ollama部署模型

下载模型
ollama pull qwen:0.5b

本地运行
ollama run qwen:0.5b

局域网连接

修改监听ip
vim /etc/systemd/system/ollama.service
    在文件中添加
    Environment="OLLAMA_HOST=0.0.0.0:11434"

cat /etc/systemd/system/ollama.service
[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/cuda-12.5/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin"
Environment="OLLAMA_HOST=0.0.0.0:11434"
[Install]
WantedBy=default.target

systemctl daemon-reload
systemctl restart ollama.service

# 测试代码 python

from langchain_community.chat_models import ChatOllama  
from langchain_core.messages import HumanMessage  

ollama_llm = ChatOllama(model="qwen:0.5b", base_url='http://172.10.10.2:11434')  

messages = [  
    HumanMessage(  
        content="你好，请你介绍一下你自己",  
    )  
]  

chat_model_response = ollama_llm.invoke(messages)  
print(chat_model_response)