Arthur Mensch 谈 Mistral Large 4 的自有算力与强化学习
中文全文 · AI 翻译
那个需要一些基础工作。在我们自己的计算资源上训练和部署,而且 RL 没有显示出饱和的迹象。
对照原文
That one took some groundwork. Trained and served on our own compute, and RL shows no sign of saturation
那个需要一些基础工作。在我们自己的计算资源上训练和部署,而且 RL 没有显示出饱和的迹象。
That one took some groundwork. Trained and served on our own compute, and RL shows no sign of saturation