目录
Xinference 多运用与企业级部署,而 Ollama 则简化本地部署与交互,提供开箱即用的命令行工具和轻量级 API,支持快速模型加载和交互式调试。
1. 安装
在线安装
shell
curl -fsSL https://ollama.com/install.sh | sh离线安装
shell
curl -L https://ollama.com/download/ollama-linux-amd64.tgz -o ollama-linux-amd64.tgz
sudo tar -C /usr -xzf ollama-linux-amd64.tgz权限设置
shell
sudo useradd -r -s /bin/false -U -m -d /usr/share/ollama ollama
sudo usermod -a -G ollama $(whoami)2. 配置
https://github.com/ollama/ollama/blob/main/docs/faq.md
shell
# /etc/systemd/system/ollama.service.d/override.conf
sudo systemctl edit ollama
[Service]
Environment="OLLAMA_HOST=172.17.0.1:8888"
Environment="OLLAMA_KEEP_ALIVE=1h"
Environment="OLLAMA_MAX_LOADED_MODELS=2"
Environment="OLLAMA_NUM_PARALLEL=3"默认位置: /usr/share/ollama/.ollama/models
**特别注意:**修改了默认主机后,运行ollama命令需要增加加前缀 OLLAMA_HOST=172.17.0.1:8888
例如:OLLAMA_HOST=172.17.0.1:8888 ollama ps
3. 自启动
sudo vim /etc/systemd/system/ollama.service
shell
[Unit]
Description=Ollama Service
After=network-online.target
[Service]
ExecStart=/usr/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=$PATH"
[Install]
WantedBy=default.target启动
shell
sudo systemctl daemon-reload
sudo systemctl enable --now ollama4. 卸载
shell
sudo systemctl stop ollama
sudo systemctl disable ollama
sudo rm /etc/systemd/system/ollama.service
sudo rm $(which ollama)
sudo rm -r /usr/share/ollama
sudo userdel ollama
sudo groupdel ollama
sudo rm -rf /usr/local/lib/ollama5. 导入GGUF模型
5.1. 创建 Modelfile 文件
vim DeepSeek-R1-Distill-Qwen-7B-GGUF/Modelfile
shell
FROM DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf
TEMPLATE """{{- if .System }}{{ .System }}{{ end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1}}
{{- if eq .Role "user" }}<|User|>{{ .Content }}
{{- else if eq .Role "assistant" }}<|Assistant|>{{ .Content }}{{- if not $last }}<|end▁of▁sentence|>{{- end }}
{{- end }}
{{- if and $last (ne .Role "assistant") }}<|Assistant|>{{- end }}
{{- end }}"""
PARAMETER stop "<|begin▁of▁sentence|>"
PARAMETER stop "<|end▁of▁sentence|>"
PARAMETER stop "<|User|>"
PARAMETER stop "<|Assistant|>"5.2. 创建、运行模型
shell
#ollama create <model_name> -f <path_to_Modelfile>
ollama create deepseek-r1-7b
ollama run deepseek-r1-7b
ollama list
ollama ps