ubuntu ollama 本地部署

1、下载install.sh

$ sudo mkdir ollama

$ cd ollama

$ sudo wget https://ollama.com/install.sh

2、注释下载功能

# curl --fail --show-error --location --progress-bar -o $TEMP_DIR/ollama "https://ollama.com/download/ollama-linux-${ARCH}${VER_PARAM}"

手动下载 https://ollama.com/download/ollama-linux-amd64

保存在ollama目录下

3、注释以前安装功能，增加当前路径下ollama的安装

4 运行 install.sh ,安装

sudo bash install.sh

>>> Downloading ollama...
https://ollama.com/download/ollama-linux-amd64
>>> Installing ollama to /usr/local/bin...
>>> Creating ollama user...
>>> Adding ollama user to video group...
>>> Adding current user to ollama group...
>>> Creating ollama systemd service...
>>> Enabling and starting ollama service...
Created symlink /etc/systemd/system/default.target.wants/ollama.service → /etc/systemd/system/ollama.service.
>>> NVIDIA GPU installed.

5、设置模型下载路径

mkdir ollama_cache
sudo vim ~.bashrc

添加
export OLLAMA_MODELS=/home/xxxx/ollama/ollama_cache

如果开始没配置OLLAMA_MODELS ，默认路径是/usr/share/ollama/.ollama/models

6、运行ollama serve

Error: listen tcp 127.0.0.1:11434: bind: address already in use

修改ollama端口

sudo vim /etc/systemd/system/ollama.service

在 [Service] 下添加  
Environment="OLLAMA_HOST=0.0.0.0"

[Service]
ExecStart=/usr/local/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=/usr/local/sbin:/usr/local/bin:/sbin:/bin:/usr/sbin:/usr/bin:/root/bin"
Environment="OLLAMA_HOST=0.0.0.0"

重启服务

sudo systemctl daemon-reload
sudo systemctl restart ollama

关闭服务
systemctl stop ollama
启动服务
systemctl start ollama