chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'master' into frontier

Browse Source
This commit is contained in:
binary-husky 2023-12-05 15:08:49 +08:00
commit 2b96a60b76
5 changed files with 30 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
README.md
View File

@ -18,15 +18,15 @@
[![Wiki][Wiki-image]][Wiki-url] [![Wiki][Wiki-image]][Wiki-url]
[![PR][PRs-image]][PRs-url] [![PR][PRs-image]][PRs-url]
[License-image]: https://img.shields.io/badge/LICENSE-GPL3.0-orange?&style=flat-square [Github-image]: https://img.shields.io/badge/github-12100E.svg?style=flat-square
[Github-image]: https://img.shields.io/badge/github-12100E.svg?&style=flat-square [License-image]: https://img.shields.io/github/license/binary-husky/gpt_academic?label=License&style=flat-square&color=orange
[Releases-image]: https://img.shields.io/badge/Releases-v3.6.0-blue?style=flat-square [Releases-image]: https://img.shields.io/github/release/binary-husky/gpt_academic?label=Release&style=flat-square&color=blue
[Installation-image]: https://img.shields.io/badge/Installation-v3.6.1-blue?style=flat-square [Installation-image]: https://img.shields.io/badge/dynamic/json?color=blue&url=https://raw.githubusercontent.com/binary-husky/gpt_academic/master/version&query=$.version&label=Installation&style=flat-square
[Wiki-image]: https://img.shields.io/badge/wiki-项目文档-black?style=flat-square [Wiki-image]: https://img.shields.io/badge/wiki-项目文档-black?style=flat-square
[PRs-image]: https://img.shields.io/badge/PRs-welcome-pink?style=flat-square [PRs-image]: https://img.shields.io/badge/PRs-welcome-pink?style=flat-square
[License-url]: https://github.com/binary-husky/gpt_academic/blob/master/LICENSE
[Github-url]: https://github.com/binary-husky/gpt_academic [Github-url]: https://github.com/binary-husky/gpt_academic
[License-url]: https://github.com/binary-husky/gpt_academic/blob/master/LICENSE
[Releases-url]: https://github.com/binary-husky/gpt_academic/releases [Releases-url]: https://github.com/binary-husky/gpt_academic/releases
[Installation-url]: https://github.com/binary-husky/gpt_academic#installation [Installation-url]: https://github.com/binary-husky/gpt_academic#installation
[Wiki-url]: https://github.com/binary-husky/gpt_academic/wiki [Wiki-url]: https://github.com/binary-husky/gpt_academic/wiki
@ -38,7 +38,8 @@
**如果喜欢这个项目，请给它一个Star；如果您发明了好用的快捷键或插件，欢迎发pull requests！** **如果喜欢这个项目，请给它一个Star；如果您发明了好用的快捷键或插件，欢迎发pull requests！**
If you like this project, please give it a Star. Read this in [English](docs/README.English.md) | [日本語](docs/README.Japanese.md) | [한국어](docs/README.Korean.md) | [Русский](docs/README.Russian.md) | [Français](docs/README.French.md). All translations have been provided by the project itself. To translate this project to arbitrary language with GPT, read and run [`multi_language.py`](multi_language.py) (experimental). If you like this project, please give it a Star.
Read this in [English](docs/README.English.md) | [日本語](docs/README.Japanese.md) | [한국어](docs/README.Korean.md) | [Русский](docs/README.Russian.md) | [Français](docs/README.French.md). All translations have been provided by the project itself. To translate this project to arbitrary language with GPT, read and run [`multi_language.py`](multi_language.py) (experimental).
<br> <br>
@ -47,7 +48,7 @@ If you like this project, please give it a Star. Read this in [English](docs/REA
> 2.本项目中每个文件的功能都在[自译解报告](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic项目自译解报告)`self_analysis.md`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。常见问题请查阅wiki。 > 2.本项目中每个文件的功能都在[自译解报告](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic项目自译解报告)`self_analysis.md`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。常见问题请查阅wiki。
> [![常规安装方法](https://img.shields.io/static/v1?label=&message=常规安装方法&color=gray)](#installation) [![一键安装脚本](https://img.shields.io/static/v1?label=&message=一键安装脚本&color=gray)](https://github.com/binary-husky/gpt_academic/releases) [![配置说明](https://img.shields.io/static/v1?label=&message=配置说明&color=gray)](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明) [![wiki](https://img.shields.io/static/v1?label=&message=wiki&color=gray)]([https://github.com/binary-husky/gpt_academic/wiki/项目配置说明](https://github.com/binary-husky/gpt_academic/wiki)) > [![常规安装方法](https://img.shields.io/static/v1?label=&message=常规安装方法&color=gray)](#installation) [![一键安装脚本](https://img.shields.io/static/v1?label=&message=一键安装脚本&color=gray)](https://github.com/binary-husky/gpt_academic/releases) [![配置说明](https://img.shields.io/static/v1?label=&message=配置说明&color=gray)](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明) [![wiki](https://img.shields.io/static/v1?label=&message=wiki&color=gray)]([https://github.com/binary-husky/gpt_academic/wiki/项目配置说明](https://github.com/binary-husky/gpt_academic/wiki))
> >
> 3.本项目兼容并鼓励尝试国产大语言模型ChatGLM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,azure-key3,api2d-key4"`。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。 > 3.本项目兼容并鼓励尝试国产大语言模型ChatGLM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,azure-key3,api2d-key4"`。需要临时更换`API_KEY`时，在输入区输入临时的`API_KEY`然后回车键提交即可生效。
<br><br> <br><br>

