On: Code Llama, a state-of-the-art large language model for coding

[liuliu]

34B should be able to run on 24GiB consumer graphics card, or 32GiB Mac (M1 / M2 chips) with quantization (5~6bit) (and 7B should be able to run on your smart toaster).

[epolanski → liuliu]

Are there cloud offerings to run those models on somebody's else computer?

Any "eli5" tutorial on how to do so, if so?

I want to give these models a run but I have no powerful GPU to run them on so don't know where to start.

[RossBencina → epolanski]

runpod, togethercomputer, replicate.

Matthew Berman has a tutorial on YT showing how to use TheBloke's docker containers on runpod. Sam Witteveen has done videos on together and replicate, they both offer cloud-hosted LLM inference as a service.

[kordlessagain → epolanski]

I started something here about this: https://news.ycombinator.com/item?id=37121384

[redox99 → epolanski]

On runpod there is a TheBloke template with everything set up for you. An A6000 is good enough to run 70b 4bit.