update arxiv url

README.md

@@ -7,7 +7,7 @@ tags:
 - muddformer
 license: mit
 ---
-In comparison with Pythia-1.4B, MUDDPythia-1.4B is a pretrained language model on the Pile with 300B tokens, which uses a simple yet effective method to address the limitations of residual connections and enhance cross-layer information flow in Transformers. Please see downstrem evaluations and more details in the paper[(MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections)](https://arxiv.org). In addition, we open-source Jax training code on [(Github)](https://github.com/Caiyun-AI/MUDDFormer/).
+In comparison with Pythia-1.4B, MUDDPythia-1.4B is a pretrained language model on the Pile with 300B tokens, which uses a simple yet effective method to address the limitations of residual connections and enhance cross-layer information flow in Transformers. Please see downstrem evaluations and more details in the paper[(MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections)](https://arxiv.org/abs/2502.12170). In addition, we open-source Jax training code on [(Github)](https://github.com/Caiyun-AI/MUDDFormer/).
 
 We recommend <strong>compiled version</strong> of MUDDPythia with *torch.compile* for inference acceleration. Please refer to Generation section for compile implementation.