linux内网部署deepseek大模型（ollama+anythingllm）

一、安装ollama

来源：ollama/docs/linux.md at main · ollama/ollama · GitHub

1.下载安装包

ollama下载链接：https://ollama.com/download/ollama-linux-amd64.tgz，下载后放在用户目录下

2.运行脚本

#!/bin/sh
# This script installs Ollama on Linux.
# It detects the current operating system architecture and installs the appropriate version of Ollama.

set -eu

red="$( (/usr/bin/tput bold || :; /usr/bin/tput setaf 1 || :) 2>&-)"
plain="$( (/usr/bin/tput sgr0 || :) 2>&-)"

status() { echo ">>> $*" >&2; }
error() { echo "${red}ERROR:${plain} $*"; exit 1; }
warning() { echo "${red}WARNING:${plain} $*"; }

TEMP_DIR=$(mktemp -d)
cleanup() { rm -rf $TEMP_DIR; }
trap cleanup EXIT

available() { command -v $1 >/dev/null; }
require() {
    local MISSING=''
    for TOOL in $*; do
        if ! available $TOOL; then
            MISSING="$MISSING $TOOL"
        fi
    done

    echo $MISSING
}

[ "$(uname -s)" = "Linux" ] || error 'This script is intended to run on Linux only.'

ARCH=$(uname -m)
case "$ARCH" in
    x86_64) ARCH="amd64" ;;
    aarch64|arm64) ARCH="arm64" ;;
    *) error "Unsupported architecture: $ARCH" ;;
esac

IS_WSL2=false

KERN=$(uname -r)
case "$KERN" in
    *icrosoft*WSL2 | *icrosoft*wsl2) IS_WSL2=true;;
    *icrosoft) error "Microsoft WSL1 is not currently supported. Please use WSL2 with 'wsl --set-version <distro> 2'" ;;
    *) ;;
esac

VER_PARAM="${OLLAMA_VERSION:+?version=$OLLAMA_VERSION}"

SUDO=
if [ "$(id -u)" -ne 0 ]; then
    # Running as root, no need for sudo
    if ! available sudo; then
        error "This script requires superuser permissions. Please re-run as root."
    fi

    SUDO="sudo"
fi

NEEDS=$(require awk grep sed tee xargs)
if [ -n "$NEEDS" ]; then
    status "ERROR: The following tools are required but missing:"
    for NEED in $NEEDS; do
        echo "  - $NEED"
    done
    exit 1
fi

for BINDIR in /usr/local/bin /usr/bin /bin; do
    echo $PATH | grep -q $BINDIR && break || continue
done
OLLAMA_INSTALL_DIR=$(dirname ${BINDIR})

if [ -d "$OLLAMA_INSTALL_DIR/lib/ollama" ] ; then
    status "Cleaning up old version at $OLLAMA_INSTALL_DIR/lib/ollama"
    $SUDO rm -rf "$OLLAMA_INSTALL_DIR/lib/ollama"
fi
status "Installing ollama to $OLLAMA_INSTALL_DIR"
$SUDO install -o0 -g0 -m755 -d $BINDIR
$SUDO install -o0 -g0 -m755 -d "$OLLAMA_INSTALL_DIR"
status "Downloading Linux ${ARCH} bundle"
#curl --fail --show-error --location --progress-bar \
#    "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
$SUDO tar -xzf ollama-linux-amd64.tgz -C "$OLLAMA_INSTALL_DIR"
if [ "$OLLAMA_INSTALL_DIR/bin/ollama" != "$BINDIR/ollama" ] ; then
    status "Making ollama accessible in the PATH in $BINDIR"
    $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
fi

# Check for NVIDIA JetPack systems with additional downloads
if [ -f /etc/nv_tegra_release ] ; then
    if grep R36 /etc/nv_tegra_release > /dev/null ; then
        status "Downloading JetPack 6 components"
        #curl --fail --show-error --location --progress-bar \
        #    "https://ollama.com/download/ollama-linux-${ARCH}-jetpack6.tgz${VER_PARAM}" | \
        $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
    elif grep R35 /etc/nv_tegra_release > /dev/null ; then
        status "Downloading JetPack 5 components"
        #curl --fail --show-error --location --progress-bar \
        #    "https://ollama.com/download/ollama-linux-${ARCH}-jetpack5.tgz${VER_PARAM}" | \
        $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
    else
        warning "Unsupported JetPack version detected.  GPU may not be supported"
    fi
fi

install_success() {
    status 'The Ollama API is now available at 127.0.0.1:11434.'
    status 'Install complete. Run "ollama" from the command line.'
}
trap install_success EXIT

# Everything from this point onwards is optional.
configure_systemd() {
    if ! id ollama >/dev/null 2>&1; then
        status "Creating ollama user..."
        $SUDO useradd -r -s /bin/false -U -m -d /usr/share/ollama ollama
    fi
    if getent group render >/dev/null 2>&1; then
        status "Adding ollama user to render group..."
        $SUDO usermod -a -G render ollama
    fi
    if getent group video >/dev/null 2>&1; then
        status "Adding ollama user to video group..."
        $SUDO usermod -a -G video ollama
    fi

    status "Adding current user to ollama group..."
    $SUDO usermod -a -G ollama $(whoami)

    status "Creating ollama systemd service..."
    cat <<EOF | $SUDO tee /etc/systemd/system/ollama.service >/dev/null
[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=$BINDIR/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=$PATH"

