当前位置： 首页 > article >正文

离线环境如何玩转LLM？Ollama一键部署指南（Ubuntu）

article 2025/2/25 22:04:34

一、离线环境部署背景

有限的网络连接性：有些服务器所处的环境可能没有可靠或连续的网络连接，这时候离线部署就能确保服务器依然可以正常运行，而不需要依赖网络连接。

安全性考虑：一些组织对网络连接安全性要求非常高，不愿意服务器在外部网络上下载或更新软件。通过离线部署，可以避免潜在的网络安全风险。

降低网络成本：在一些地区网络连接成本较高，或者网络不稳定，离线部署可以避免频繁的网络通信和数据传输，节省网络费用。

加速部署过程：在一些场景下，通过离线部署可以加快服务器的部署速度，不需要等待软件或系统下载和安装，可以直接开始运行。

二、Ollama 离线安装（v0.3.12）

Step1、查看服务器CPU的型号

lscpu

Step2、根据CPU型号下载Ollama安装包

# x86_64 CPU选择下载ollama-linux-amd64
# aarch64|arm64 CPU选择下载ollama-linux-arm64
# 下载地址 https://github.com/ollama/ollama/releases/

https://github.com/ollama/ollama/releases/download/v0.3.12/ollama-linux-amd64.tgz

Step3、下载 Ollama 安装脚本

## 下载地址1，浏览器中打开下面地址
https://ollama.com/install.sh

## 下载地址2
https://github.com/ollama/ollama/blob/main/scripts/install.sh
## 国内加速可访问https://gitee.com/ai-big-model/ollama/blob/main/scripts/install.sh

install.sh 脚本如下：

## install.sh

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

set -eu

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

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=$(require curl awk grep sed tee xargs)
if [ -n "$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})

status "Installing ollama to $OLLAMA_INSTALL_DIR"
$SUDO install -o0 -g0 -m755 -d $BINDIR
$SUDO install -o0 -g0 -m755 -d "$OLLAMA_INSTALL_DIR"
if curl -I --silent --fail --location "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" >/dev/null ; then
    status "Downloading Linux ${ARCH} bundle"
    curl --fail --show-error --location --progress-bar \
        "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
        $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
    BUNDLE=1
    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
else
    status "Downloading Linux ${ARCH} CLI"
    curl --fail --show-error --location --progress-bar -o "$TEMP_DIR/ollama"\
    "https://ollama.com/download/ollama-linux-${ARCH}${VER_PARAM}"
    $SUDO install -o0 -g0 -m755 $TEMP_DIR/ollama $OLLAMA_INSTALL_DIR/ollama
    BUNDLE=0
    if [ "$OLLAMA_INSTALL_DIR/ollama" != "$BINDIR/ollama" ] ; then
        status "Making ollama accessible in the PATH in $BINDIR"
        $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
    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
            ;;
    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

# 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

if ! check_gpu lspci nvidia && ! check_gpu lshw nvidia && ! check_gpu lspci amdgpu && ! check_gpu lshw amdgpu; then
    install_success
    warning "No NVIDIA/AMD GPU detected. Ollama will run in CPU-only mode."
    exit 0
fi

if check_gpu lspci amdgpu || check_gpu lshw amdgpu; then
    if [ $BUNDLE -ne 0 ]; then
        status "Downloading Linux ROCm ${ARCH} bundle"
        curl --fail --show-error --location --progress-bar \
            "https://ollama.com/download/ollama-linux-${ARCH}-rocm.tgz${VER_PARAM}" | \
            $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"

        install_success
        status "AMD GPU ready."
        exit 0
    fi
    # Look for pre-existing ROCm v6 before downloading the dependencies
    for search in "${HIP_PATH:-''}" "${ROCM_PATH:-''}" "/opt/rocm" "/usr/lib64"; do
        if [ -n "${search}" ] && [ -e "${search}/libhipblas.so.2" -o -e "${search}/lib/libhipblas.so.2" ]; then
            status "Compatible AMD GPU ROCm library detected at ${search}"
            install_success
            exit 0
        fi
    done

    status "Downloading AMD GPU dependencies..."
    $SUDO rm -rf /usr/share/ollama/lib
    $SUDO chmod o+x /usr/share/ollama
    $SUDO install -o ollama -g ollama -m 755 -d /usr/share/ollama/lib/rocm
    curl --fail --show-error --location --progress-bar "https://ollama.com/download/ollama-linux-amd64-rocm.tgz${VER_PARAM}" \
        | $SUDO tar zx --owner ollama --group ollama -C /usr/share/ollama/lib/rocm .
    install_success
    status "AMD GPU ready."
    exit 0
fi

