在linux服務(wù)器本地部署Deepseek及在mac遠(yuǎn)程web-ui訪問的操作

更新時間：2025年02月19日 11:03:53 作者：niuguangshuo

文章介紹了在Linux服務(wù)器上部署和使用DeepSeek模型的步驟,包括安裝Ollama、下載和運(yùn)行模型,以及在Linux服務(wù)器上配置Ollama服務(wù)以實現(xiàn)遠(yuǎn)程訪問,接著,文章介紹了在Mac上安裝WebUI工具OpenWebUI,以便更方便地與遠(yuǎn)程Linux服務(wù)器上的DeepSeek模型進(jìn)行交互

1. 在Linux服務(wù)器上部署DeepSeek模型

要在 Linux 上通過 Ollama 安裝和使用模型，您可以按照以下步驟進(jìn)行操作：

步驟 1：安裝 Ollama

安裝 Ollama：
使用以下命令安裝 Ollama：

curl -sSfL https://ollama.com/install.sh | sh

驗證安裝：
安裝完成后，您可以通過以下命令驗證 Ollama 是否安裝成功：

ollama --version

步驟 2：下載模型

ollama run deepseek-r1:32b

這將下載并啟動DeepSeek R1 32B模型。

DeepSeek R1 蒸餾模型列表

模型名稱	參數(shù)量	基礎(chǔ)架構(gòu)	適用場景
DeepSeek-R1-Distill-Qwen-1.5B	1.5B	Qwen2.5	適合移動設(shè)備或資源受限的終端
DeepSeek-R1-Distill-Qwen-7B	7B	Qwen2.5	適合普通文本生成工具
DeepSeek-R1-Distill-Llama-8B	8B	Llama3.1	適合小型企業(yè)日常文本處理
DeepSeek-R1-Distill-Qwen-14B	14B	Qwen2.5	適合桌面級應(yīng)用
DeepSeek-R1-Distill-Qwen-32B	32B	Qwen2.5	適合專業(yè)領(lǐng)域知識問答系統(tǒng)
DeepSeek-R1-Distill-Llama-70B	70B	Llama3.3	適合科研、學(xué)術(shù)研究等高要求場景

RTX 4090 顯卡顯存為 24GB，32B 模型在 4-bit 量化下約需 22GB 顯存，適合該硬件。32B 模型在推理基準(zhǔn)測試中表現(xiàn)優(yōu)異，接近 70B 模型的推理能力，但對硬件資源需求更低。

步驟 3：運(yùn)行模型

 ollama run deepseek-r1:32b

通過上面的步驟，已經(jīng)可以直接在 Linux服務(wù)器通過命令行的形式使用Deepseek了。但是不夠友好，下面介紹更方便的形式。

2. 在linux服務(wù)器配置Ollama服務(wù)

1. 設(shè)置Ollama服務(wù)配置

設(shè)置OLLAMA_HOST=0.0.0.0環(huán)境變量，這使得Ollama服務(wù)能夠監(jiān)聽所有網(wǎng)絡(luò)接口，從而允許遠(yuǎn)程訪問。

sudo vi /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="OLLAMA_HOST=0.0.0.0"
Environment="PATH=/usr/local/cuda/bin:/home/bytedance/miniconda3/bin:/home/bytedance/miniconda3/condabin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin"
[Install]
WantedBy=default.target

2. 重新加載并重啟Ollama服務(wù)

sudo systemctl daemon-reload
sudo systemctl restart ollama

3.驗證Ollama服務(wù)是否正常運(yùn)行

運(yùn)行以下命令，確保Ollama服務(wù)正在監(jiān)聽所有網(wǎng)絡(luò)接口：

sudo netstat -tulpn | grep ollama

您應(yīng)該看到類似以下的輸出，表明Ollama服務(wù)正在監(jiān)聽所有網(wǎng)絡(luò)接口（0.0.0.0）：

tcp 0 0 0.0.0.0:11434 0.0.0.0:* LISTEN - ollama

4. 配置防火墻以允許遠(yuǎn)程訪問

為了確保您的Linux服務(wù)器允許從外部訪問Ollama服務(wù)，您需要配置防火墻以允許通過端口11434的流量。

sudo ufw allow 11434/tcp
sudo ufw reload

5. 驗證防火墻規(guī)則

確保防火墻規(guī)則已正確添加，并且端口11434已開放。您可以使用以下命令檢查防火墻狀態(tài)：

sudo ufw status

狀態(tài)： 激活
至                          動作          來自
-                          --          --
22/tcp                     ALLOW       Anywhere                  
11434/tcp                  ALLOW       Anywhere                  
22/tcp (v6)                ALLOW       Anywhere (v6)             
11434/tcp (v6)             ALLOW       Anywhere (v6)

