1 离线安装

1.1 下载离线包

# 1 确定系统架构
# x86_64 -> amd64
# aarch64或arm64 ->arm64
uname -m

# 2 下载
# x86架构
curl https://ollama.com/download/ollama-linux-amd64.tgz

# arm架构
# curl https://ollama.com/download/ollama-linux-arm64.tgz

1.2 安装

tar -zxvf ollama-linux-amd64.tgz

sudo mv ollam /usr/local/bin
sudo chmod +x /usr/local/bin/ollama

ollama --version

1.3 启动

ollama serve

2 将ollama设为后台服务，开机启动

2.1 创建ollama用户和用户组

sudo useradd -r -s /bin/false -U -m -d /usr/share/ollama ollama
sudo usermod -a -G ollama $(whoami)

2.2 创建ollama.service

vim /etc/systemd/system/ollama.service，输入以下内容

[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=/usr/local/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=/usr/local/bin"


[Install]
WantedBy=default.target

2.3 启动服务

sudo systemctl daemon-reload
sudo systemctl enable ollama
sudo systemctl start ollama

2.4 查看状态及日志

sudo systemctl status ollama

sudo journalctl -u ollama

3 注册离线模型

3.1 下载模型

从modelscope中下载DeepSeek-R1-Distill-Qwen-1.5B

modelscope download --model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --local_dir ./DeepSeek-R1-Distill-Qwen-1.5B

3.2 创建Modelfile

在DeepSeek-R1-Distill-Qwen-1.5B的目录下，创建Modelfile，写入以下内容

FROM .

3.3 注册为ollama模型

# 进入到DeepSeek-R1-Distill-Qwen-1.5B的目录下，执行以下命令
ollama create DeepSeek-R1-Distill-Qwen-1.5B -f .\Modelfile

3.4 查看

ollama ls

3.5 运行

ollama run DeepSeek-R1-Distill-Qwen-1.5B:latest