Will a LLM trained with FP4 have competitive performance in 2 years time?
Plus
13
Ṁ1381Jan 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
and3.00
Sort by:
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?
@NoaNabeshima Yes, you need to be better than everything else, but be trained in 4-bit (to some extent)
Related questions
Related questions
Will an LLM improve its own ability along some important metric well beyond the best trained LLMs before 2026?
58% chance
Will a LLM beat human experts on GPQA by Jan 1, 2025?
90% chance
Will a publicly-available LLM achieve gold on IMO before 2026?
37% chance
Will LLMs mostly overcome the Reversal Curse by the end of 2025?
66% chance
Will a home grown LLM developed by Chinese company be competitive by end of 2025?
73% chance
LLM Hallucination: Will an LLM score >90% on SimpleQA before 2026?
55% chance
Will a 15 billion parameter LLM match or outperform GPT4 in 2024?
24% chance
Will any LLM released in the next year double my coding productivity?
24% chance
At EOY 2024, who will have the best LLM?
Which company will have the best LLM by the end of 2024?