10
config.py
View File

@ -15,13 +15,13 @@ API_KEY = "此处填API密钥" # 可同时填写多个API-KEY，用英文逗
USE_PROXY = False USE_PROXY = False
if USE_PROXY: if USE_PROXY:
""" """
代理网络的地址，打开你的代理软件查看代理协议(socks5h / http)、地址(localhost)和端口(11284)
填写格式是 [协议]:// [地址] :[端口]，填写之前不要忘记把USE_PROXY改成True，如果直接在海外服务器部署，此处不修改 填写格式是 [协议]:// [地址] :[端口]，填写之前不要忘记把USE_PROXY改成True，如果直接在海外服务器部署，此处不修改
<配置教程&视频教程> https://github.com/binary-husky/gpt_academic/issues/1> <配置教程&视频教程> https://github.com/binary-husky/gpt_academic/issues/1>
[协议] 常见协议无非socks5h/http; 例如 v2**y 和 ss* 的默认本地协议是socks5h; 而cl**h 的默认本地协议是http [协议] 常见协议无非socks5h/http; 例如 v2**y 和 ss* 的默认本地协议是socks5h; 而cl**h 的默认本地协议是http
[地址] 懂的都懂，不懂就填localhost或者127.0.0.1肯定错不了（localhost意思是代理软件安装在本机上） [地址] 填localhost或者127.0.0.1（localhost意思是代理软件安装在本机上）
[端口] 在代理软件的设置里找。虽然不同的代理软件界面不一样，但端口号都应该在最显眼的位置上 [端口] 在代理软件的设置里找。虽然不同的代理软件界面不一样，但端口号都应该在最显眼的位置上
""" """
# 代理网络的地址，打开你的*学*网软件查看代理的协议(socks5h / http)、地址(localhost)和端口(11284)
proxies = { proxies = {
# [协议]:// [地址] :[端口] # [协议]:// [地址] :[端口]
"http": "socks5h://localhost:11284", # 再例如 "http": "http://127.0.0.1:7890", "http": "socks5h://localhost:11284", # 再例如 "http": "http://127.0.0.1:7890",
@ -100,6 +100,12 @@ AVAIL_LLM_MODELS = ["gpt-3.5-turbo-1106","gpt-4-1106-preview","gpt-4-vision-prev
MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3" MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
# 选择本地模型变体（只有当AVAIL_LLM_MODELS包含了对应本地模型时，才会起作用）
# 如果你选择Qwen系列的模型，那么请在下面的QWEN_MODEL_SELECTION中指定具体的模型
# 也可以是具体的模型路径
QWEN_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
# 百度千帆（LLM_MODEL="qianfan"） # 百度千帆（LLM_MODEL="qianfan"）
BAIDU_CLOUD_API_KEY = '' BAIDU_CLOUD_API_KEY = ''
BAIDU_CLOUD_SECRET_KEY = '' BAIDU_CLOUD_SECRET_KEY = ''

