Upload 6 files

.flake8

@@ -0,0 +1,21 @@
+[flake8]
+ignore =
+  # E203 whitespace before ':'
+  E203
+  D203,
+  # line too long
+  E501
+per-file-ignores =
+  # imported but unused
+  # __init__.py: F401
+  test_*.py: F401
+exclude =
+  .git,
+  __pycache__,
+  docs/source/conf.py,
+  old,
+  build,
+  dist,
+  .venv
+  pad*.py
+max-complexity = 25

.gitattributes

@@ -1,5 +1,35 @@
-*.h linguist-detectable=false
-*.cpp linguist-detectable=false
-*.tex linguist-detectable=false
-*.cs linguist-detectable=false
-*.tps linguist-detectable=false
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,152 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-pip-wheel-metadata/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-
-# Translations
-*.mo
-*.pot
-github
-.github
-TEMP
-TRASH
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-.python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-.vscode
-.idea
-
-history
-ssr_conf
-config_private.py
-gpt_log
-private.md
-private_upload
-other_llms
-cradle*
-debug*
-private*
-crazy_functions/test_project/pdf_and_word
-crazy_functions/test_samples
-request_llm/jittorllms
-multi-language
-request_llm/moss
-media

README.md

@@ -1,346 +1,12 @@
 ---
-title: ChatImprovement
-emoji: 😻
-colorFrom: blue
+title: chatglm2 6b int4
+emoji: 🌖
+colorFrom: purple
 colorTo: blue
 sdk: gradio
-sdk_version: 3.32.0
+sdk_version: 3.35.2
 app_file: app.py
-pinned: false
+pinned: true
 ---
 
-# ChatGPT 学术优化
-> **Note**
->
-> 2023.5.27 对Gradio依赖进行了调整，Fork并解决了官方Gradio的若干Bugs。请及时**更新代码**并重新更新pip依赖。安装依赖时，请严格选择`requirements.txt`中**指定的版本**： 
-> 
-> `pip install -r requirements.txt`
->
-
-# <img src="docs/logo.png" width="40" > GPT 学术优化 (GPT Academic)
-
-**如果喜欢这个项目，请给它一个Star；如果你发明了更好用的快捷键或函数插件，欢迎发pull requests**
-
-If you like this project, please give it a Star. If you've come up with more useful academic shortcuts or functional plugins, feel free to open an issue or pull request. We also have a README in [English|](docs/README_EN.md)[日本語|](docs/README_JP.md)[한국어|](https://github.com/mldljyh/ko_gpt_academic)[Русский|](docs/README_RS.md)[Français](docs/README_FR.md) translated by this project itself.
-To translate this project to arbitary language with GPT, read and run [`multi_language.py`](multi_language.py) (experimental).
-
-> **Note**
->
-> 1.请注意只有**红颜色**标识的函数插件（按钮）才支持读取文件，部分插件位于插件区的**下拉菜单**中。另外我们以**最高优先级**欢迎和处理任何新插件的PR！
->
-> 2.本项目中每个文件的功能都在自译解[`self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/chatgpt-academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E6%8A%A5%E5%91%8A)详细说明。随着版本的迭代，您也可以随时自行点击相关函数插件，调用GPT重新生成项目的自我解析报告。常见问题汇总在[`wiki`](https://github.com/binary-husky/gpt_academic/wiki/%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98)当中。[安装方法](#installation)。
-> 
-> 3.本项目兼容并鼓励尝试国产大语言模型chatglm和RWKV, 盘古等等。支持多个api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,api2d-key3"`。需要临时更换`API_KEY`时，在输入区输入临时的`API_KEY`然后回车键提交后即可生效。
-
-
- 
-
-<div align="center">
-
-功能 | 描述
---- | ---
-一键润色 | 支持一键润色、一键查找论文语法错误
-一键中英互译 | 一键中英互译
-一键代码解释 | 显示代码、解释代码、生成代码、给代码加注释
-[自定义快捷键](https://www.bilibili.com/video/BV14s4y1E7jN) | 支持自定义快捷键
-模块化设计 | 支持自定义强大的[函数插件](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions)，插件支持[热更新](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
-[自我程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] [一键读懂](https://github.com/binary-husky/gpt_academic/wiki/chatgpt-academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E6%8A%A5%E5%91%8A)本项目的源代码
-[程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] 一键可以剖析其他Python/C/C++/Java/Lua/...项目树
-读论文、[翻译](https://www.bilibili.com/video/BV1KT411x7Wn)论文 | [函数插件] 一键解读latex/pdf论文全文并生成摘要
-Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [函数插件] 一键翻译或润色latex论文
-批量注释生成 | [函数插件] 一键批量生成函数注释
-Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [函数插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)了吗？
-chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
-[PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [函数插件] PDF论文提取题目&摘要+翻译全文（多线程）
-[Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [函数插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
-[谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [函数插件] 给定任意谷歌学术搜索页面URL，让gpt帮你[写relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)
-互联网信息聚合+GPT | [函数插件] 一键[让GPT先从互联网获取信息](https://www.bilibili.com/video/BV1om4y127ck)，再回答问题，让信息永不过时
-⭐Arxiv论文精细翻译 | [函数插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，迄今为止最好的论文翻译工具⭐
-公式/图片/表格显示 | 可以同时显示公式的[tex形式和渲染形式](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png)，支持公式、代码高亮
-多线程函数插件支持 | 支持多线调用chatgpt，一键处理[海量文本](https://www.bilibili.com/video/BV1FT411H7c5/)或程序
