39
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 27 Sep 2023
39 points (91.5% liked)
Programming
17225 readers
117 users here now
Welcome to the main community in programming.dev! Feel free to post anything relating to programming here!
Cross posting is strongly encouraged in the instance. If you feel your post or another person's post makes sense in another community cross post into it.
Hope you enjoy the instance!
Rules
Rules
- Follow the programming.dev instance rules
- Keep content related to programming in some way
- If you're posting long videos try to add in some form of tldr for those who don't want to watch videos
Wormhole
Follow the wormhole through a path of communities !webdev@programming.dev
founded 1 year ago
MODERATORS
This looks really interesting!
Some recent studies have shown that (for the performance demonstrated) most models are nowhere near as compact as they could/should be. This means that we should expect an explosion in the capability of small models like this as new techniques find ways to improve our models.
Unfortunately, I couldn't find a recommendation for how much VRAM you need to run this model, though it does call out being able to run it locally, which is awesome!
I'll try it out after work and see if it can run on an old 8GB 2070. 😄
It will depend on the representation of the parameters. Most models support bfloat16, where each parameters is 16-bits (2 Bytes). For these models, every Billion parameters needs roughly 2 GB of VRAM.
It is possible to reduce the memory footprint by using 8 bits for each param, and some models support this, but they start to get very stupid.
That would mean 16GB are required to run this one
It's not clear to me either on exactly what hardware is required for the reference implementation, but there's a bunch of discussion about getting it to work with llama.cpp in the HN thread, so it might be possible soon (or maybe already is?) to run it on the CPU if you're willing to wait longer for it to process.
Let us know how it goes!