20250417 - 本机部署Deepseek R1:8b模型

安装4个软件:

1_VSCodeSetup-x64-1.84.1.exe /silent /norestart

2_Git-2.42.0.2-64-bit.exe /silent /norestart

3_pycharm-community-2023.2.4.exe /S

4_Docker Desktop - 注册需VPN

Python

安装WSL 命令:

dism.exe /online /enable-feature /featurename:VirtualMachinePlatform /all /norestart

0 or 3010

dism.exe /online /enable-feature /featurename:Microsoft-Windows-Subsystem-Linux /all /norestart

0 or 3010

可能需要安装

wsl_update_x64.msi /q /norestart

20250320 - 获取更新

wsl --update

20250320 - 通过运行以下命令启用“虚拟机平台”:

wsl.exe --install --no-distribution

 

设置版本及查看状态

wsl --set-default-version 2

 

WSL --status

 

打开代理

WSL --list --online查看可用版本

WSL --install Ubuntu 安装版本

 

安装Ollama

进入WSL

 

 

运行

curl -fsSL https://ollama.com/install.sh | sh

 

 

 

查看版本

Ollama --version

 

 

 

下载大模型数据

ollama pull deepseek-r1

ollama pull deepseek-r1:7b

Note: DeepSeek-R1 7B version is significantly more powerful but requires more RAM and CPU resources.

 

 

开启服务

ollama run deepseek-r1

ollama run deepseek-r1:7b

ollama run deepseek-r1:8b

 

 

 

 

 

 

检查docker版本 WSL

 

 

 

The following Docker command will map the container port 8080 to host port 3000 and ensure the container can communicate with the Ollama server running on your host machine.

 

Run the following Docker command:

 

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

 

会自动下载open-WebUI WSL

 

 

 

Now, the WebUI has been successfully deployed, which can be accessed at http://localhost:3000.