←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: 0.353s | source
Show context
netdevnet ◴[16 Oct 24 08:11 UTC] No.41856729[source]▶
Am I right thinking that a self-hosted llama wouldn't have the kind restrictions ChatGPT has since it has no initial system prompt?
replies(4): >>41856734 #>>41856777 #>>41856779 #>>41856872 #
1. exe34 ◴[16 Oct 24 08:19 UTC] No.41856779[source]▶
It has a sanitised output. You might want to look for "abliterated" models, where the general performance might drop a bit but the guard-rails have been diminished.