-启动暗色gradio[主题](https://github.com/binary-husky/gpt_academic/issues/173) | 在浏览器url后面添加```/?__theme=dark```可以切换dark主题
-[多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持 | 同时被GPT3.5、GPT4、[清华ChatGLM](https://github.com/THUDM/ChatGLM-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)同时伺候的感觉一定会很不错吧？
-更多LLM模型接入，支持[huggingface部署](https://huggingface.co/spaces/qingxu98/gpt-academic) | 加入Newbing接口(新必应)，引入清华[Jittorllms](https://github.com/Jittor/JittorLLMs)支持[LLaMA](https://github.com/facebookresearch/llama)，[RWKV](https://github.com/BlinkDL/ChatRWKV)和[盘古α](https://openi.org.cn/pangu/)
-更多新功能展示(图像生成等) …… | 见本文档结尾处 ……
-
-</div>
-
-
-- 新界面（修改`config.py`中的LAYOUT选项即可实现“左右布局”和“上下布局”的切换）
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/230361456-61078362-a966-4eb5-b49e-3c62ef18b860.gif" width="700" >
-</div>
-
-
-- 所有按钮都通过读取functional.py动态生成，可随意加自定义功能，解放粘贴板
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
-</div>
-
-- 润色/纠错
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
-</div>
-
-- 如果输出包含公式，会同时以tex形式和渲染形式显示，方便复制和阅读
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
-</div>
-
-- 懒得看项目代码？整个工程直接给chatgpt炫嘴里
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
-</div>
-
-- 多种大语言模型混合调用（ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4）
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
-</div>
-
----
-# Installation
-## 安装-方法1：直接运行 (Windows, Linux or MacOS) 
-
-1. 下载项目
-```sh
-git clone https://github.com/binary-husky/gpt_academic.git
-cd gpt_academic
-```
-
-2. 配置API_KEY
-
-在`config.py`中，配置API KEY等设置，[点击查看特殊网络环境设置方法](https://github.com/binary-husky/gpt_academic/issues/1) 。
-
-(P.S. 程序运行时会优先检查是否存在名为`config_private.py`的私密配置文件，并用其中的配置覆盖`config.py`的同名配置。因此，如果您能理解我们的配置读取逻辑，我们强烈建议您在`config.py`旁边创建一个名为`config_private.py`的新配置文件，并把`config.py`中的配置转移（复制）到`config_private.py`中。`config_private.py`不受git管控，可以让您的隐私信息更加安全。P.S.项目同样支持通过`环境变量`配置大多数选项，环境变量的书写格式参考`docker-compose`文件。读取优先级: `环境变量` > `config_private.py` > `config.py`)
-
-
-3. 安装依赖
-```sh
-# （选择I: 如熟悉python）（python版本3.9以上，越新越好），备注：使用官方pip源或者阿里pip源,临时换源方法：python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
-python -m pip install -r requirements.txt
-
-# （选择II: 如不熟悉python）使用anaconda，步骤也是类似的 (https://www.bilibili.com/video/BV1rc411W7Dr)：
-conda create -n gptac_venv python=3.11    # 创建anaconda环境
-conda activate gptac_venv                 # 激活anaconda环境
-python -m pip install -r requirements.txt # 这个步骤和pip安装一样的步骤
-```
-
-
-<details><summary>如果需要支持清华ChatGLM/复旦MOSS作为后端，请点击展开此处</summary>
-<p>
-
-【可选步骤】如果需要支持清华ChatGLM/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
-```sh
-# 【可选步骤I】支持清华ChatGLM。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
-python -m pip install -r request_llm/requirements_chatglm.txt  
-
-# 【可选步骤II】支持复旦MOSS
-python -m pip install -r request_llm/requirements_moss.txt
-git clone https://github.com/OpenLMLab/MOSS.git request_llm/moss  # 注意执行此行代码时，必须处于项目根路径
-
-# 【可选步骤III】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型，目前支持的全部模型如下(jittorllms系列目前仅支持docker方案)：
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
-```
-
-</p>
-</details>
-
-
-
-4. 运行
-```sh
-python main.py
-```
-
-## 安装-方法2：使用Docker
-
-1. 仅ChatGPT（推荐大多数人选择，等价于docker-compose方案1）
-
-``` sh
-git clone https://github.com/binary-husky/gpt_academic.git  # 下载项目
-cd gpt_academic                                 # 进入路径
-nano config.py                                      # 用任意文本编辑器编辑config.py, 配置 “Proxy”， “API_KEY” 以及 “WEB_PORT” (例如50923) 等
-docker build -t gpt-academic .                      # 安装
-
-#（最后一步-选择1）在Linux环境下，用`--net=host`更方便快捷
-docker run --rm -it --net=host gpt-academic
-#（最后一步-选择2）在macOS/windows环境下，只能用-p选项将容器上的端口(例如50923)暴露给主机上的端口
-docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic
-```
-P.S. 如果需要依赖Latex的插件功能，请见Wiki。另外，您也可以直接使用docker-compose获取Latex功能（修改docker-compose.yml，保留方案4并删除其他方案）。
-
-2. ChatGPT + ChatGLM + MOSS（需要熟悉Docker）
-
-``` sh
-# 修改docker-compose.yml，保留方案2并删除其他方案。修改docker-compose.yml中方案2的配置，参考其中注释即可
-docker-compose up
-```
-
-3. ChatGPT + LLAMA + 盘古 + RWKV（需要熟悉Docker）
-``` sh
-# 修改docker-compose.yml，保留方案3并删除其他方案。修改docker-compose.yml中方案3的配置，参考其中注释即可
-docker-compose up
-```
-
-
-## 安装-方法3：其他部署姿势
-1. 一键运行脚本。
-完全不熟悉python环境的Windows用户可以下载[Release](https://github.com/binary-husky/gpt_academic/releases)中发布的一键运行脚本安装无本地模型的版本。
-脚本的贡献来源是[oobabooga](https://github.com/oobabooga/one-click-installers)。
-
-2. 使用docker-compose运行。
-请阅读docker-compose.yml后，按照其中的提示操作即可
-
-3. 如何使用反代URL
-按照`config.py`中的说明配置API_URL_REDIRECT即可。
-
-4. 微软云AzureAPI
-按照`config.py`中的说明配置即可（AZURE_ENDPOINT等四个配置）
-
-5. 远程云服务器部署（需要云服务器知识与经验）。
-请访问[部署wiki-1](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
-
