Will a LLM trained with FP4 have competitive performance in 2 years time?

1kṀ2955

resolved Mar 4

Resolved

ALL

"Currently, the technology for 4-bit training does not exists, but research looks promising and I expect the first high performance FP4 Large Language Model (LLM) with competitive predictive performance to be trained in 1-2 years time." (see: https://timdettmers.com/2023/01/16/which-gpu-for-deep-learning/)

Granted, the model must be open source for us to know, so the market will resolve based on publicly available information.

Get

1,000

to start trading!

🏅 Top traders

#	Name	Total profit
1		Ṁ158
2		Ṁ152
3		Ṁ90
4		Ṁ55
5		Ṁ13

People are also trading

Will a LLM trained with FP4 have frontier-level performance before 2028?

31% chance

6 months from now will I judge that LLMs had already peaked by Nov 2024?

16% chance

Will an LLM improve its own ability along some important metric well beyond the best trained LLMs before 2026?

50% chance

Will one of the major LLMs be capable of continual lifelong learning (learning from inference runs) by EOY 2025?

26% chance

Will a publicly-available LLM achieve gold on IMO before 2026?

34% chance

Will LLMs mostly overcome the Reversal Curse by the end of 2025?

44% chance

Will there be major breakthrough in LLM Continual Learning before 2026?

36% chance

Will China have the best LLM by the end of 2025?

11% chance

Will Apple release its own LLM on par with state of the art LLMs before 2026?

3% chance

Will a majority of Harvard undergrads train an LLM within 3 years as per Altman?

Sort by:

@typedfemale Hi! Would you mind resolving this market?

@Gabrielle @Bayesian we got a lesson about this in Discord, here

My executive summary:

There's some evidence that FP4 is 'around the corner' and may demonstrate some of these qualities

But it's not enough to qualify for the market's criteria of:

Open source
Publicly available information
As of 21 January 2025

If someone disagrees with the way I'm spinning the summary of the conversation, post here!

@Eliza it should resolve NO

@PoliticalEconomyPK Well, I agree, but do we need to wait for a panel of 3 moderators to weigh in? I tried to wrangle some with no luck and it's been some weeks by now.

According to the linked analysis from sof, this simply did not happen. It doesn't sound like an ambiguity or a judgement call, but just "did anyone refute this analysis" (no).

So, let's resolve it no as "the resolution is obvious" rather than "ambiguous".

@Manifold

@mods

@ManifoldAI

Any AI expert can chime in and resolve this market? According to a prompt on chatGPT that I made, this should resolve no

predictedNO

Exclusively in FP4? Or does partially in FP4 count. What if the model is on average 60% FP4 over the course of training?

I guess you covered this with "trained in 4-bit (to some extent)"

predictedNO

https://arxiv.org/pdf/2212.09720.pdf

predictedNO

@NoaNabeshima This is ab post-training precision adjustments

Competitive with what? SOTA with fp16?

predictedNO

This seems important @typedfemale
Will this resolve YES if scaling laws suggest a 4-bit model would be competitive if compute-matched to a SOTA 16-bit model?