Comment on Llama-2, GPT-4, or Claude-2; Which Artificial Intelligence Language Model Is The Best?
j4k3@lemmy.world 1 year ago
Llama-2 because you can run it on your own hardware. For the big GPU on a rented instance: Falcon 70b. OpenAI and Google can have turns playing proprietary asshat jack in the box.
procrastinator@lemmy.world 1 year ago
How expensive would it be to run on a rented server?
Stubborn9867@lemmy.jnks.xyz 1 year ago
For the bigger ones you could do it under $.50 / hr. I run llama 2 13b-8 bit on my 3090 no problem, which can be rented for $.20/hr.
vast.ai/#pricing
Since of the lower pricing I’ve seen.
PeepinGoodArgs@reddthat.com 1 year ago
How do you get into doing this? Like, are you a data scientist? AI Engineer? Hobbyist?
I want to be able to use tools like this, and I want a formal education in it, but I’m not sure what path to take. (I don’t necessarily want a career in it…my current career is pretty fantastic, but I think understanding tools like this is extremely important in understanding the modern world. That’s my main motivation.)
Stubborn9867@lemmy.jnks.xyz 1 year ago
I’m a software engineer by trade, but a hobbyist when it comes to LLMs.
github.com/AUTOMATIC1111
This is a good place to start. Loads of YouTubers with setup videos. I like this guy youtube.com/@Aitrepreneur he covers LLM and Image generation too.
Hugging face is a good place to get the actual LLM.