כתבה
arXiv cs.CL ·
Rufus-Air: תזונה פתוחה ל-LLM לאחר הכשרה
Rufus-Air: An Open LLM Post-Training Recipe
Rufus-Air היא תזונה פתוחה ל-LLM לאחר הכשרה, המורכבת משמונה שלבים ומתועדת באופן רפודוקילי. השלבים כוללים SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, ו-RLHF.
תקציר מקורי באנגליתarXiv:2609.29421v2 Announce Type: replace Abstract: Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and stagewise results needed to reproduce the recipe. Stages progress from basic to advanced capabilities and from hard, verifiable rewards to softer judge-based signals. Training builds on open-source components and public data, much of it used as released, without new human annotation or an in-house distillation teacher. Our main findings are that (i) diverse, high-quality SFT establishes a strong capability floor; (ii) difficu
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית