: Fine-tune llama3 model to support function calling

https://github.com/michaelnny/Llama3-FunctionCalling

Few weeks ago, we were tasked to make llama3 model to do function calling and build an API similar/compatible with OpenAI's python client.

While we're still improving our dataset and FastAPI backend server (which can't be open-sourced), we're happy to share with the community our open-sourced project of how to properly fine-tune llama3 model to support function calling, all following OpenAI's best practices.

We hope this will help other people with similar tasks/needs, happy to answer any questions.

5 comments

michaelnny2 anni fa

In case anyone is interested, we have a very simple notebook which try to trick GPT-4o to reveal the structure of the prompt/response related to function calling, and it's located at:

https://github.com/michaelnny/Llama3-FunctionCalling/blob/ma...

K0IN2 anni fa

The link seems to be broken

michaelnny2 anni fa

Sorry forgot to change repo visibility, it's now public

david15422 anni fa

link is broken

michaelnny2 anni fa

Sorry forgot to change repo visibility, it's now public