add paper link

README.md

@@ -10,7 +10,7 @@ license: mit
 ---
 DCPythia-6.9B is a pretrained language model on the Pile with 300B tokens. With comparison of Pythia-6.9B, we validate the scaling performance of Dynamically
 Composable Multi-Head Attention(DCMHA), a parameter and computation efficient attention architecture that tackles the shortcomings of MHA and increases the expressive power of the model
-by dynamically composing attention heads. Please see downstrem evaluations and more details in the paper[(Improving Transformers with Dynamically Composable Multi-Head Attention)](). In addition, we open-source Jax training code on [(Github)](https://github.com/Caiyun-AI/DCFormer/).
+by dynamically composing attention heads. Please see downstrem evaluations and more details in the paper[(Improving Transformers with Dynamically Composable Multi-Head Attention)](https://arxiv.org/abs/2405.08553). In addition, we open-source Jax training code on [(Github)](https://github.com/Caiyun-AI/DCFormer/).
 
 We recommend <strong>compiled version</strong> of DCPythia with *torch.compile* for inference acceleration. Please refer to Generation section for compile implementation.