Impressive level of openness on such a large run
Nearly half a year of silence. We spent it studying one problem: how far RL can scale. MiMo-V2.6 is in the middle of its RL run right now. Three things we scale...
AI 导读
小米团队称 MiMo-V2.6 目前正处于 RL 训练中途，探索 RL 的规模上限。其扩展了三个方向：算力（每步约 2B tokens，1568 prompts × 16 rollouts。
Thomas Wolf@Thom_Wolf54
AI 编辑部评分，满分 100小米团队称 MiMo-V2.6 目前正处于 RL 训练中途，探索 RL 的规模上限。其扩展了三个方向：算力（每步约 2B tokens，1568 prompts × 16 rollouts。
来源：Thomas Wolf· x.com