[Install]
WantedBy=default.target
EOF
    SYSTEMCTL_RUNNING="$(systemctl is-system-running || true)"
    case $SYSTEMCTL_RUNNING in
        running|degraded)
            status "Enabling and starting ollama service..."
            $SUDO systemctl daemon-reload
            $SUDO systemctl enable ollama

            start_service() { $SUDO systemctl restart ollama; }
            trap start_service EXIT
            ;;
        *)
            warning "systemd is not running"
            if [ "$IS_WSL2" = true ]; then
                warning "see https://learn.microsoft.com/en-us/windows/wsl/systemd#how-to-enable-systemd to enable it"
            fi
            ;;
    esac
}

if available systemctl; then
    configure_systemd
fi

# WSL2 only supports GPUs via nvidia passthrough
# so check for nvidia-smi to determine if GPU is available
if [ "$IS_WSL2" = true ]; then
    if available nvidia-smi && [ -n "$(nvidia-smi | grep -o "CUDA Version: [0-9]*\.[0-9]*")" ]; then
        status "Nvidia GPU detected."
    fi
    install_success
    exit 0
fi

# Don't attempt to install drivers on Jetson systems
if [ -f /etc/nv_tegra_release ] ; then
    status "NVIDIA JetPack ready."
    install_success
    exit 0
fi

# Install GPU dependencies on Linux
if ! available lspci && ! available lshw; then
    warning "Unable to detect NVIDIA/AMD GPU. Install lspci or lshw to automatically detect and install GPU dependencies."
    exit 0
fi

check_gpu() {
    # Look for devices based on vendor ID for NVIDIA and AMD
    case $1 in
        lspci)
            case $2 in
                nvidia) available lspci && lspci -d '10de:' | grep -q 'NVIDIA' || return 1 ;;
                amdgpu) available lspci && lspci -d '1002:' | grep -q 'AMD' || return 1 ;;
            esac ;;
        lshw)
            case $2 in
                nvidia) available lshw && $SUDO lshw -c display -numeric -disable network | grep -q 'vendor: .* \[10DE\]' || return 1 ;;
                amdgpu) available lshw && $SUDO lshw -c display -numeric -disable network | grep -q 'vendor: .* \[1002\]' || return 1 ;;
            esac ;;
        nvidia-smi) available nvidia-smi || return 1 ;;
    esac
}

if check_gpu nvidia-smi; then
    status "NVIDIA GPU installed."
    exit 0
fi

3.验证是否安装成功

ollama -v

二、ollama加载本地模型文件

1.下载gguf格式模型

下载地址：DeepSeek-R1-Distill-Qwen-1.5B-GGUF · 模型库 (modelscope.cn)

2.在ollama中添加模型

准备本地Modelfile文件：

vi deepseek-r1.mf

内容如下：

FROM后面是模型路径

FROM /root/deepseek/models/DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.gguf

TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>{{ end }}<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"

这里可以多写多个FROM，加载多个模型。

加载模型：

ollama create deepseek-r1-1.5B -f deepseek-r1.mf

3.运行模型

ollama run DeepSeek-R1-1.5B

三、使用docker安装anythingllm

1.把镜像转移到内网

先下载镜像再打包：

docker pull --platform linux/arm64 mintplexlabs/anythingllm
docker save mintplexlabs/anythingllm -o /opt/anythingllm.tar

拷到内网，加载镜像：

docker load -i /opt/anythingllm.tar

2.启动anythingllm

创建docker要映射到本地的文件夹：

export STORAGE_LOCATION=$HOME/anythingllm && \
mkdir -p $STORAGE_LOCATION && \
touch "$STORAGE_LOCATION/.env" && \

运行docker服务：

docker run -d -p 3001:3001 \
--name anythingllm \
--cap-add SYS_ADMIN \
-v ${STORAGE_LOCATION}:/app/server/storage \
-v ${STORAGE_LOCATION}/.env:/app/server/.env \
-e STORAGE_DIR="/app/server/storage" \
mintplexlabs/anythingllm

查看log确认docker服务启动成功：

docker logs -f anythingllm

如果日志中出现报错：Assertion (0)==(uv_thread_create(t.get(), start_thread, this))failed

（1）停止删除docker容器：

docker stop anythingllm
docker rm anythingllm

（2）用以下命令启动anythingllm容器，这里比官方的多了个--privileged=true：

docker run -d -p 3001:3001 \
--name anythingllm \
--privileged=true \
--cap-add SYS_ADMIN \
-v ${STORAGE_LOCATION}:/app/server/storage \
-v ${STORAGE_LOCATION}/.env:/app/server/.env \
-e STORAGE_DIR="/app/server/storage" \
mintplexlabs/anythingllm

3.访问anythingllm

访问 http://localhost:3001，正常出现页面即为成功。