-6. 使用WSL2（Windows Subsystem for Linux 子系统）。
-请访问[部署wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
-
-7. 如何在二级网址（如`http://localhost/subpath`）下运行。
-请访问[FastAPI运行说明](docs/WithFastapi.md)
-
----
-# Advanced Usage
-## 自定义新的便捷按钮 / 自定义函数插件
-
-1. 自定义新的便捷按钮（学术快捷键）
-任意文本编辑器打开`core_functional.py`，添加条目如下，然后重启程序即可。（如果按钮已经添加成功并可见，那么前缀、后缀都支持热修改，无需重启程序即可生效。）
-例如
-```
-"超级英译中": {
-    # 前缀，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等
-    "Prefix": "请翻译把下面一段内容成中文，然后用一个markdown表格逐一解释文中出现的专有名词：\n\n", 
-    
-    # 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来。
-    "Suffix": "",
-},
-```
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
-</div>
-
-2. 自定义函数插件
-
-编写强大的函数插件来执行任何你想得到的和想不到的任务。
-本项目的插件编写、调试难度很低，只要您具备一定的python基础知识，就可以仿照我们提供的模板实现自己的插件功能。
-详情请参考[函数插件指南](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)。
-
----
-# Latest Update
-## 新功能动态
-
-1. 对话保存功能。在函数插件区调用 `保存当前的对话` 即可将当前对话保存为可读+可复原的html文件，
-另外在函数插件区（下拉菜单）调用 `载入对话历史存档` ，即可还原之前的会话。
-Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史html存档缓存。
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
-</div>
-
-2. ⭐Latex/Arxiv论文翻译功能⭐
-<div align="center">
-<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
-<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
-</div>
-
-3. 生成报告。大部分插件都会在执行结束后，生成工作报告
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/227503770-fe29ce2c-53fd-47b0-b0ff-93805f0c2ff4.png" height="250" >
-<img src="https://user-images.githubusercontent.com/96192199/227504617-7a497bb3-0a2a-4b50-9a8a-95ae60ea7afd.png" height="250" >
-</div>
-
-4. 模块化功能设计，简单的接口却能支持强大的功能
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
-<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
-</div>
-
-5. 译解其他开源项目
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
-<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
-</div>
-
-6. 装饰[live2d](https://github.com/fghrsh/live2d_demo)的小功能（默认关闭，需要修改`config.py`）
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
-</div>
-
-7. 新增MOSS大语言模型支持
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/236639178-92836f37-13af-4fdd-984d-b4450fe30336.png" width="500" >
-</div>
-
-8. OpenAI图像生成
-<div align="center">
-<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
-</div>
-
-9. OpenAI音频解析与总结
-<div align="center">
-<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
-</div>
-
-10. Latex全文校对纠错
-<div align="center">
-<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
-<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
-</div>
-
-
-
-## 版本:
-- version 3.5(Todo): 使用自然语言调用本项目的所有函数插件（高优先级）
-- version 3.4: +arxiv论文翻译、latex论文批改功能
-- version 3.3: +互联网信息综合功能
-- version 3.2: 函数插件支持更多参数接口 (保存对话功能, 解读任意语言代码+同时询问任意的LLM组合)
-- version 3.1: 支持同时问询多个gpt模型！支持api2d，支持多个apikey负载均衡
-- version 3.0: 对chatglm和其他小型llm的支持
-- version 2.6: 重构了插件结构，提高了交互性，加入更多插件
-- version 2.5: 自更新，解决总结大工程源代码时文本过长、token溢出的问题
-- version 2.4: (1)新增PDF全文翻译功能; (2)新增输入区切换位置的功能; (3)新增垂直布局选项; (4)多线程函数插件优化。
-- version 2.3: 增强多线程交互性
-- version 2.2: 函数插件支持热重载
-- version 2.1: 可折叠式布局
-- version 2.0: 引入模块化函数插件
-- version 1.0: 基础功能
-
-gpt_academic开发者QQ群-2：610599535
-
-- 已知问题
-    - 某些浏览器翻译插件干扰此软件前端的运行
-    - 官方Gradio目前有很多兼容性Bug，请务必使用`requirement.txt`安装Gradio
-
-## 参考与学习
-
-```
-代码中参考了很多其他优秀项目中的设计，顺序不分先后：
-
-# 清华ChatGLM-6B:
-https://github.com/THUDM/ChatGLM-6B
-
-# 清华JittorLLMs:
-https://github.com/Jittor/JittorLLMs
-
-# ChatPaper:
-https://github.com/kaixindelele/ChatPaper
-
-# Edge-GPT:
-https://github.com/acheong08/EdgeGPT
-
-# ChuanhuChatGPT:
-https://github.com/GaiZhenbiao/ChuanhuChatGPT
-
-# Oobabooga one-click installer:
-https://github.com/oobabooga/one-click-installers
-
-# More：
-https://github.com/gradio-app/gradio
-https://github.com/fghrsh/live2d_demo
-```
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,215 +1,386 @@
-import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
-
-def main():
-    import subprocess, sys
-    subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'gradio-stable-fork'])
-    import gradio as gr
-    if gr.__version__ not in ['3.28.3','3.32.3']: assert False, "请用 pip install -r requirements.txt 安装依赖"
-    from request_llm.bridge_all import predict
-    from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
-    # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
-    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS = \
-        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS')
-
-    # 如果WEB_PORT是-1, 则随机选取WEB端口
-    PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
-    if not AUTHENTICATION: AUTHENTICATION = None
-
-    from check_proxy import get_current_version
-    initial_prompt = "Serve me as a writing and programming assistant."
