←back to thread

Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model

(github.com)
343 points sillysaurusx | 1 comments | 05 Mar 23 04:28 UTC | HN request time: 0.29s | source
Show context
vanillax ◴[05 Mar 23 16:54 UTC] No.35031357[source]▶
How or what can someone do with this who isn't a ML expert? Is there some docker app that leverages this? To the average dev, is this useful to me? I know there's lots of "plug and play" style docker apps to get started with Stable Diffusion. I'm curious if I can do something fun with this.
replies(3): >>35031508 #>>35031541 #>>35031848 #
1. kkielhofner ◴[05 Mar 23 17:36 UTC] No.35031848[source]▶
You can shortcut a lot of the steps in these various guides by using the Pytorch container from Nvidia[0].

It shouldn't be too hard for someone (me?) to create a Dockerfile and Docker hub container FROM this image to get it up and running easily.

[0] - https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorc...