Upload 2 files
Browse files- .gitattributes +1 -0
- README.md +62 -0
- demo.png +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
demo.png filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# BrainGPT1
|
| 2 |
+
|
| 3 |
+
<p align="center">
|
| 4 |
+
💻 <a href="https://github.com/1920993165/BrainGPT1" target="_blank">Github Repo</a>• 🐦 <a href="https://blog.csdn.net/a1920993165/article/details/128007435" target="_blank">blog</a>
|
| 5 |
+
</p>
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
**华东师范大学,计算机科学与技术学院,智能教育研究院**,[小怪兽会微笑](mailto:wtliu@stu.ecnu.edu.cn)
|
| 10 |
+
|
| 11 |
+
## 介绍
|
| 12 |
+
|
| 13 |
+
**BrainGPT1**是一个工具调用多轮对话模型,与GPT-4o不同的是,模型通过调用多个工具模型实现了多模态的多轮对话。因此,模型具备有工具灵活更新,定制化使用的特点。模型主要具有以下能力:
|
| 14 |
+
|
| 15 |
+
1. **通用问答**:默认使用讯飞星火大模型提供的免费API([spark lite](https://console.xfyun.cn/services/bm35)),也可以自行接入其他API或本地模型,项目中提供了接入本地ChatGLM3的API的demo。
|
| 16 |
+
|
| 17 |
+
2. **画图能力**:默认使用[stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)模型。
|
| 18 |
+
|
| 19 |
+
3. **图片问答**:默认使用[InternLM-XComposer](https://github.com/InternLM/InternLM-XComposer)模型。
|
| 20 |
+
|
| 21 |
+
4. **多媒体播放**:默认代码查询并返回[bilibili](https://www.bilibili.com/)的搜索结果。
|
| 22 |
+
|
| 23 |
+
5. **天气查询**:默认使用代码查询并返回API的结果。
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
**BrainGPT1**的基座模型采用了[ChatGLM3](https://github.com/THUDM/ChatGLM3),经过全量微调获得,调用工具的实现方式与ChatGLM3类似。
|
| 28 |
+
|
| 29 |
+
项目前端使用streamlit框架,主要基于[Streamlit Multimodal Chat Input](https://github.com/het-25/st-multimodal-chatinput/tree/main)和[streamlit-chat](https://github.com/AI-Yash/st-chat) 实现前端的多轮多模态对话效果。
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
尽管模型在训练的各个阶段都尽力确保数据的合规性和准确性,但由于缺乏实际用户下的训练数据,且模型受概率随机性因素影响,无法保证输出内容的准确。**本项目不承担开源模型和代码导致的数据安全、舆情风险或发生任何模型被误导、滥用、传播、不当利用而产生的风险和责任。**本项目遵循[BSD 3-Clause License](https://github.com/NExT-GPT/NExT-GPT/blob/main/LICENSE.txt)
|
| 34 |
+
|
| 35 |
+
。
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
## Demo
|
| 42 |
+
|
| 43 |
+
<p align="center">
|
| 44 |
+
<img src="./demo.png" width="650"/>
|
| 45 |
+
</p>
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
## Readme_EN
|
| 52 |
+
|
| 53 |
+
Previously, an incident occurred where my application for the llama3 model on Hugging Face was not approved. As a result, this document does not have an English introduction, and future applications for the model file will not be open to regions outside of mainland China.
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
|
demo.png
ADDED
|
Git LFS Details
|