FiveTech Support Forums

FiveWin / Harbour / xBase community
Board index latest AI news Less is More
Posts: 44158
Joined: Thu Oct 06, 2005 05:47 PM
Less is More
Posted: Sat Feb 15, 2025 01:20 PM
Researchers find you don’t need a ton of data to train LLMs for reasoning tasks

https://venturebeat.com/ai/researchers-find-you-dont-need-a-ton-of-data-to-train-llms-for-reasoning-tasks/
With merely 817 curated training samples, LIMO achieves 57.1% accuracy on AIME and 94.8% on MATH, improving from previous SFT-based models' 6.5% and 59.2% respectively, while only using 1% of the training data required by previous approaches.
regards, saludos

Antonio Linares
www.fivetechsoft.com

Continue the discussion