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

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

Plus

13

Ṁ1381

Jan 21

22%

chance

1D

1W

1M

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.

This question is managed and resolved by Manifold.

Get

1,000

and

3.00

Sort by:

predicts NO

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)"

predicts NO

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

predicts NO

@NoaNabeshima This is ab post-training precision adjustments

Competitive with what? SOTA with fp16?

predicts NO

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?

predicts NO

(but there isn't a trained SOTA 4-bit model)

@NoaNabeshima Yes, you need to be better than everything else, but be trained in 4-bit (to some extent)

@typedfemale Finetuned w 4 bit would trigger Yes? 80% of parameters in 4 bit would trigger Yes?

Related questions

Will a home grown LLM developed by Chinese company be competitive by end of 2025?

-11% 1d51% chance

At EOY 2024, who will have the best LLM?

Will a LLM beat human experts on GPQA by Jan 1, 2025?

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

Will any LLM released in the next year double my coding productivity?

Will any LLM outrank GPT-4 by 150 Elo in LMSYS chatbot arena before 2025?

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

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

Will a 15 billion parameter LLM match or outperform GPT4 in 2024?

Which company will have the best LLM by the end of 2024?

Related questions

Will a home grown LLM developed by Chinese company be competitive by end of 2025?

Will any LLM outrank GPT-4 by 150 Elo in LMSYS chatbot arena before 2025?

At EOY 2024, who will have the best LLM?

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

Will a LLM beat human experts on GPQA by Jan 1, 2025?

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

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

Will a 15 billion parameter LLM match or outperform GPT4 in 2024?

Will any LLM released in the next year double my coding productivity?

Which company will have the best LLM by the end of 2024?

© Manifold Markets, Inc.•Terms + Mana-only Terms•Privacy•Rules