-    title_html = f'<h1 align=\"center\">ChatGPT 学术优化 {get_current_version()}<a href="https://huggingface.co/fb700/chatglm-fitness-RLHF">（模型by帛凡Ai）</a></h1>'
-    description =  """代码开源和更新[地址🚀](https://github.com/binary-husky/chatgpt_academic)，感谢热情的[开发者们❤️](https://github.com/binary-husky/chatgpt_academic/graphs/contributors)"""
-
-    # 问询记录, python 版本建议3.9+（越新越好）
-    import logging
-    os.makedirs("gpt_log", exist_ok=True)
-    try:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO, encoding="utf-8")
-    except:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO)
-    print("所有问询记录将自动保存在本地目录./gpt_log/chat_secrets.log, 请注意自我隐私保护哦！")
-
-    # 一些普通功能模块
-    from core_functional import get_core_functions
-    functional = get_core_functions()
-
-    # 高级函数插件
-    from crazy_functional import get_crazy_functions
-    crazy_fns = get_crazy_functions()
-
-    # 处理markdown文本格式的转变
-    gr.Chatbot.postprocess = format_io
-
-    # 做一些外观色彩上的调整
-    from theme import adjust_theme, advanced_css
-    set_theme = adjust_theme()
-
-    # 代理与自动更新
-    from check_proxy import check_proxy, auto_update, warm_up_modules
-    proxy_info = check_proxy(proxies)
-
-    gr_L1 = lambda: gr.Row().style()
-    gr_L2 = lambda scale: gr.Column(scale=scale)
-    if LAYOUT == "TOP-DOWN":
-        gr_L1 = lambda: DummyWith()
-        gr_L2 = lambda scale: gr.Row()
-        CHATBOT_HEIGHT /= 2
-
-    cancel_handles = []
-    with gr.Blocks(title="ChatGPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
-        gr.HTML(title_html)
-        gr.HTML('''<center>本应用基于chatglm6b【帛凡 AI】的微调模型进行部署，模型中文总结能力优于GPT3.5，欢迎体验<a href="https://huggingface.co/fb700/chatglm-fitness-RLHF">下载地址</a></center>''')
-        cookies = gr.State({'api_key': API_KEY, 'llm_model': LLM_MODEL})
-        with gr_L1():
-            with gr_L2(scale=2):
-                chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}")
-                chatbot.style(height=CHATBOT_HEIGHT)
-                history = gr.State([])
-            with gr_L2(scale=1):
-                with gr.Accordion("输入区", open=True) as area_input_primary:
-                    with gr.Row():
-                        txt = gr.Textbox(show_label=False, lines=2, placeholder="输入问题或API密钥，输入多个密钥时，用英文逗号间隔。支持OpenAI密钥和API2D密钥共存。").style(container=False)
-                    with gr.Row():
-                        submitBtn = gr.Button("提交", variant="primary")
-                    with gr.Row():
-                        resetBtn = gr.Button("重置", variant="secondary"); resetBtn.style(size="sm")
-                        stopBtn = gr.Button("停止", variant="secondary"); stopBtn.style(size="sm")
-                        clearBtn = gr.Button("清除", variant="secondary", visible=False); clearBtn.style(size="sm")
-                    with gr.Row():
-                        status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。当前模型: {LLM_MODEL} \n {proxy_info}")
-                with gr.Accordion("基础功能区", open=True) as area_basic_fn:
-                    with gr.Row():
-                        for k in functional:
-                            if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
-                            variant = functional[k]["Color"] if "Color" in functional[k] else "secondary"
-                            functional[k]["Button"] = gr.Button(k, variant=variant)
-                with gr.Accordion("函数插件区", open=True) as area_crazy_fn:
-                    with gr.Row():
-                        gr.Markdown("注意：以下“红颜色”标识的函数插件需从输入区读取路径作为参数.")
