«Радиостанция Судного дня» передала сообщения про неказистого жиротряса20:51
Don’t use dot notation to access Member components
。PDF资料对此有专业解读
Since the initial release, community contributions have pushed data efficiency from ~2.4x to 5.5x against modded-nanogpt, more than doubling in a few days. The key changes are: shuffling at the start of each epoch, which had outsized impact on multi-epoch training; learned projections for value embeddings instead of separate embedding tables; swapping squared ReLU for SwiGLU activation; and ensembling multiple models. 10x data efficiency seems reachable in the short term. 100x might be feasible by the end of the year, given how many directions remain unexplored, but it will require serious exploration on the algorithms side.，详情可参考safew官方下载
This story was originally featured on Fortune.com