remove resiDual, as hyperconnections is the culmination for that line…

… of research
lucidrains · Feb 4, 2025 · 62237f8 · 62237f8
1 parent 66ab2c7
commit 62237f8
Show file tree

Hide file tree

Showing 2 changed files with 56 additions and 76 deletions.
diff --git a/README.md b/README.md
@@ -2015,16 +2015,6 @@ ids_out, num_out, is_number_mask = model.generate(start_ids, start_nums, 17)
 }
 ```
 
-```bibtex
-@article{Xie2023ResiDualTW,
-  title     = {ResiDual: Transformer with Dual Residual Connections},
-  author    = {Shufang Xie and Huishuai Zhang and Junliang Guo and Xu Tan and Jiang Bian and Hany Hassan Awadalla and Arul Menezes and Tao Qin and Rui Yan},
-  journal   = {ArXiv},
-  year      = {2023},
-  volume    = {abs/2304.14802}
-}
-```
-
 ```bibtex
 @inproceedings{Dehghani2023ScalingVT,
     title   = {Scaling Vision Transformers to 22 Billion Parameters},