-                    with gr.Row():
-                        for k in crazy_fns:
-                            if not crazy_fns[k].get("AsButton", True): continue
-                            variant = crazy_fns[k]["Color"] if "Color" in crazy_fns[k] else "secondary"
-                            crazy_fns[k]["Button"] = gr.Button(k, variant=variant)
-                            crazy_fns[k]["Button"].style(size="sm")
-                    with gr.Row():
-                        with gr.Accordion("更多函数插件", open=True):
-                            dropdown_fn_list = [k for k in crazy_fns.keys() if not crazy_fns[k].get("AsButton", True)]
-                            with gr.Row():
-                                dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="").style(container=False)
-                            with gr.Row():
-                                plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False, 
-                                                                 placeholder="这里是特殊函数插件的高级参数输入区").style(container=False)
-                            with gr.Row():
-                                switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary")
-                    with gr.Row():
-                        with gr.Accordion("点击展开“文件上传区”。上传本地文件可供红色函数插件调用。", open=False) as area_file_up:
-                            file_upload = gr.Files(label="任何文件, 但推荐上传压缩文件(zip, tar)", file_count="multiple")
-                with gr.Accordion("更换模型 & SysPrompt & 交互界面布局", open=(LAYOUT == "TOP-DOWN")):
-                    system_prompt = gr.Textbox(show_label=True, placeholder=f"System Prompt", label="System prompt", value=initial_prompt)
-                    top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
-                    temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
-                    max_length_sl = gr.Slider(minimum=256, maximum=40960, value=5120, step=1, interactive=True, label="Local LLM MaxLength",)
-                    checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "底部输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区")
-                    md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
-
-                    gr.Markdown(description)
-                with gr.Accordion("备选输入区", open=True, visible=False) as area_input_secondary:
-                    with gr.Row():
-                        txt2 = gr.Textbox(show_label=False, placeholder="Input question here.", label="输入区2").style(container=False)
-                    with gr.Row():
-                        submitBtn2 = gr.Button("提交", variant="primary")
-                    with gr.Row():
-                        resetBtn2 = gr.Button("重置", variant="secondary"); resetBtn2.style(size="sm")
-                        stopBtn2 = gr.Button("停止", variant="secondary"); stopBtn2.style(size="sm")
-                        clearBtn2 = gr.Button("清除", variant="secondary", visible=False); clearBtn2.style(size="sm")
-        # 功能区显示开关与功能区的互动
-        def fn_area_visibility(a):
-            ret = {}
-            ret.update({area_basic_fn: gr.update(visible=("基础功能区" in a))})
-            ret.update({area_crazy_fn: gr.update(visible=("函数插件区" in a))})
-            ret.update({area_input_primary: gr.update(visible=("底部输入区" not in a))})
-            ret.update({area_input_secondary: gr.update(visible=("底部输入区" in a))})
-            ret.update({clearBtn: gr.update(visible=("输入清除键" in a))})
-            ret.update({clearBtn2: gr.update(visible=("输入清除键" in a))})
-            ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))})
-            if "底部输入区" in a: ret.update({txt: gr.update(value="")})
-            return ret
-        checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2, plugin_advanced_arg] )
-        # 整理反复出现的控件句柄组合
-        input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
-        output_combo = [cookies, chatbot, history, status]
-        predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=input_combo, outputs=output_combo)
-        # 提交按钮、重置按钮
-        cancel_handles.append(txt.submit(**predict_args))
-        cancel_handles.append(txt2.submit(**predict_args))
-        cancel_handles.append(submitBtn.click(**predict_args))
-        cancel_handles.append(submitBtn2.click(**predict_args))
-        resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
-        resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
-        clearBtn.click(lambda: ("",""), None, [txt, txt2])
-        clearBtn2.click(lambda: ("",""), None, [txt, txt2])
-        # 基础功能区的回调函数注册
-        for k in functional:
-            if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
-            click_handle = functional[k]["Button"].click(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True), gr.State(k)], outputs=output_combo)
-            cancel_handles.append(click_handle)
-        # 文件上传区，接收文件后与chatbot的互动
-        file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes], [chatbot, txt, txt2])
-        # 函数插件-固定按钮区
-        for k in crazy_fns:
-            if not crazy_fns[k].get("AsButton", True): continue
-            click_handle = crazy_fns[k]["Button"].click(ArgsGeneralWrapper(crazy_fns[k]["Function"]), [*input_combo, gr.State(PORT)], output_combo)
-            click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
-            cancel_handles.append(click_handle)
-        # 函数插件-下拉菜单与随变按钮的互动
-        def on_dropdown_changed(k):
-            variant = crazy_fns[k]["Color"] if "Color" in crazy_fns[k] else "secondary"
-            ret = {switchy_bt: gr.update(value=k, variant=variant)}
-            if crazy_fns[k].get("AdvancedArgs", False): # 是否唤起高级插件参数区
-                ret.update({plugin_advanced_arg: gr.update(visible=True,  label=f"插件[{k}]的高级参数说明：" + crazy_fns[k].get("ArgsReminder", [f"没有提供高级参数功能说明"]))})
+"""Credit to https://github.com/THUDM/ChatGLM2-6B/blob/main/web_demo.py while mistakes are mine."""
