S-LoRA: Serving Concurrent LoRA Adapters

Tricked by acronym confusion, I thought this was about LoRa (Long Range) <i>radio</i><p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;LoRa" rel="nofollow noreferrer">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;LoRa</a><p>Instead it&#x27;s about LoRA, note the capitalized last A, or Low-Rank Adaptation, a method for tuning LLMs.

Super cool, not sure if there’s already a popular project for this but I’ve seen so many asking for exactly this capability.<p>‘Conventional’ (if that means anything in a field 10 minutes old) wisdom is “fine tune to add knowledge, LoRA to adjust presentation” - could you comment on your experiences with this?

Looks kind of inactive.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;predibase&#x2F;lorax">https:&#x2F;&#x2F;github.com&#x2F;predibase&#x2F;lorax</a><p>Does a similar thing and seems more active.

Probably ignorant question: I know Loras are being used all the time, but where do you get them? All I see on huggingface is the whole models.