

So if the Chinese version is so efficient, and is open source, then couldn’t openAI and anthropic run the same on their huge hardware and get enormous capacity out of it?
So if the Chinese version is so efficient, and is open source, then couldn’t openAI and anthropic run the same on their huge hardware and get enormous capacity out of it?
It says right there in your screenshot that it’s the CABLE that can become damaged.
Like 90% of all the apple cables I’ve ever seen. But I guess that’s different.
Just a sentence, please kind sir, not a video?
Joke’s on them. As a homelab noob, I just run whatever the Docker containers provide. I will not dive into a nerd cave to adjust to the latest and greatest (fad).
Try using words?
I have to create a fucking account just to fucking read your article?! Kthxbye!
On average, a person contains slightly more than one skeleton.
On average, a person has slightly less than two legs.
Switch to Colemak and that XCV goodness is right where it needs to be.
Never had a nicer typing experience, thanks to DreymaR introducing me to DHm-angle-wide-mod. Colemak FTW!
🐑
Also, that text is barely English. Who wrote that?
This makes sense, but it would still allow a hundred times more people to use the model without running into limits, no?