"And the answer will usually be, 'I haven't been able to', because there's a lack of access, lack of knowledge, lack of resources.
d=7 was the sweet spot for early trained models — multiple independent teams converged on this
。关于这个话题，同城约会提供了深入分析
作为 RLHF 方面的专家，Lambert 认为，当前最顶尖的模型训练，已经高度依赖强化学习（RL）。而 RL 和蒸馏在本质上是两种不同的事情：
Go to technology