Fine tunning text-davinci-002

API
1

Hello,
I’m currently trying to build my own OCR using text-davinci-002 although it works well, I found it pretty instable sometimes the response is great sometimes it’s pretty bad (using the same input).
I was wondering if this is possible to finetune the model and give him more data to learn from ?
Maybe someone have another idea to get more stable answer without finetuning.

Thanks

2

Here’s what docs say about fine-tuning:

What models can be fine-tuned?

Fine-tuning is currently only available for the following base models: davinci, curie, babbage, and ada. These are the original models that do not have any instruction following training (like text-davinci-003 does for example). You are also able to continue fine-tuning a fine-tuned model to add additional data without having to start from scratch.