* Support model-based (/engineless) completions in openai cli (#31)

* Engineless completions in the SDK

* Cosmetic improvements to fine tuning CLI

* Remove done TODO

* Raise error if neither engine nor model provided

* Undocument the `timeout` parameter on completions, because it doesn't do anything and causes user confusion.

* Move things around

* Update message

* Some day we should care about versions

* Minor version bump