Q: Does your api integrate with GPT’s fine tuning model?
Does your integration work export to gpt’s fine tuning api format?
rushabhshroff
Sep 3, 2024A: Yes, it can but some modification is required in the response. For example Fine tuning model accepts
{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the capital of France?"}, {"role": "assistant", "content": "Paris, as if everyone doesn't know that already."}]}
Which means you need to modify the spreadsheet response to be contained within a object with an array of messages.
Ok thanks, how would I do that? I don't understand?
You need to create JSON objects to train a Large Language Model (LLM). In Google Sheets, you can use a formula to structure your data into JSON format. The formula will combine relevant data (e.g., user messages and assistant responses) from your sheet into a JSON object that can be used for fine-tuning an LLM.