From 3bc7d70e9c8605c95a01135fc5edffec3c1fa6bd Mon Sep 17 00:00:00 2001
From: Tikeng Notsawo Pascal Junior <pascalnotsawo@gmail.com>
Date: Thu, 9 Dec 2021 11:35:22 -0500
Subject: [PATCH] Fix : wrong link in the documentation (ConvBERT vs
 DistilBERT) (#14705)

---
 docs/source/model_summary.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/source/model_summary.rst b/docs/source/model_summary.rst
index 94572675b..106beb96a 100644
--- a/docs/source/model_summary.rst
+++ b/docs/source/model_summary.rst
@@ -360,7 +360,7 @@ ConvBERT
        <img alt="Doc" src="https://img.shields.io/badge/Model_documentation-convbert-blueviolet">
    </a>
 
-`ConvBERT: Improving BERT with Span-based Dynamic Convolution <https://arxiv.org/abs/1910.01108>`_, Zihang Jiang,
+`ConvBERT: Improving BERT with Span-based Dynamic Convolution <https://arxiv.org/abs/2008.02496>`_, Zihang Jiang,
 Weihao Yu, Daquan Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan.
 
 Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural