Re:Ollama v0.1.45
by jhbadger on Saturday June 15, 2024 @11:42PM
(#40694533)
I think you are arguing at cross-purposes. If you use HuggingFace to simply download models to run locally with ollama or llama.cpp, then you can say it is "local". But you can also use it as a service to run models (which is how they make money). Then they obviously aren't local.
[ Parent
| on HN ]
Re:Ollama v0.1.45
by Der_Einzige on Sunday June 16, 2024 @01:07AM
(#40694814)
Huggingface let's you run locally with huggingface exclusive code! They started this way and the managed/hosted solution came later.
You downvoters are the folks who jumped into this craze post ChatGPT.
Re:Ollama v0.1.45
by doctorpangloss on Sunday June 16, 2024 @09:28PM
(#40701530)
I have no idea where people got the idea that Hugging Face isn’t local. I mean they show you how to run everything locally, with all the quantization strategies you could want, with far fewer bugs.