6. 測試遠(yuǎn)程訪問

在完成上述配置后，您可以通過遠(yuǎn)程設(shè)備（如Mac）測試對Ollama服務(wù)的訪問。
在遠(yuǎn)程設(shè)備上測試連接：
在Mac上打開終端，運(yùn)行以下命令以測試對Ollama服務(wù)的連接：

curl http://10.37.96.186:11434/api/version

顯示

{"version":"0.5.7"}

測試問答

curl -X POST http://10.37.96.186:11434/api/generate \
     -H "Content-Type: application/json" \
     -d '{"model": "deepseek-r1:32b", "prompt": "你是誰?"}'

顯示

{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.118616168Z","response":"\u003cthink\u003e","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.150938966Z","response":"\n\n","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.175255854Z","response":"\u003c/think\u003e","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.199509353Z","response":"\n\n","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.223657359Z","response":"您好","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.24788375Z","response":"！","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.272068174Z","response":"我是","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.296163417Z","response":"由","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.320515728Z","response":"中國的","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.344646528Z","response":"深度","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.36880216Z","response":"求","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.393006489Z","response":"索","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.417115966Z","response":"（","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.441321254Z","response":"Deep","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.465439117Z","response":"Seek","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.489619415Z","response":"）","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.51381827Z","response":"公司","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.538012781Z","response":"開發(fā)","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.562186246Z","response":"的","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.586331325Z","response":"智能","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.610539651Z","response":"助手","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.634769989Z","response":"Deep","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.659134003Z","response":"Seek","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.683523205Z","response":"-R","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.70761762Z","response":"1","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.731953604Z","response":"。","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.756135462Z","response":"如","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.783480232Z","response":"您","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.807766337Z","response":"有任何","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.831964079Z","response":"任何","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.856229156Z","response":"問題","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.880487159Z","response":"，","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.904710537Z","response":"我會","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.929026993Z","response":"盡","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.953239249Z","response":"我","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:15.977496819Z","response":"所能","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:16.001763128Z","response":"為您提供","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:16.026068523Z","response":"幫助","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:16.050242581Z","response":"。","done":false}
{"model":"deepseek-r1:32b","created_at":"2025-02-06T00:47:16.074454593Z","response":"","done":true,"done_reason":"stop","context":[151644,105043,100165,30,151645,151648,271,151649,198,198,111308,6313,104198,67071,105538,102217,30918,50984,9909,33464,39350,7552,73218,100013,9370,100168,110498,33464,39350,12,49,16,1773,29524,87026,110117,99885,86119,3837,105351,99739,35946,111079,113445,100364,1773],"total_duration":3872978599,"load_duration":2811407308,"prompt_eval_count":6,"prompt_eval_duration":102000000,"eval_count":40,"eval_duration":958000000}

通過上述步驟，已經(jīng)成功在Linux服務(wù)器上配置了Ollama服務(wù)，并通過Mac遠(yuǎn)程訪問了DeepSeek模型。接下來，將介紹如何在Mac上安裝Web UI，以便更方便地與模型進(jìn)行交互。

3. 在Mac上安裝Web UI

為了更方便地與遠(yuǎn)程Linux服務(wù)器上的DeepSeek模型進(jìn)行交互，可以在Mac上安裝一個Web UI工具。這里我們推薦使用 Open Web UI，它是一個基于Web的界面，支持多種AI模型，包括Ollama。

1. 通過conda安裝open-webui

打開終端，運(yùn)行以下命令創(chuàng)建一個新的conda環(huán)境，并指定Python版本為3.11：

conda create -n open-webui-env python=3.11
conda activate open-webui-env
pip install open-webui

2. 啟動open-webui

open-webui serve

3. 瀏覽器訪問

http://localhost:8080/

使用管理員身份（第一個注冊用戶）登錄

在Open webui界面中，依次點(diǎn)擊“展開左側(cè)欄”（左上角三道杠）–>“頭像”（左下角）–>管理員面板–>設(shè)置（上側(cè)）–>外部連接

在外部連接的Ollama API一欄將switch開關(guān)打開，在欄中填上http://10.37.96.186:11434（這是我的服務(wù)器地址）

點(diǎn)擊右下角“保存”按鈕

點(diǎn)擊“新對話”（左上角），確定是否正確刷出模型列表，如果正確刷出，則設(shè)置完畢。

4. 愉快的使用本地deepseek模型

到此這篇關(guān)于在linux服務(wù)器本地部署Deepseek及在mac遠(yuǎn)程web-ui訪問的操作的文章就介紹到這了,更多相關(guān)linux 本地部署Deepseek內(nèi)容請搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章: