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

3 points by michaelnny 2y ago ↗ HN

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

[ 6.5 ms ] story [ 20.7 ms ] thread

K0IN 2y ago ↗

The link seems to be broken

michaelnny 2y ago ↗

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

david1542 2y ago ↗

link is broken

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...