+# pylint: disable=broad-exception-caught, redefined-outer-name, missing-function-docstring, missing-module-docstring, too-many-arguments, line-too-long, invalid-name, redefined-builtin, redefined-argument-from-local
+# import gradio as gr
+
+# model_name = "models/THUDM/chatglm2-6b-int4"
+# gr.load(model_name).lauch()
+
+# %%writefile demo-4bit.py
+
+import os
+import time
+from textwrap import dedent
+
+import gradio as gr
+import mdtex2html
+import torch
+from loguru import logger
+from transformers import AutoModel, AutoTokenizer
+
+# fix timezone in Linux
+os.environ["TZ"] = "Asia/Shanghai"
+try:
+    time.tzset()  # type: ignore # pylint: disable=no-member
+except Exception:
+    # Windows
+    logger.warning("Windows, cant run time.tzset()")
+
+# model_name = "THUDM/chatglm2-6b"  # 7x?G
+model_name = "THUDM/chatglm2-6b-int4"  # 3.9G
+
+RETRY_FLAG = False
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+# model = AutoModel.from_pretrained(model_name, trust_remote_code=True).cuda()
+
+# 4/8 bit
+# model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).quantize(4).cuda()
+
+has_cuda = torch.cuda.is_available()
+# has_cuda = False  # force cpu
+
+if has_cuda:
+    if model_name.endswith("int4"):
+        model = AutoModel.from_pretrained(model_name, trust_remote_code=True).cuda()
+    else:
+        model = (
+            AutoModel.from_pretrained(model_name, trust_remote_code=True).cuda().half()
+        )
+else:
+    model = AutoModel.from_pretrained(
+        model_name, trust_remote_code=True
+    ).float()  #  .half().float(), .float() required for CPU
+
+model = model.eval()
+
+_ = """Override Chatbot.postprocess"""
+
+
+def postprocess(self, y):
+    if y is None:
+        return []
+    for i, (message, response) in enumerate(y):
+        y[i] = (
+            None if message is None else mdtex2html.convert((message)),
+            None if response is None else mdtex2html.convert(response),
+        )
+    return y
+
+
+gr.Chatbot.postprocess = postprocess
+
+
+def parse_text(text):
+    """Copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/."""
+    lines = text.split("\n")
+    lines = [line for line in lines if line != ""]
+    count = 0
+    for i, line in enumerate(lines):
+        if "```" in line:
+            count += 1
+            items = line.split("`")
+            if count % 2 == 1:
+                lines[i] = f'<pre><code class="language-{items[-1]}">'
             else:
-                ret.update({plugin_advanced_arg: gr.update(visible=False, label=f"插件[{k}]不需要高级参数。")})
-            return ret
-        dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt, plugin_advanced_arg] )
-        def on_md_dropdown_changed(k):
-            return {chatbot: gr.update(label="当前模型："+k)}
-        md_dropdown.select(on_md_dropdown_changed, [md_dropdown], [chatbot] )
-        # 随变按钮的回调函数注册
-        def route(k, *args, **kwargs):
-            if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
-            yield from ArgsGeneralWrapper(crazy_fns[k]["Function"])(*args, **kwargs)
-        click_handle = switchy_bt.click(route,[switchy_bt, *input_combo, gr.State(PORT)], output_combo)
-        click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
-        cancel_handles.append(click_handle)
-        # 终止按钮的回调函数注册
-        stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
-        stopBtn2.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
-
-    # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
-    def auto_opentab_delay():
-        import threading, webbrowser, time
-        print(f"如果浏览器没有自动打开，请复制并转到以下URL：")
-        print(f"\t（亮色主题）: http://localhost:{PORT}")
-        print(f"\t（暗色主题）: http://localhost:{PORT}/?__theme=dark")
-        def open():
-            time.sleep(2)       # 打开浏览器
-            DARK_MODE, = get_conf('DARK_MODE')
-            if DARK_MODE: webbrowser.open_new_tab(f"http://localhost:{PORT}/?__theme=dark")
-            else: webbrowser.open_new_tab(f"http://localhost:{PORT}")
-        threading.Thread(target=open, name="open-browser", daemon=True).start()
-        threading.Thread(target=auto_update, name="self-upgrade", daemon=True).start()
-        threading.Thread(target=warm_up_modules, name="warm-up", daemon=True).start()
-
-    auto_opentab_delay()
-    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", share=False, favicon_path="docs/logo.png", blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
-
-    # 如果需要在二级路径下运行
-    # CUSTOM_PATH, = get_conf('CUSTOM_PATH')
-    # if CUSTOM_PATH != "/": 
-    #     from toolbox import run_gradio_in_subpath
-    #     run_gradio_in_subpath(demo, auth=AUTHENTICATION, port=PORT, custom_path=CUSTOM_PATH)
-    # else: 
-    #     demo.launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png",
-    #                 blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
-
-if __name__ == "__main__":
-    main()
+                lines[i] = "<br></code></pre>"
+        else:
+            if i > 0:
+                if count % 2 == 1:
+                    line = line.replace("`", r"\`")
