this post was submitted on 28 Nov 2023
1 points (100.0% liked)
Machine Learning
1 readers
1 users here now
Community Rules:
- Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
- Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
- Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
- Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Do You Have the Slightest Idea How Little That Narrows It Down?
That is exactly the reason, I'm literally looking at my options and from the comments, it definitely isn't looking good 😭
Let's say I want to work on Noon (https://huggingface.co/Naseej/noon-7b), how much would I actually need?
Not trying to be rude, but you’re also like saying you want to participate in a car race and you don’t have a fast car kind of a prerequisite unfortunately.
You could look at things that offload your model to disk but they’re going to be slow as hell.
Paste your model name in this HF space, https://huggingface.co/spaces/Vokturz/can-it-run-llm
https://imgur.com/a/Ednemii (the result)
It seems you need less than 32 GiBs vram
And thanks to you, it now works. I knew exactly what to do and what I needed to get it to work. Thanks, man!