CUDA_REPO_ERR_MSG="NVIDIA GPU detected, but your OS and Architecture are not supported by NVIDIA.  Please install the CUDA driver manually https://docs.nvidia.com/cuda/cuda-installation-guide-linux/"
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-7-centos-7
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-8-rocky-8
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-9-rocky-9
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#fedora
install_cuda_driver_yum() {
    status 'Installing NVIDIA repository...'
    
    case $PACKAGE_MANAGER in
        yum)
            $SUDO $PACKAGE_MANAGER -y install yum-utils
            if curl -I --silent --fail --location "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-$1$2.repo" >/dev/null ; then
                $SUDO $PACKAGE_MANAGER-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-$1$2.repo
            else
                error $CUDA_REPO_ERR_MSG
            fi
            ;;
        dnf)
            if curl -I --silent --fail --location "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-$1$2.repo" >/dev/null ; then
                $SUDO $PACKAGE_MANAGER config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-$1$2.repo
            else
                error $CUDA_REPO_ERR_MSG
            fi
            ;;
    esac

    case $1 in
        rhel)
            status 'Installing EPEL repository...'
            # EPEL is required for third-party dependencies such as dkms and libvdpau
            $SUDO $PACKAGE_MANAGER -y install https://dl.fedoraproject.org/pub/epel/epel-release-latest-$2.noarch.rpm || true
            ;;
    esac

    status 'Installing CUDA driver...'

    if [ "$1" = 'centos' ] || [ "$1$2" = 'rhel7' ]; then
        $SUDO $PACKAGE_MANAGER -y install nvidia-driver-latest-dkms
    fi

    $SUDO $PACKAGE_MANAGER -y install cuda-drivers
}

# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#ubuntu
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#debian
install_cuda_driver_apt() {
    status 'Installing NVIDIA repository...'
    if curl -I --silent --fail --location "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-keyring_1.1-1_all.deb" >/dev/null ; then
        curl -fsSL -o $TEMP_DIR/cuda-keyring.deb https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-keyring_1.1-1_all.deb
    else
        error $CUDA_REPO_ERR_MSG
    fi

    case $1 in
        debian)
            status 'Enabling contrib sources...'
            $SUDO sed 's/main/contrib/' < /etc/apt/sources.list | $SUDO tee /etc/apt/sources.list.d/contrib.list > /dev/null
            if [ -f "/etc/apt/sources.list.d/debian.sources" ]; then
                $SUDO sed 's/main/contrib/' < /etc/apt/sources.list.d/debian.sources | $SUDO tee /etc/apt/sources.list.d/contrib.sources > /dev/null
            fi
            ;;
    esac

    status 'Installing CUDA driver...'
    $SUDO dpkg -i $TEMP_DIR/cuda-keyring.deb
    $SUDO apt-get update

    [ -n "$SUDO" ] && SUDO_E="$SUDO -E" || SUDO_E=
    DEBIAN_FRONTEND=noninteractive $SUDO_E apt-get -y install cuda-drivers -q
}

if [ ! -f "/etc/os-release" ]; then
    error "Unknown distribution. Skipping CUDA installation."
fi

. /etc/os-release

OS_NAME=$ID
OS_VERSION=$VERSION_ID

PACKAGE_MANAGER=
for PACKAGE_MANAGER in dnf yum apt-get; do
    if available $PACKAGE_MANAGER; then
        break
    fi
done

if [ -z "$PACKAGE_MANAGER" ]; then
    error "Unknown package manager. Skipping CUDA installation."
fi

if ! check_gpu nvidia-smi || [ -z "$(nvidia-smi | grep -o "CUDA Version: [0-9]*\.[0-9]*")" ]; then
    case $OS_NAME in
        centos|rhel) install_cuda_driver_yum 'rhel' $(echo $OS_VERSION | cut -d '.' -f 1) ;;
        rocky) install_cuda_driver_yum 'rhel' $(echo $OS_VERSION | cut -c1) ;;
        fedora) [ $OS_VERSION -lt '39' ] && install_cuda_driver_yum $OS_NAME $OS_VERSION || install_cuda_driver_yum $OS_NAME '39';;
        amzn) install_cuda_driver_yum 'fedora' '37' ;;
        debian) install_cuda_driver_apt $OS_NAME $OS_VERSION ;;
        ubuntu) install_cuda_driver_apt $OS_NAME $(echo $OS_VERSION | sed 's/\.//') ;;
        *) exit ;;
    esac
fi

if ! lsmod | grep -q nvidia || ! lsmod | grep -q nvidia_uvm; then
    KERNEL_RELEASE="$(uname -r)"
    case $OS_NAME in
        rocky) $SUDO $PACKAGE_MANAGER -y install kernel-devel kernel-headers ;;
        centos|rhel|amzn) $SUDO $PACKAGE_MANAGER -y install kernel-devel-$KERNEL_RELEASE kernel-headers-$KERNEL_RELEASE ;;
        fedora) $SUDO $PACKAGE_MANAGER -y install kernel-devel-$KERNEL_RELEASE ;;
        debian|ubuntu) $SUDO apt-get -y install linux-headers-$KERNEL_RELEASE ;;
        *) exit ;;
    esac