+                    line = line.replace("<", "&lt;")
+                    line = line.replace(">", "&gt;")
+                    line = line.replace(" ", "&nbsp;")
+                    line = line.replace("*", "&ast;")
+                    line = line.replace("_", "&lowbar;")
+                    line = line.replace("-", "&#45;")
+                    line = line.replace(".", "&#46;")
+                    line = line.replace("!", "&#33;")
+                    line = line.replace("(", "&#40;")
+                    line = line.replace(")", "&#41;")
+                    line = line.replace("$", "&#36;")
+                lines[i] = "<br>" + line
+    text = "".join(lines)
+    return text
+
+
+def predict(
+    RETRY_FLAG, input, chatbot, max_length, top_p, temperature, history, past_key_values
+):
+    try:
+        chatbot.append((parse_text(input), ""))
+    except Exception as exc:
+        logger.error(exc)
+        logger.debug(f"{chatbot=}")
+        _ = """
+        if chatbot:
+            chatbot[-1] = (parse_text(input), str(exc))
+            yield chatbot, history, past_key_values
+        # """
+        yield chatbot, history, past_key_values
+
+    for response, history, past_key_values in model.stream_chat(
+        tokenizer,
+        input,
+        history,
+        past_key_values=past_key_values,
+        return_past_key_values=True,
+        max_length=max_length,
+        top_p=top_p,
+        temperature=temperature,
+    ):
+        chatbot[-1] = (parse_text(input), parse_text(response))
+
+        yield chatbot, history, past_key_values
+
+
+def trans_api(input, max_length=4096, top_p=0.8, temperature=0.2):
+    if max_length < 10:
+        max_length = 4096
+    if top_p < 0.1 or top_p > 1:
+        top_p = 0.85
+    if temperature <= 0 or temperature > 1:
+        temperature = 0.01
+    try:
+        res, _ = model.chat(
+            tokenizer,
+            input,
+            history=[],
+            past_key_values=None,
+            max_length=max_length,
+            top_p=top_p,
+            temperature=temperature,
+        )
+        # logger.debug(f"{res=} \n{_=}")
+    except Exception as exc:
+        logger.error(f"{exc=}")
+        res = str(exc)
+
+    return res
+
+
+def reset_user_input():
+    return gr.update(value="")
+
+
+def reset_state():
+    return [], [], None
+
+
+# Delete last turn
+def delete_last_turn(chat, history):
+    if chat and history:
+        chat.pop(-1)
+        history.pop(-1)
+    return chat, history
+
+
+# Regenerate response
+def retry_last_answer(
+    user_input, chatbot, max_length, top_p, temperature, history, past_key_values
+):
+    if chatbot and history:
+        # Removing the previous conversation from chat
+        chatbot.pop(-1)
+        # Setting up a flag to capture a retry
+        RETRY_FLAG = True
+        # Getting last message from user
+        user_input = history[-1][0]
+        # Removing bot response from the history
+        history.pop(-1)
+
+    yield from predict(
+        RETRY_FLAG,  # type: ignore
+        user_input,
+        chatbot,
+        max_length,
+        top_p,
+        temperature,
+        history,
+        past_key_values,
+    )
+
+
+with gr.Blocks(title="ChatGLM2-6B-int4", theme=gr.themes.Soft(text_size="sm")) as demo:
+    # gr.HTML("""<h1 align="center">ChatGLM2-6B-int4</h1>""")
+    gr.HTML(
+        """<center><a href="https://huggingface.co/spaces/mikeee/chatglm2-6b-4bit?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>To avoid the queue and for faster inference Duplicate this Space and upgrade to GPU</center>"""
+    )
+
+    with gr.Accordion("🎈 Info", open=False):
+        _ = f"""
+            ## {model_name}
+
+            Try to refresh the browser and try again when  occasionally an error occurs.
+
+            With a GPU, a query takes from a few seconds to a few tens of seconds, dependent on the number of words/characters
+            the question and responses contain. The quality of the responses varies quite a bit it seems. Even the same
+            question with the same parameters, asked at different times, can result in quite different responses.
+
+            * Low temperature: responses will be more deterministic and focused; High temperature: responses more creative.
+
+            * Suggested temperatures -- translation: up to 0.3; chatting: > 0.4
+
+            * Top P controls dynamic vocabulary selection based on context.
+
+            For a table of example values for different scenarios, refer to [this](https://community.openai.com/t/cheat-sheet-mastering-temperature-and-top-p-in-chatgpt-api-a-few-tips-and-tricks-on-controlling-the-creativity-deterministic-output-of-prompt-responses/172683)
+
+            If the instance is not on a GPU (T4), it will be very slow. You can try to run the colab notebook [chatglm2-6b-4bit colab notebook](https://colab.research.google.com/drive/1WkF7kOjVCcBBatDHjaGkuJHnPdMWNtbW?usp=sharing) for a spin.
+
+            The T4 GPU is sponsored by a community GPU grant from Huggingface. Thanks a lot!
