LATIDIA · Investigación

ZGCM-1: un modelo de base totalmente abierto y extremadamente eficiente para las matemáticas y la búsqueda agénica

arXiv:2609.13356v1 Tipo de anuncio: nuevo Resumen: En este trabajo, presentamos ZGCM-1, un modelo de cimentación densa 7B completamente abierto entrenado desde cero con datos extremos, sistema y eficiencia algorítmica. ZGCM-1 se basa en una c

La noticia

arXiv:2609.13356v1 Announce Type: new Abstract: In this work, we present ZGCM-1, a fully open 7B dense foundation model trained from scratch with extreme data, system, and algorithmic efficiency. ZGCM-1 is founded on a core premise: compact models cannot passively memorize the open web, but can overcome parametric capacity limits by coupling deliberate internal thinking with active external tool use. To support this paradigm across a 256K context, we develop an end-to-end, high-efficiency open training recipe: Architecture & System Co-design: interleaved gated sliding-window and full attention, and a stable FP8 Muon optimizer; Progressive Curriculum & MDP Mid-Training: context scaling across 16K, 64K, and 256K, and the reformulation of interaction traces into