Sure! Youāll probably want to look at train-text-from-scratch in the llama.cpp project, it runs on pure CPU. The (admittedly little docs) should help, otherwise ChatGPT is a good help if you show it the code. NanoGPT is fine too.
For dataset, maybe you could train on French Wikipedia, or scrape from a French story site or fan fiction or whatever. Wikipedia is probably easiest, since they provide downloadable offline versions that are only a couple gigs.
A simple way would be to load the comments themselves, and then check for blocked users. But this would basically ddos the instance servers and would be extremely janky lol
or Iām being me and missing something obvious :/
The technology of compression a diffusion model would have to achieve to realistically (not too lossily) store āthe training dataā would be more valuable than the entirety of the machine learning field right now.
Young something has been in my eye for the past twelve hours and I want to scream
but it yummy
also expensive as fuck wtf the last time I had it it was like 12 bucks never again
greedy music labels strike again!
I choose to press. What did she do wrong?
my dumbass read
:3
yayy
I presume you have experience with these traps?
UwU
I neeeeeeed it
my meme now
I mean I agree with most of them but briāish?? Never!
This looks exactly like an image that would accompany an SCP article lol
Sure! Youāll probably want to look at train-text-from-scratch in the llama.cpp project, it runs on pure CPU. The (admittedly little docs) should help, otherwise ChatGPT is a good help if you show it the code. NanoGPT is fine too.
For dataset, maybe you could train on French Wikipedia, or scrape from a French story site or fan fiction or whatever. Wikipedia is probably easiest, since they provide downloadable offline versions that are only a couple gigs.
yes please
A simple way would be to load the comments themselves, and then check for blocked users. But this would basically ddos the instance servers and would be extremely janky lol
or Iām being me and missing something obvious :/
Thank you so much! Have a good break!
tech support?? thatās going a bit far I think
ok but if everyone would accept me when coming out I think it would be worth it..
kid called EU anticompetitive laws:
The technology of compression a diffusion model would have to achieve to realistically (not too lossily) store āthe training dataā would be more valuable than the entirety of the machine learning field right now.
They do not ācompressā images.