Follow
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation. (arXiv:2302.10322v1 [cs.LG]) http://arxiv.org/abs/2302.10322
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation. (arXiv:2302.10322v1 [cs.LG]) http://arxiv.org/abs/2302.10322