#Can I create embeddings/finetune chatGPT3.5Turbo and use that with the chat api? How?

22 messages · Page 1 of 1 (latest)

amber ruin
#

I'm trying to utilize the chat api with in-house data and while I'm familiar with the process for fine-tuning davinci and the completions API I cannot find similar instruction for the chatGPT3.5Turbo and chat API? Any help is appreciated.

#

I've got the system prompt the way I want and it works great, but I can't include all of the data (thousands of records) in the system as it overloads the token limit.

wanton ruin
amber ruin
#

or is it the same, I just substitute turbo in for what I'm already doing with davinci?

lone mist
#

what exactly do you want to do?

#

embeddings have their own model (ada-002)

amber ruin
lone mist
#

this has been done and asked ad-nauseum

#

like, everyday there's someone doing the same

amber ruin
#

Can you point me to any resources? I’ve been successful with completions but my goo-fu must be failing me with the chat api.

lone mist
#

look in the openai community forums

amber ruin
#

Is that not this?

lone mist
#

langchain also has plugins for that

lone mist
amber ruin
#

Thanks I’ll check both of those out.

spark geode
#

hi, sorry im still new with finetune, i couldnt get it to work, i did a simple prompt and completion with jsonl and created finetune with success via davinci model, but when i use the model finetuned, it never give me the same completion as my prompt to completion, for example prompt: what is xyz? completion: xyz is a product abc brand. finetune prepared without any error as i followed the ending suffix for prompt and completion with ending \n\n. been figuring for 1week now. but @amber ruin i would love to hear if you found your solution for chat, it will be even better

wanton ruin
spark geode
#

ah okay

#

i will try, thank you

#

but how come basic q and a dont work