Andrew Ng· @AndrewYNg · X·· 2026-08-24AI 评分54
AI 导读
Andrew Ng 转发 Percy Liang 的消息：Marin 535B-A23B 本周启动训练，计划在 11 台 GB200 NVL72 上用约 3 个月完成 18.75T tokens 的预训练与 midtraining，全程开源代码、数据、配方和实验结果。此前已通过 1.6B-A61M 到 27.7B-A1.2B 的 4 级 scaling ladder 调试并预测主训练表现。Ng 称 Marin 是捍卫 AI 开放的珍贵示范，开放发布曾一度是研究常态。
正文
In the fight to defend openness in AI, the Marin project is a precious demonstration of openness in model training, with open code, data, recipes, even experimental results. Releasing AI research openly used to be the norm; I'm grateful for @percyliang's open lab approach.
🚢 Marin 535B-A23B started training this week! As usual, the whole process is open. Voyage plan: pretraining (80%) + midtraining (20%) on 18.75T tokens on 11 x GB200 NVL72 for ~3 months (2.7e24 FLOPs). Post-training will follow. Before kicking off the run, we trained a 4-rung scaling ladder from 1.6B-A61M (48B tokens) to 27.7B-A1.2B (926B tokens) to debug issues, and to make a forecast of our hero run. This is by far our biggest run, so definitely expecting the unexpected.在 X 查看被引用的帖子
来源：Andrew Ng · x.com