Reconfigure HuggingFace Hub interface to use any repo

[caufieldjh]

I initially set up the HF Hub interface to only work with a pre-established set of models (those defined in models.yaml). This was built on the assumption that some models will work better with OntoGPT's extract methods than others. This assumption isn't wrong, but it's also not possible to test all of the available models out there. It would be convenient to have a pre-tested set of models defined, but still permit usage of any model the API can access (i.e., any HF Hub repo name). The CLI could look for a specific prefix like hf_hub: to indicate that it should use a manually specified model repo.