OpenAI/Codex: Can I create a fine-tuned model for Codex?

user_1802425 0
Viewed 310

I'd like to translate user requests into tickets in some sort of structured data format, e.g. JSON. For example:

  • User: I want to order two chairs and a desk with three drawers on the left side.
  • Output:
{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "left" }] },
        { "type": "chair", "qty": 2 }
    ]
}

It looks like GPT3 itself is not very-well suited for this task, because output is not in the form of natural language, however Codex might be? But I can't find in OpenAI docs how I can (if it's possible at all?) to create a custome/fine-tuned model for Codex?

codex openai
2 Answers

@xara Codex does not support a way to fine tune their model.

What you can do is prompt engineering.

Provide the model some demonstrations and try out whether Codex can perovide you with expected output.

user_21954400

It is currently in beta, but you can fine-tune the OpenAI codex model on your custom dataset for a charge to improve its performance. Please refer to the following link for details instruction: https://beta.openai.com/docs/guides/fine-tuning

user_39664800
Related