ScrawnyStork

joined 1 year ago

I'm inclined to fine tune/make a Lora for Llama (2? I'm not sure how well it's supported yet), you definitely won't want to train from scratch. The big thing seems to be formating the dataset properly, although I haven't actually done any of this myself yet. this blog seems to have a few good articles about it that you might be interested in reading.

[–] ScrawnyStork@sh.itjust.works 42 points 1 year ago* (last edited 1 year ago) (5 children)

Facebook has the most csam of any website, but I hardly ever see the same fear mongering from the media. Odd.

[–] ScrawnyStork@sh.itjust.works 10 points 1 year ago (1 children)

Watched this earlier today. It's not the densest video ever, but watching Billy's story change is very amusing. I wonder if he has actually deluded himself into believing his bullshit.

[–] ScrawnyStork@sh.itjust.works 23 points 1 year ago (6 children)

I really appreciate the information, it's very interesting to me. Given that you have a fairly specific price in mind for a server, what kind of hardware are you thinking of?