From 5008aa4c935e1f2ccc58c822bab7fe47bedaab52 Mon Sep 17 00:00:00 2001
From: Haoyu Lu <39251602+RERV@users.noreply.github.com>
Date: Fri, 15 Mar 2024 01:29:00 +0800
Subject: [PATCH] docs: update README.md (#31)

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 747dba9..fd67ac9 100644
--- a/README.md
+++ b/README.md
@@ -55,10 +55,10 @@
 
 
 <p align="center">
-  <a href="https://arxiv.org/abs/2403.05525"><b>Paper Link</b>👁️</a>
+  <a href="https://arxiv.org/abs/2403.05525"><b>Paper Link</b></a> |
+  <a href="https://huggingface.co/spaces/deepseek-ai/DeepSeek-VL-7B"><b>Demo</b></a>
 </p>
 
-
 ## 1. Introduction
 
 Introducing DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications. DeepSeek-VL possesses general multimodal understanding capabilities, capable of processing logical diagrams, web pages, formula recognition, scientific literature, natural images, and embodied intelligence in complex scenarios.