You probably want 48gb of vram or more to run the good stuff. I recommend renting GPU time instead of using your own hardware, via AWS or other vendors - runpod.io is pretty good.
You probably want 48gb of vram or more to run the good stuff. I recommend renting GPU time instead of using your own hardware, via AWS or other vendors - runpod.io is pretty good.
Imo it’s worthwhile to just run the biggest model available and rent expensive GPU time. It still amounts to very little overall and you get much better results. Project dependent of course
Uncensored models are so much better, too. chatGPT is like one of those plastic children’s toy hammers vs real models are titanium hammers
I recently interviewed for a software job where they want you to work at least 12 hours per day.
During the first interview, I had asked about work-life balance, too, and the HR rep said, “well I’m not an engineer, so I’m not sure.” And then after my fourth interview, she goes, "just so you know, this will be a high intensity position. There is not much of a work/life balance.
I tried the demo this morning - tons of fun! I only played one match, but it played extremely well. Very StarCraft + warcraft 3.
This looks amazing 🤩