sudo apt-get update sudo apt upgrade 更新时间较长,请耐心等待
sudo apt-get install ca-certificates curl gnupg lsb-release curl -fsSL http://mirrors.aliyun.com/docker-ce/linux/ubuntu/gpg | sudo apt-key add - sudo add-apt-repository "deb [arch=amd64] http://mirrors.aliyun.com/docker-ce/linux/ubuntu $(lsb_release -cs) stable" apt-get install docker-ce docker-ce-cli containerd.i docker -v 
vi /etc/docker/daemon.json 按i进入编辑模式
加入以下内容:
{ "registry-mirrors": [ "https://docker.mirrors.ustc.edu.cn", "https://hub-mirror.c.163.com", "https://docker.m.daocloud.io", "https://ghcr.io", "https://mirror.baidubce.com", "https://docker.nju.edu.cn" ] } 按ESC键退出编辑模式,接着输入:wq,保存并退出
sudo systemctl daemon-reload sudo systemctl restart docker curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \ | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \ | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \ | sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list sudo apt-get update sudo apt-get install -y nvidia-container-toolkit sudo nvidia-ctk runtime configure --runtime=docker sudo systemctl restart docker docker pull ollama/ollama:latest 国内镜像
docker pull dhub.kubesre.xyz/ollama/ollama:latest docker run -d --gpus=all --restart=always -v /home/docker/ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama 使ollama保持模型加载在内存(显存)中
docker run -d --gpus=all -e OLLAMA_KEEP_ALIVE=-1 --restart=always -v /home/docker/ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama docker exec -it ollama ollama run qwen2 运行效果如图:
模型库
| 模型 | 参数数量 | 大小 | 下载方式 |
|---|---|---|---|
| Llama 2 | 7B | 3.8GB | docker exec -it ollama ollama run llama2 |
| Mistral | 7B | 4.1GB | docker exec -it ollama ollama run mistral |
| Dolphin Phi | 2.7B | 1.6GB | docker exec -it ollama ollama run dolphin-phi |
| Phi-2 | 2.7B | 1.7GB | docker exec -it ollama ollama run phi |
| Neural Chat | 7B | 4.1GB | docker exec -it ollama ollama run neural-chat |
| Starling | 7B | 4.1GB | docker exec -it ollama ollama run starling-lm |
| Code Llama | 7B | 3.8GB | docker exec -it ollama ollama run codellama |
| Llama 2 Uncensored | 7B | 3.8GB | docker exec -it ollama ollama run llama2-uncensored |
| Llama 2 | 13B | 7.3GB | docker exec -it ollama ollama run llama2:13b |
| Llama 2 | 70B | 39GB | docker exec -it ollama ollama run llama2:70b |
| Orca Mini | 3B | 1.9GB | docker exec -it ollama ollama run orca-mini |
| Vicuna | 7B | 3.8GB | docker exec -it ollama ollama run vicuna |
| LLaVA | 7B | 4.5GB | docker exec -it ollama ollama run llava |
| Gemma | 2B | 1.4GB | docker exec -it ollama ollama run gemma:2b |
| Gemma | 7B | 4.8GB | docker exec -it ollama ollama run gemma:7b |
查看自己服务器的业务端口,我们这里是30131-30140
main版本
docker run -d -p 30131:8080 --gpus all --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.nju.edu.cn/open-webui/open-webui:main cuda版本
docker run -d -p 30131:8080 --gpus all --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.nju.edu.cn/open-webui/open-webui:cuda 



