BLEU scores according to different layer-wise pairs.
收藏NIAID Data Ecosystem2026-05-01 收录
数据链接：
官方服务：
资源简介：
No pair denotes a four-layer vanilla Transformer model without layer-wise and matrix-wise pairs. Layer-wise parameter-shared model with pairs from {(L1, L3), (L2, L4)} shows the best accuracy with half the size of the four-layer vanilla Transformer model.
创建时间：
2023-07-06
相关数据集
暂无相关数据集
