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 11 months ago

MODERATORS

communick@academy.garden

Are LLMs at a practical limit for layer stacking? [D] (alien.top)

submitted 10 months ago by cstein123@alien.top to c/machinelearning@academy.garden

4 comments fedilink hide all child comments

Can LLMs stack more layers than the largest ones currently have, or is it bottlenecked? Is it because the gradients can’t propagate properly to the beginning of the network? Because inference would be to slow?

If anyone could provide a paper that talks about layer stacking scaling I would love to read it!

you are viewing a single comment's thread
view the rest of the comments

[–] currentscurrents@alien.top 1 points 10 months ago (1 children)

They definitely can go deeper - with skip connections and normalization you can propagate gradients through any depth of architecture.

Adding more layers isn't free though, it requires more parameters and thus more compute. There's an optimal depth-to-width ratio for a given parameter count.

[–] cstein123@alien.top 1 points 10 months ago (1 children)

Exactly the answer I was looking for, thank you!

[–] iantimmis@alien.top 1 points 10 months ago

It becomes very expensive compute-wise, but where we are actually running up to the edge is the scale of the data. They've discovered "scaling laws" (see chinchilla paper) that determines how big your model should be given the amount of data you have. We could go bigger but there's no reason to use a multi-trillion parameter model for example because it's just wasted capacity.