←back to thread

I Self-Hosted Llama 3.2 with Coolify on My Home Server

(geek.sg)
221 points whitefables | 1 comments | 16 Oct 24 05:26 UTC | HN request time: 0.203s | source
Show context
taosx ◴[16 Oct 24 07:41 UTC] No.41856567[source]▶
For the people who self-host LLMs at home: what use cases do you have?

Personally, I have some notes and bookmarks that I'd like to scrape, then have an LLM summarize, generate hierarchical tags, and store in a database. For the notes part at least, I wouldn't want to give them to another provider; even for the bookmarks, I wouldn't be comfortable passing my reading profile to anyone.

replies(11): >>41856653 #>>41856701 #>>41856881 #>>41856970 #>>41856992 #>>41857395 #>>41858199 #>>41858353 #>>41861443 #>>41864562 #>>41890288 #
1. theodric ◴[16 Oct 24 22:37 UTC] No.41864562[source]▶
I've been enjoying fine-tuning various models with various data, for example 17 years of my own tweets, and then just cranking up the temperature and letting the model generate random crap that cracks me up. Is that practical? Is joy practical? I think there's a place for it.