> distillation from larger models to smaller open-source models and smaller-closed source models
They don't limit it only to open-source models. And you can finetune 3.5 Turbo on OpenAI API.
They don't limit it only to open-source models. And you can finetune 3.5 Turbo on OpenAI API.
I'm confused why you are mentioning 3.5 here. The weights aren't public, so you aren't actually running any derivative of GPT-3.5
Or am I mistaken. Can you clarify?