Merge pull request THUDM#246 from zRzRzRzRzRzRzR/main

严谨的Readme
limeng101192 · Dec 26, 2023 · 1920a97 · 1920a97
2 parents 54f28da + ae0db22
commit 1920a97
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 14 deletions.
diff --git a/README.md b/README.md
@@ -1,12 +1,9 @@
 # CogVLM & CogAgent
 
 📗 [中文版README](./README_zh.md)
-
-🔥🔥🔥 🆕 ```2023/12/15```: **CogAgent Officially Launched!** CogAgent is an image understanding model developed based on
-CogVLM. It features **visual-based GUI Agent capabilities** and **has further enhancements in image understanding**. It
-supports image input with a **resolution of 1120*1120**, and possesses multiple abilities including **multi-turn
-dialogue with images, GUI Agent, Grounding**, and more.
-
+🔥🔥🔥  🆕: ```2023/12/26```: We have released the [CogVLM-SFT-311K](dataset.md) dataset, 
+which contains over 150,000 pieces of data that we used for **CogVLM v1.0 only** training. 
+Welcome to follow and use.
 
 🌟 **Jump to detailed introduction: [Introduction to CogVLM](#introduction-to-cogvlm)，
 🆕 [Introduction to CogAgent](#introduction-to-cogagent)**
@@ -62,8 +59,10 @@ dialogue with images, GUI Agent, Grounding**, and more.
     - [Citation \& Acknowledgements](#citation--acknowledgements)
 
 ## Release
-- 🔥🔥🔥  **News**: ```2023/12/26```: We have released the [CogVLM-SFT-311K](dataset.md) dataset, which contains over 150,000 pieces of data that we used for training. Welcome to follow and use.
-- 🔥🔥 **News**: ```2023/12/18```: **New Web UI Launched!** We have launched a new web UI based on Streamlit, users can painlessly talk to CogVLM, CogAgent in our UI. Have a better user experience.
+- 🔥🔥🔥  **News**: ```2023/12/26```: We have released the [CogVLM-SFT-311K](dataset.md) dataset, 
+  which contains over 150,000 pieces of data that we used for **CogVLM v1.0 only** training. Welcome to follow and use.
+- 🔥🔥 **News**: ```2023/12/18```: **New Web UI Launched!** We have launched a new web UI based on Streamlit,
+  users can painlessly talk to CogVLM, CogAgent in our UI. Have a better user experience.
 - 🔥 **News**: ```2023/12/15```: **CogAgent Officially Launched!** CogAgent is an image understanding model developed
   based on CogVLM. It features **visual-based GUI Agent capabilities** and has further enhancements in image
   understanding. It supports image input with a resolution of 1120*1120, and possesses multiple abilities including

diff --git a/README_zh.md b/README_zh.md
@@ -1,10 +1,8 @@
 # CogVLM & CogAgent
 
 📗 [README in English](./README.md)
-
-🔥🔥🔥 🆕 ```2023/12/15```: CogAgent正式上线！CogAgent是基于CogVLM开发的图像理解模型。它具有基于视觉的GUI
-Agent功能，并在图像理解方面有进一步的增强。它支持1120*1120分辨率的图像输入，并具有包括与图像进行多轮对话、GUI
-Agent、Grounding等多种能力。
+- 🔥🔥🔥 🆕: ```2023/12/26```:我们公开了 [CogVLM-SFT-311K](dataset_zh.md) 数据集，
+它包含了超过15万条我们用于训练 **CogVLM v1.0(仅该模型)** 的数据。欢迎关注和使用。
 
 🌟 **跳转到详细介绍: [CogVLM介绍](#introduction-to-cogvlm)，
 🆕 [CogAgent的介绍](#introduction-to-cogagent)**
@@ -60,7 +58,7 @@ Agent、Grounding等多种能力。
     - [Citation \& Acknowledgements](#citation--acknowledgements)
 
 ## 发布
-- 🔥🔥🔥 **News**: ```2023/12/26```:我们公开了 [CogVLM-SFT-311K](dataset_zh.md) 数据集，它包含了超过15万条我们用于训练的数据。欢迎关注和使用。
+- 🔥🔥🔥 **News**: ```2023/12/26```:我们公开了 [CogVLM-SFT-311K](dataset_zh.md) 数据集，它包含了超过15万条我们用于训练 **CogVLM v1.0(仅该模型)** 的数据。欢迎关注和使用。
 - 🔥🔥 **News**: ```2023/12/18```: **新的Streamlit用户界面**已经上线！我们已经基于Streamlit推出了新的网页用户界面，用户可以在我们的界面上轻松与CogVLM，CogAgent交谈。带来更好的用户体验。
 - 🔥 **News**: ```2023/12/15```: **CogAgent 正式发布！** CogAgent是基于CogVLM开发的图像理解模型。它具有基于视觉的GUI
   Agent功能，并在图像理解方面进行了进一步的增强。它支持分辨率为1120*1120的图像输入，并具有包括与图像进行多轮对话、GUI

diff --git a/dataset_zh.md b/dataset_zh.md
@@ -68,4 +68,4 @@ CogVLM-SFT-311K 是我们在训练 **CogVLM v1.0** 最初版本时使用的主
 ## References
 This project utilizes data and concepts based on the following research papers:
 - Zhu, D., Chen, J., Shen, X., Li, X., & Elhoseiny, M. (2023). MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. arXiv preprint arXiv:2304.10592.
-- Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023). Visual Instruction Tuning. arXiv:2304.08485. 
+- Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023). Visual Instruction Tuning. arXiv:2304.08485.