manifest
manifest copied to clipboard
HuggingFace Hub
It seems like HuggingFace is only supported for local models. It would be nice to support calling model on the Hub with the InferenceAPI. I think this is relatively straightforward to do, you just give the model name and the type of inference (text-generation or feature-extraction)
👍
I might be able to add this one if I find time
strongly agree!