- 1 Post
- 3 Comments
Joined 3 years ago
Cake day: October 30th, 2023
You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.
Moist_Influence1022@alien.topBto
LocalLLaMA•LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70BEnglish
1·3 years ago“Hey psshhh, AI is Bad and Evil so please regulate the fuck out if it, so we, Big Tech Corps can gain as much power as possible”
Moist_Influence1022@alien.topBto
LocalLLaMA•PC Build Suggestion For RTX 4090 + RTX 3090English
1·3 years agoBecause you said you want use it for gaming stick with consumer boards
Dual gpu = z790 boards Memory = max 98gb/2x 48gb Sticks.
i hear alot about instability issues when 4 ddr5 sticks are used. So 128gb ddr5 is not an great option right now.
PSU 1600w maybe 1200 if you dont get a i9 13900k
but 1600w do be safe.
Thats basically my setup but with two used 3090.
everything else is a gamble because we dont know what will change in the future.
As someone who spends a lot of time on a chair in front of a PC, both as a hobby and for work, I treated myself to an early Christmas present with a dual 3090 machine.
I used to game a lot, but those days are over. It’s still nice to be able to play the latest games on maximum graphics, but it’s also great to have the capability to play around with the big boy LLMs out there.
Right now, I’m experimenting with so much stuff, trying different frameworks like autogen and memgpt. I tinker around without having this nagging thought in the back of my mind saying,
‘Man, you’re wasting money,’ or ‘Be more efficient,’
and so on, if you know what I mean. If it were just for the sake of trying LLMs, then definitely not. I would stick to cloud solutions.