Mystery of the undeleletable fine-tuned model

[_j]

This post details the requirements to delete a fine-tune model, and a script to help:

Unable to delete my fine-tuned model

I figured out why some configurations could delete and others couldn’t in a brainwave that was “duh, obvious given the error message”: Send the API key, along with matching project AND organization, in the delete call. This Python SDK script will use the model name you hard-code dump out your environment variables set in the openai client. Then uses the model endpoint to make sure the model exists, with info. Then deletes only if you type 999 Then checks the model endpoint again. The environ…

You of course put your actual ft: model name in the script near the top instead of the bare "gpt-3.5-turbo-0125" model name. The existing name is there for safety - you see it not deleting OpenAI’s own model.