←back to thread

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators

(machinelearning.apple.com)
171 points pizza | 4 comments | 06 Apr 25 08:53 UTC | HN request time: 0.001s | source
1. _0ffh ◴[06 Apr 25 17:31 UTC] No.43603178[source]▶
I suspect an April fools joke.

In general, compression using PRNGs is not a thing. There might be a special exception for this case, but I somewhat doubt it. =)

replies(2): >>43603315 #>>43604559 #
2. RainyDayTmrw ◴[06 Apr 25 17:48 UTC] No.43603315[source]▶
The version on Arxiv dates to October 2024, which likely rules this out.
replies(1): >>43603462 #
3. _0ffh ◴[06 Apr 25 18:02 UTC] No.43603462[source]▶
I submit that there is no "compression into PRNG seeds" going on here. This is just a quantisation method that happens to leverage PRNs, which might have some specific advantages and disadvantages. What I am sure it does not do, is what it's title seems to claim, if taken literally. I suspect they're having a good laugh, getting away with what they must know is borderline trolling. I'm impressed!
4. threeseed ◴[06 Apr 25 20:10 UTC] No.43604559[source]▶
I suspect that you are literally the only person on this planet who would find this to be funny enough for Apple to waste the time of a dozen AI Researchers, Meta, arXiv and Apple Legal who vet everything.