> For the complete documentation index, see [llms.txt](https://doraemonzzz.gitbook.io/transformer_evolution_paper/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doraemonzzz.gitbook.io/transformer_evolution_paper/normalize_and_residual.md).

# Normalize\_And\_Residual

- [ReZero is All You Need Fast Convergence at Large Depth](https://doraemonzzz.gitbook.io/transformer_evolution_paper/normalize_and_residual/001.md)
- [Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks](https://doraemonzzz.gitbook.io/transformer_evolution_paper/normalize_and_residual/002.md)
- [Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention](https://doraemonzzz.gitbook.io/transformer_evolution_paper/normalize_and_residual/003.md)
- [RealFormer Transformer Likes Residual Attention](https://doraemonzzz.gitbook.io/transformer_evolution_paper/normalize_and_residual/004.md)
- [On Layer Normalizations and Residual Connections in Transformers](https://doraemonzzz.gitbook.io/transformer_evolution_paper/normalize_and_residual/005.md)
- [Transformers without Tears: Improving the Normalization of Self-Attention](https://doraemonzzz.gitbook.io/transformer_evolution_paper/normalize_and_residual/006.md)
- [Query-Key Normalization for Transformers](https://doraemonzzz.gitbook.io/transformer_evolution_paper/normalize_and_residual/007.md)
- [Understanding the difficulty of training transformers](https://doraemonzzz.gitbook.io/transformer_evolution_paper/normalize_and_residual/008.md)