From 5324b3706fbce50c14296916a8cff9e888df17f2 Mon Sep 17 00:00:00 2001
From: ouyanglinke <ouyanglinke@pjlab.org.cn>
Date: Fri, 28 Jun 2024 18:11:02 +0800
Subject: [PATCH] modify readme

---
 README-zh_CN.md | 2 +-
 README.md       | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/README-zh_CN.md b/README-zh_CN.md
index e3a6966..c679074 100644
--- a/README-zh_CN.md
+++ b/README-zh_CN.md
@@ -82,7 +82,7 @@ PDF内容提取框架如下图所示
 <span id="layout-anchor"></span>
 ### 布局检测
 
-我们与现有的开源Layout检测模型做了对比，包括[DocXchain](https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/Applications/DocXChain)、[Surya](https://github.com/VikParuchuri/surya)、[360LayoutAnalysis](https://github.com/360AILAB-NLP/360LayoutAnalysis)的两个模型，而LayoutLMv3-SFT指的是我们在[LayoutLMv3](https://github.com/microsoft/unilm/blob/master/layoutlmv3)的基础上进一步做了SFT训练后的模型。论文验证集由402张Arxiv论文页面构成，教材验证集由587张不同来源的教材页面构成。
+我们与现有的开源Layout检测模型做了对比，包括[DocXchain](https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/Applications/DocXChain)、[Surya](https://github.com/VikParuchuri/surya)、[360LayoutAnalysis](https://github.com/360AILAB-NLP/360LayoutAnalysis)的两个模型，而LayoutLMv3-SFT指的是我们在[LayoutLMv3](https://github.com/microsoft/unilm/blob/master/layoutlmv3)的基础上进一步做了SFT训练后的模型。论文验证集由402张论文页面构成，教材验证集由587张不同来源的教材页面构成。
 
 <table>
     <tr>
diff --git a/README.md b/README.md
index d622510..9090c43 100644
--- a/README.md
+++ b/README.md
@@ -147,7 +147,7 @@ We have compared our model with existing open-source layout detection models, in
 <span id="mfd-anchor"></span>
 ### Formula Detection
 
-We have compared our model with the open-source formula detection model [Pix2Text-MFD](https://github.com/breezedeus/pix2text). Additionally, the YoloV8-SFT is the weight obtained after we performed SFT training on the basis of the YoloV8 model. The paper's validation set is composed of 255 Arxiv paper pages, and the multi-source validation set consists of 789 pages from various sources, including textbooks and books.
+We have compared our model with the open-source formula detection model [Pix2Text-MFD](https://github.com/breezedeus/pix2text). Additionally, the YoloV8-SFT is the weight obtained after we performed SFT training on the basis of the YoloV8 model. The paper's validation set is composed of 255 academic paper pages, and the multi-source validation set consists of 789 pages from various sources, including textbooks and books.
 
 <table>
     <tr>