User avatar
jade @karebu@social.karebu.gay
1y
lock in china
❤️1
2
1
1
1
User avatar
Two Hollywood Phonies @autumn@cafe.autumn.town
1y
@karebu self host it it's really funny
❤️1
2
0
1
1
User avatar
jade @karebu@social.karebu.gay
1y
@autumn not sure i have good enough hardware for it to not take 5 minutes for a response
1
0
0
0
User avatar
Two Hollywood Phonies @autumn@cafe.autumn.town
1y
@karebu i'm using my 6700XT for it and it's performing like any other 14b model. the difference is that it will display the thought process as regular text so for an actual response you need to wait a bit longer
1
0
0
0
User avatar
jade @karebu@social.karebu.gay
1y
@autumn ive never been able to get any of these ai things to use my amd gpu
1
0
1
0
User avatar
Two Hollywood Phonies @autumn@cafe.autumn.town
1y
@karebu if you're hosting ollama in docker and your amd gpu isn't officially supported (anything below 6800 i think?) then you pass an environment based on which GPU you've got (for me it's HSA_OVERRIDE_GFX_VERSION=10.3.0, you can find them here)
2
0
0
0
User avatar
jade @karebu@social.karebu.gay
1y
@autumn i wasnt even using docker i installed all 5000 python packages directly onto my system
❤️1
3
0
1
1
User avatar
jade @karebu@social.karebu.gay
1y
@autumn when i did stable diffusion i was able to get it to work once but i deleted everything after and it started failing when i tried to set it up again
1
0
0
0
User avatar
Two Hollywood Phonies @autumn@cafe.autumn.town
1y
@karebu yeah stable diffusion has not been stable for me either it sucks
0
0
1
0