Hellfire103@lemmy.ca to linuxmemes@lemmy.worldEnglish · 5 months agoDistro Focuseslemmy.caexternal-linkmessage-square228fedilinkarrow-up1985arrow-down114
arrow-up1971arrow-down1external-linkDistro Focuseslemmy.caHellfire103@lemmy.ca to linuxmemes@lemmy.worldEnglish · 5 months agomessage-square228fedilink
minus-squareZachariah@lemmy.worldlinkfedilinkarrow-up7·edit-25 months agoWho doesn’t? I mean version 2.9.2 just came out in May.
minus-square1985MustangCobra@lemmy.calinkfedilinkEnglisharrow-up6·5 months agoi tried living in the terminal but i had no one to talk to
minus-squareZachariah@lemmy.worldlinkfedilinkarrow-up8·5 months agoWe’re in your terminal: https://github.com/LunaticHacker/lemmy-terminal-viewer
minus-square1985MustangCobra@lemmy.calinkfedilinkEnglisharrow-up4·5 months agosadly based on the latest issues submitted and my experience, the app no longer works: https://github.com/LunaticHacker/lemmy-terminal-viewer/issues/11
minus-squareLucy :3@feddit.orglinkfedilinkarrow-up1·5 months agoIf you have a decent GPU or CPU, you can just set up ollama with ollama-cuda/ollama-rocm and run llama3.1 or llama3.1-uncensored.
minus-square1985MustangCobra@lemmy.calinkfedilinkEnglisharrow-up2·5 months agoI have a ryzen 5 laptop. not really decent enough for that workload. and im not crazy about AI.
minus-squareLucy :3@feddit.orglinkfedilinkarrow-up1·5 months agoI bet even my Pi Zero W could run such a model* * with 1 character per hour or so
minus-square1985MustangCobra@lemmy.calinkfedilinkEnglisharrow-up2·5 months agointeresting, well it’s something to look into, but id like a place to communicate with like minded people.
Who doesn’t?
I mean version 2.9.2 just came out in May.
i tried living in the terminal but i had no one to talk to
We’re in your terminal: https://github.com/LunaticHacker/lemmy-terminal-viewer
sadly based on the latest issues submitted and my experience, the app no longer works: https://github.com/LunaticHacker/lemmy-terminal-viewer/issues/11
😍
If you have a decent GPU or CPU, you can just set up ollama with ollama-cuda/ollama-rocm and run llama3.1 or llama3.1-uncensored.
I have a ryzen 5 laptop. not really decent enough for that workload. and im not crazy about AI.
I bet even my Pi Zero W could run such a model*
* with 1 character per hour or so
interesting, well it’s something to look into, but id like a place to communicate with like minded people.