AI

Local deployment Llama3 – 8B/70B large model

本地部署开源Llama3 大模型。

1. GPT4All :  适合低配置用户,可以在CPU/GPU上跑【点击下载

Local deployment Llama3 – 8B/70B large model

2.LMstudio ,支持下载多模型 8B/70B 等,模型选择更多!【点击下载

Local deployment Llama3 – 8B/70B large model

3.Ollama,支持多平台!Windows / Mac /Linux 都可以运行 【点击下载

并在 Windows 上打开 WSL  功能:

Local deployment Llama3 – 8B/70B large model

安装Docker Desktop :【点击前往

然后本地安装webUI

(1)在CPU下运行:

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

(2)支持GPU运行:

docker run -d -p 3000:8080 –gpus=all -v ollama:/root/.ollama -v open-webui:/app/backend/data –name open-webui –restart always ghcr.io/open-webui/open-webui:ollama

安装完成通过本地地址:http://127.0.0.1:3000 进行访问

Local deployment Llama3 – 8B/70B large model

Leave a Reply

Your email address will not be published. Required fields are marked *