HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Apriel-H1: Towards Efficient Enterprise Reasoning Models(arxiv.org)

1 points·by guiriduro·7개월 전·1 comments
arxiv.org
Apriel-H1: Towards Efficient Enterprise Reasoning Models

https://arxiv.org/abs/2511.02651

1 comments

guiriduro·7개월 전
Apriel-H1-15b-Thinker-SFT uses incremental distillation from Apriel-Nemotron-15B-Thinker, selectively replacing less critical attention layers with linear Mamba blocks to reduce computational complexity while preserving reasoning quality.