24
request_llms/bridge_qwen.py
View File

@ -1,13 +1,7 @@
model_name = "Qwen" model_name = "Qwen"
cmd_to_install = "`pip install -r request_llms/requirements_qwen.txt`" cmd_to_install = "`pip install -r request_llms/requirements_qwen.txt`"
from toolbox import ProxyNetworkActivate, get_conf
from transformers import AutoModel, AutoTokenizer
import time
import threading
import importlib
from toolbox import update_ui, get_conf, ProxyNetworkActivate
from multiprocessing import Process, Pipe
from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
@ -24,16 +18,14 @@ class GetQwenLMHandle(LocalLLMHandle):
def load_model_and_tokenizer(self): def load_model_and_tokenizer(self):
# 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行 # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
import os, glob # from modelscope import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
import os from transformers import AutoModelForCausalLM, AutoTokenizer
import platform from transformers.generation import GenerationConfig
from modelscope import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
with ProxyNetworkActivate('Download_LLM'): with ProxyNetworkActivate('Download_LLM'):
model_id = 'qwen/Qwen-7B-Chat' model_id = get_conf('QWEN_MODEL_SELECTION')
self._tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen-7B-Chat', trust_remote_code=True, resume_download=True) self._tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, resume_download=True)
# use fp16 # use fp16
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True, fp16=True).eval() model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True).eval()
model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参 model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
self._model = model self._model = model
@ -51,7 +43,7 @@ class GetQwenLMHandle(LocalLLMHandle):
query, max_length, top_p, temperature, history = adaptor(kwargs) query, max_length, top_p, temperature, history = adaptor(kwargs)
for response in self._model.chat(self._tokenizer, query, history=history, stream=True): for response in self._model.chat_stream(self._tokenizer, query, history=history):
yield response yield response
def try_to_import_special_deps(self, **kwargs): def try_to_import_special_deps(self, **kwargs):

2
request_llms/requirements_qwen.txt
View File

@ -1,2 +1,4 @@
modelscope modelscope
transformers_stream_generator transformers_stream_generator
auto-gptq
optimum

5
tests/test_llms.py
View File

@ -16,8 +16,9 @@ if __name__ == "__main__":
# from request_llms.bridge_jittorllms_llama import predict_no_ui_long_connection # from request_llms.bridge_jittorllms_llama import predict_no_ui_long_connection
# from request_llms.bridge_claude import predict_no_ui_long_connection # from request_llms.bridge_claude import predict_no_ui_long_connection
# from request_llms.bridge_internlm import predict_no_ui_long_connection # from request_llms.bridge_internlm import predict_no_ui_long_connection
from request_llms.bridge_deepseekcoder import predict_no_ui_long_connection # from request_llms.bridge_deepseekcoder import predict_no_ui_long_connection
# from request_llms.bridge_qwen import predict_no_ui_long_connection # from request_llms.bridge_qwen_7B import predict_no_ui_long_connection
from request_llms.bridge_qwen import predict_no_ui_long_connection
# from request_llms.bridge_spark import predict_no_ui_long_connection # from request_llms.bridge_spark import predict_no_ui_long_connection
# from request_llms.bridge_zhipu import predict_no_ui_long_connection # from request_llms.bridge_zhipu import predict_no_ui_long_connection
# from request_llms.bridge_chatglm3 import predict_no_ui_long_connection # from request_llms.bridge_chatglm3 import predict_no_ui_long_connection