HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization Paper • 2503.04598 • Published Mar 6 • 18 • 8
HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization Paper • 2503.04598 • Published Mar 6 • 18 • 8
HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization Paper • 2503.04598 • Published Mar 6 • 18 • 8
Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models Paper • 2502.15499 • Published Feb 21 • 13 • 2