flâneur

[2607.16051] Loop the Loopies!

arxiv.org · 6,020 words · saved by 1 readers

Abstract:We present the Loopie series, consisting of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active parameters and a 6B-parameter model with 0.6B active parameters. Looped Transformers have long faced a challenge: given an N times increase in pre-training compute, increasing the parameter count by a factor of N usually outperforms looping a model N times. Loopie addresses this challenge. Extensive ablation studies, including comparisons with a vanilla 30B-A3B model, show that Loopie substantially outperforms vanilla Transformer baselines trained with the same compute budget. With a novel post-training method, Loopie develops strong reasoning abilities and achieves frontier-level reasoning performance.

Loop the Loopies! Zitian Gao Yilong Chen Yihao Xiao Xinyu Yang Ran Tao Joey Zhou Bryan Dai IQuest Research See the full author contributions here. Models: Loopie-20B-A2B…

saved by

related reading