Re:Show HN: Fine-tune your own Llama 2 to replace GPT-3.5/4
by binarymax on Tuesday September 12, 2023 @02:53PM
(#37485972)
This looks awesome! Tangential question - do you find GPT function calling to work consistently and without error, or do you get errors when using it? By errors I mostly mean incorrect function signatures/types or missing values...but if you see other unpredictable behavior that would help too.
[ Parent
| on HN ]
Re:Show HN: Fine-tune your own Llama 2 to replace GPT-3.5/4
by Arctic_fly on Tuesday September 12, 2023 @03:07PM
(#37486241)
I haven't had much trouble with GPT 3.5 or 4 function calls returning in an undesirable format recently. I did get a few bad syntax responses when OpenAI first rolled it out, but not for the past few months.
Llama 2 can also pick the function call format up, given sufficient training data that contains function call responses, though you'll then have to parse the returned object out of the text-based response.
Re:Show HN: Fine-tune your own Llama 2 to replace GPT-3.5/4
by behnamoh on Tuesday September 12, 2023 @11:33PM
(#37491877)
Has anyone done such fine tuning on llama though? Afaik most projects like llama.cpp use grammars instead.
Re:Show HN: Fine-tune your own Llama 2 to replace GPT-3.5/4
by Arctic_fly on Wednesday September 13, 2023 @12:53AM
(#37492342)
Yep! The linked notebook includes an example of exactly that (fine-tuning a 7b model to match the syntax of GPT-4 function call responses): https://github.com/OpenPipe/OpenPipe/blob/main/examples/clas...