Please boost - Mvto!
Uncategorized
1
Posts
1
Posters
7
Views
-
Please boost - Mvto!
Help Native arts and artists survive. Like most artistic endeavors few Native artists are getting rich. Mass majority are just trying to survive and keep their cultures alive with dignity.
Sold #Beadwork = food, rent and other essential bills.
HELP Native art and artists stay not just alive but thrive! Get some Holiday gifts, show some handmade love to your partner or loved ones...
#Native #Indigenous #IndigenousMutualAid #MutualAid
>>---> https://cvkvlv.com/collections/national-native-american-heritage-month-1 -
undefined oblomov@sociale.network shared this topic on
Feed RSS
Gli ultimi otto messaggi ricevuti dalla Federazione
-
-
@mos_8502 LM Studio or oLlama and a nice open model
-
emptiness levels are holding at 100%
(100%) ■■■■■■■■■■
-
@mos_8502 Hank Green gave a good breakdown of the it.
-
@vwbusguy I have an old GPU, but 64GB of system RAM and 24 logical cores in my Xeon workstation?
-
@mos_8502 There's a lot of it depends, but most of the cost is AI is in training the models rather than the queries themselves. If you have a machine with a newish GPU and you download a model like granite or phi, the cost is your time and a nominal amount of electricity.
-
Like… what does it cost for a model to run for just one person, self hosted?
-
@mos_8502 Mainly get a capable model (like granite) locally on your box and call it with pytorch. I have a python script on my laptop for calling llm queries completely locally. Having a newish GPU will help.
