Finetuning Code-davinci

[i.sravya577]

I have been working on code-davinci with some cool results. I am little curious to fine-tune code-davinci with my code corpus. Is there a way to fine-tune code-davinci model?

[PaulBellow]

@i.sravya577

fine-tune code-davinci model?

There’s been a lot of interest, but not many answers from what I’ve seen. I believe the answer, currently, is no.

Fine Tuning Codex Model

Can I fine-tune a Codex Model? I’m trying to use davicni-codex as the base model for fine tuning job, but I get this error: “Error: Invalid base model: davinci_codex (model must be one of ada, babbage, curie, davinci) (HTTP status code: 400)” I’m ultimately trying to create a model that will write code for a robot, so I would also appreciate any help on somehow increasing Codex’s knowledge of this Github repo: GitHub - FIRST-Tech-Challenge/FtcRobotController as well as its forks, thanks. Thank…

Fine-tuning a codex model?

Is it possible to fine-tune either of the codex models? I’d love to play with some block-based coding datasets. The stock davinci model seems to know a bit about the structure/internals of blockly, but doesn’t seem to have many samples of blocks and what they do in various contexts. I could try a really long prompt with them, but have had such good outcomes with fine-tuning I would love to try that as well.

Can I create a fine-tuned model for OpenAI API Codex models?

This last one might be worth your looking into…

How to fine tune fine tune GitHub Copilot?

The Codex model that’s powering the Copilot product is not open sourced. However, there are a few models similar to Codex available on the Hugging Face Hub such as Incoder or CodeGen:

Welcome to the forum!