From f4baff03b3e6240014fbc86ae4fac6c55053cab2 Mon Sep 17 00:00:00 2001 From: duzx16 Date: Thu, 18 May 2023 15:07:14 +0800 Subject: [PATCH] Update README --- .gitignore | 3 ++- README.md | 4 ++-- README_en.md | 4 ++-- UPDATE.md | 13 ++++++++++++- 4 files changed, 18 insertions(+), 6 deletions(-) diff --git a/.gitignore b/.gitignore index c3dd476..da568ec 100644 --- a/.gitignore +++ b/.gitignore @@ -130,4 +130,5 @@ dmypy.json .pyre/ # Mac system file -model/ \ No newline at end of file +model/ +.idea \ No newline at end of file diff --git a/README.md b/README.md index 88699d6..6edf46f 100644 --- a/README.md +++ b/README.md @@ -19,11 +19,11 @@ ChatGLM-6B 使用了和 ChatGPT 相似的技术，针对中文问答和对话进 *Read this in [English](README_en.md).* ## 更新信息 -**[2023/05/17]** 发布 [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B/)，一个支持图像理解的多模态对话语言模型。 +**[2023/05/17]** 发布 [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B)，一个支持图像理解的多模态对话语言模型。 ![](resources/visualglm.png) -可以通过本仓库中的 [cli_demo_vision.py](cli_demo_vision.py) 和 [web_demo_vision.py](web_demo_vision.py) 来运行命令行和网页 Demo。注意 VisualGLM-6B 需要额外安装 [SwissArmyTransformer](https://github.com/THUDM/SwissArmyTransformer/) 和 torchvision。 +可以通过本仓库中的 [cli_demo_vision.py](cli_demo_vision.py) 和 [web_demo_vision.py](web_demo_vision.py) 来运行命令行和网页 Demo。注意 VisualGLM-6B 需要额外安装 [SwissArmyTransformer](https://github.com/THUDM/SwissArmyTransformer/) 和 torchvision。更多信息参见 [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B)。 **[2023/05/15]** 更新 v1.1 版本 checkpoint，训练数据增加英文指令微调数据以平衡中英文数据比例，解决英文回答中夹杂中文词语的现象。 diff --git a/README_en.md b/README_en.md index 17e1819..3a23f46 100644 --- a/README_en.md +++ b/README_en.md @@ -18,11 +18,11 @@ In order to facilitate downstream developers to customize the model for their ow Try the [online demo](https://huggingface.co/spaces/ysharma/ChatGLM-6b_Gradio_Streaming) on Huggingface Spaces. ## Update -**[2023/05/17]** Release [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B/), a multimodal conversational language model supporting image understanding. +**[2023/05/17]** Release [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B), a multimodal conversational language model supporting image understanding. ![](resources/visualglm.png) -You can run the command line and web demo through [cli_demo_vision.py](cli_demo_vision.py) and [web_demo_vision.py](web_demo_vision.py) in the repository. Note that VisualGLM-6B requires additional installation of [SwissArmyTransformer](https://github.com/THUDM/SwissArmyTransformer/) and torchvision. +You can run the command line and web demo through [cli_demo_vision.py](cli_demo_vision.py) and [web_demo_vision.py](web_demo_vision.py) in the repository. Note that VisualGLM-6B requires additional installation of [SwissArmyTransformer](https://github.com/THUDM/SwissArmyTransformer/) and torchvision. For more information, please refer to [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B). **[2023/05/15]** Update the checkpoint of v1.1 version, add English instruction data for training to balance the proportion of Chinese and English data, which solves the phenomenon of Chinese words mixed in English answers . diff --git a/UPDATE.md b/UPDATE.md index 3182580..3bb2a80 100644 --- a/UPDATE.md +++ b/UPDATE.md @@ -1,4 +1,9 @@ ## 更新信息 +**[2023/05/17]** 发布 [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B)，一个支持图像理解的多模态对话语言模型。 + +![](resources/visualglm.png) + +可以通过本仓库中的 [cli_demo_vision.py](cli_demo_vision.py) 和 [web_demo_vision.py](web_demo_vision.py) 来运行命令行和网页 Demo。注意 VisualGLM-6B 需要额外安装 [SwissArmyTransformer](https://github.com/THUDM/SwissArmyTransformer/) 和 torchvision。更多信息参见 [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B)。 **[2023/05/15]** 更新 v1.1 版本 checkpoint，训练数据增加英文数据以平衡中英文数据比例，解决英文回答中夹杂中文词语的现象。 @@ -12,7 +17,7 @@ * 问题：Describe the function of a computer motherboard - v1.0: ![](resources/english-q2-old.png) - - v1.1: + - v1.1: ![](resources/english-q2-new.png) * 问题：Develop a plan to reduce electricity usage in a home. - v1.0: @@ -38,6 +43,12 @@ ## Update +**[2023/05/17]** Release [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B), a multimodal conversational language model supporting image understanding. + +![](resources/visualglm.png) + +You can run the command line and web demo through [cli_demo_vision.py](cli_demo_vision.py) and [web_demo_vision.py](web_demo_vision.py) in the repository. Note that VisualGLM-6B requires additional installation of [SwissArmyTransformer](https://github.com/THUDM/SwissArmyTransformer/) and torchvision. For more information, please refer to [VisualGLM-6B](https://github.com/THUDM/VisualGLM-6B). + **[2023/05/15]** Update the checkpoint of v1.1 version, add English instruction data for training to balance the proportion of Chinese and English data, which solves the phenomenon of Chinese words mixed in English answers .
The following is a comparison of English questions before and after the update