Paulonemillionand3

joined 10 months ago
sorted by: new top controversial old
llama2 70B from HF vs code-llama 34B in c/localllama@poweruser.forum
[–] Paulonemillionand3@alien.top 1 points 9 months ago

worked great for me

Guys, I have a crazy idea. in c/localllama@poweruser.forum
[–] Paulonemillionand3@alien.top 1 points 9 months ago

fuck that noise

Interest so run a local LLaMA with RTX 3060 12G in c/localllama@poweruser.forum
Multi GPU vs Single GPU with same VRAM in c/localllama@poweruser.forum
[–] Paulonemillionand3@alien.top 1 points 10 months ago

power and heat would be more then double the trouble then with a single card.

What is the best 7B model for reading comprehension and instruction following at the moment? in c/localllama@poweruser.forum
So what's the story on distributing or redistributing characters? in c/localllama@poweruser.forum
[–] Paulonemillionand3@alien.top 1 points 10 months ago

You will be f'd over harder then you could possibly imagine if you use a celeb with a decent lawyer. A similar case was just in the news, and even when they stopped using the clone the case continued anyway.

Good luck! Sign your assets over to friends!

I'm looking for a Step-by-step fine tuning example in c/localllama@poweruser.forum
[–] Paulonemillionand3@alien.top 1 points 10 months ago

llama-recipies