+            """
+        gr.Markdown(dedent(_))
+    chatbot = gr.Chatbot()
+    with gr.Row():
+        with gr.Column(scale=4):
+            with gr.Column(scale=12):
+                user_input = gr.Textbox(
+                    show_label=False,
+                    placeholder="Input...",
+                ).style(container=False)
+                RETRY_FLAG = gr.Checkbox(value=False, visible=False)
+            with gr.Column(min_width=32, scale=1):
+                with gr.Row():
+                    submitBtn = gr.Button("Submit", variant="primary")
+                    deleteBtn = gr.Button("Delete last turn", variant="secondary")
+                    retryBtn = gr.Button("Regenerate", variant="secondary")
+        with gr.Column(scale=1):
+            emptyBtn = gr.Button("Clear History")
+            max_length = gr.Slider(
+                0,
+                32768,
+                value=8192,
+                step=1.0,
+                label="Maximum length",
+                interactive=True,
+            )
+            top_p = gr.Slider(
+                0, 1, value=0.85, step=0.01, label="Top P", interactive=True
+            )
+            temperature = gr.Slider(
+                0.01, 1, value=0.95, step=0.01, label="Temperature", interactive=True
+            )
+
+    history = gr.State([])
+    past_key_values = gr.State(None)
+
+    user_input.submit(
+        predict,
+        [
+            RETRY_FLAG,
+            user_input,
+            chatbot,
+            max_length,
+            top_p,
+            temperature,
+            history,
+            past_key_values,
+        ],
+        [chatbot, history, past_key_values],
+        show_progress="full",
+    )
+    submitBtn.click(
+        predict,
+        [
+            RETRY_FLAG,
+            user_input,
+            chatbot,
+            max_length,
+            top_p,
+            temperature,
+            history,
+            past_key_values,
+        ],
+        [chatbot, history, past_key_values],
+        show_progress="full",
+        api_name="predict",
+    )
+    submitBtn.click(reset_user_input, [], [user_input])
+
+    emptyBtn.click(
+        reset_state, outputs=[chatbot, history, past_key_values], show_progress="full"
+    )
+
+    retryBtn.click(
+        retry_last_answer,
+        inputs=[
+            user_input,
+            chatbot,
+            max_length,
+            top_p,
+            temperature,
+            history,
+            past_key_values,
+        ],
+        # outputs = [chatbot, history, last_user_message, user_message]
+        outputs=[chatbot, history, past_key_values],
+    )
+    deleteBtn.click(delete_last_turn, [chatbot, history], [chatbot, history])
+
+    with gr.Accordion("Example inputs", open=True):
+        etext = """In America, where cars are an important part of the national psyche, a decade ago people had suddenly started to drive less, which had not happened since the oil shocks of the 1970s. """
+        examples = gr.Examples(
+            examples=[
+                ["What NFL team won the Super Bowl in the year Justin Bieber was born? "],
+                ["What NFL team won the Super Bowl in the year Justin Bieber was born? Think step by step."],
+                ["Explain the plot of Cinderella in a sentence."],
+                [
+                    "How long does it take to become proficient in French, and what are the best methods for retaining information?"
+                ],
+                ["What are some common mistakes to avoid when writing code?"],
+                ["Build a prompt to generate a beautiful portrait of a horse"],
+                ["Suggest four metaphors to describe the benefits of AI"],
+                ["Write a pop song about leaving home for the sandy beaches."],
+                ["Write a summary demonstrating my ability to tame lions"],
+                ["鲁迅和周树人什么关系"],
+                ["从前有一头牛，这头牛后面有什么？"],
+                ["正无穷大加一大于正无穷大吗？"],
+                ["正无穷大加正无穷大大于正无穷大吗？"],
+                ["-2的平方根等于什么"],
+                ["树上有5只鸟，猎人开枪打死了一只。树上还有几只鸟？"],
+                ["树上有11只鸟，猎人开枪打死了一只。树上还有几只鸟？提示：需考虑鸟可能受惊吓飞走。"],
+                ["鲁迅和周树人什么关系 用英文回答"],
+                ["以红楼梦的行文风格写一张委婉的请假条。不少于320字。"],
+                [f"{etext} 翻成中文，列出3个版本"],
+                [f"{etext} \n 翻成中文，保留原意，但使用文学性的语言。不要写解释。列出3个版本"],
+                ["js 判断一个数是不是质数"],
+                ["js 实现python 的 range(10)"],
+                ["js 实现python 的 [*(range(10)]"],
+                ["假定 1 + 2 = 4, 试求 7 + 8"],
+                ["Erkläre die Handlung von Cinderella in einem Satz."],
+                ["Erkläre die Handlung von Cinderella in einem Satz. Auf Deutsch"],
+            ],
+            inputs=[user_input],
+            examples_per_page=30,
+        )
+
+    with gr.Accordion("For Chat/Translation API", open=False, visible=False):
+        input_text = gr.Text()
+        tr_btn = gr.Button("Go", variant="primary")
+        out_text = gr.Text()
+    tr_btn.click(
+        trans_api,
+        [input_text, max_length, top_p, temperature],
+        out_text,
+        # show_progress="full",
+        api_name="tr",
+    )
+    _ = """
+    input_text.submit(
+        trans_api,
+        [input_text, max_length, top_p, temperature],
+        out_text,
+        show_progress="full",
+        api_name="tr1",
+    )
+    # """
+
+# demo.queue().launch(share=False, inbrowser=True)
+# demo.queue().launch(share=True, inbrowser=True, debug=True)
+
+# concurrency_count > 1 requires more memory, max_size: queue size
+# T4 medium: 30GB, model size: ~4G concurrency_count = 6
+# leave one for api access
+# reduce to 5 if OOM occurs to often
+
+demo.queue(concurrency_count=6, max_size=30).launch(debug=True)

requirements.txt

@@ -1,24 +1,9 @@
-tiktoken>=0.3.3
-requests[socks]
-transformers
-python-markdown-math
-beautifulsoup4
-prompt_toolkit
-latex2mathml
-python-docx
-mdtex2html
-colorama
-Markdown
-pygments
-pymupdf
-openai
-numpy
-arxiv
-rich
-pdfminer
 protobuf
-transformers==4.27.1
+transformers==4.30.2
 cpm_kernels
-torch>=1.10
+torch>=2.0
+# gradio
 mdtex2html
 sentencepiece
+accelerate
+loguru