    NVIDIA_CUDA_VERSION=$($SUDO dkms status | awk -F: '/added/ { print $1 }')
    if [ -n "$NVIDIA_CUDA_VERSION" ]; then
        $SUDO dkms install $NVIDIA_CUDA_VERSION
    fi

    if lsmod | grep -q nouveau; then
        status 'Reboot to complete NVIDIA CUDA driver install.'
        exit 0
    fi

    $SUDO modprobe nvidia
    $SUDO modprobe nvidia_uvm
fi

# make sure the NVIDIA modules are loaded on boot with nvidia-persistenced
if available nvidia-persistenced; then
    $SUDO touch /etc/modules-load.d/nvidia.conf
    MODULES="nvidia nvidia-uvm"
    for MODULE in $MODULES; do
        if ! grep -qxF "$MODULE" /etc/modules-load.d/nvidia.conf; then
            echo "$MODULE" | $SUDO tee -a /etc/modules-load.d/nvidia.conf > /dev/null
        fi
    done
fi

status "NVIDIA GPU ready."
install_success

Step4、修改install.sh脚本

Ollama 安装包与安装脚本放在同一个目录下，总共需要修改两个点：

  1. Ollama下载地址
  2. Ollama安装包存放目录

第一处修改，注释下载链接

status "Downloading ollama..."
## 在install.sh的第65行
#curl --fail --show-error --location --progress-bar -o $TEMP_DIR/ollama "https://ollama.com/download/ollama-linux-${ARCH}${VER_PARAM}"

第二处修改，修改ollama安装目录

status "Installing ollama to $BINDIR..."
$SUDO install -o0 -g0 -m755 -d $BINDIR
## 在install.sh的第73行
#$SUDO install -o0 -g0 -m755 $TEMP_DIR/ollama $BINDIR/ollama
$SUDO install -o0 -g0 -m755 ./ollama-linux-amd64  $BINDIR/ollama
status "Installing ollama to $OLLAMA_INSTALL_DIR"
$SUDO install -o0 -g0 -m755 -d $BINDIR
$SUDO install -o0 -g0 -m755 -d "$OLLAMA_INSTALL_DIR"

LOCAL_OLLAMA_TGZ="/path/to/your/local/ollama-linux-${ARCH}.tgz"  # 修改此行，指定本地文件路径

if [ -f "$LOCAL_OLLAMA_TGZ" ]; then
    status "Using local Linux ${ARCH} bundle"
    $SUDO tar -xzf "$LOCAL_OLLAMA_TGZ" -C "$OLLAMA_INSTALL_DIR"
    BUNDLE=1
    if [ "$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
else
    status "Local file $LOCAL_OLLAMA_TGZ not found"
    exit 1
fi

#if curl -I --silent --fail --location "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" >/dev/null ; then
#    status "Downloading Linux ${ARCH} bundle"
#    curl --fail --show-error --location --progress-bar \
#        "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
#        $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
#    BUNDLE=1
#    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
#else
#    status "Downloading Linux ${ARCH} CLI"
#    curl --fail --show-error --location --progress-bar -o "$TEMP_DIR/ollama"\
#    "https://ollama.com/download/ollama-linux-${ARCH}${VER_PARAM}"
#    $SUDO install -o0 -g0 -m755 $TEMP_DIR/ollama $OLLAMA_INSTALL_DIR/ollama
#    BUNDLE=0
#    if [ "$OLLAMA_INSTALL_DIR/ollama" != "$BINDIR/ollama" ] ; then
#        status "Making ollama accessible in the PATH in $BINDIR"
#        $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
#    fi
#fi

Step5、执行install.sh脚本

运行 install.sh 脚本，开始安装 ollama

# 执行installl.sh脚本，需要sudo 权限  chmod +x install.sh
./install.sh
# 如果报错误权限不足，执行
chmod +x install.sh
# 如果报错误： bash: ./build_android.sh：/bin/sh^M：解释器错误: 没有那个文件或目录，执行
sed -i 's/\r$//' install.sh

Step6、配置大模型下载目录

# 执行命令
vim ~/.bashrc
# 配置 OLLAMA_MODELS 环境变量自定义路径
### ollama model dir 改为自定义的路径，默认路径/usr/share/ollama/.ollama/models 
export OLLAMA_MODELS=/data/ollama_cache
# 复制/usr/share/ollama/.ollama/models目录中（blobs  manifests）的文件夹到OLLAMA_MODELS环境变量目录
sudo cp -r /usr/share/ollama/.ollama/models /data/ollama_cache

Step7、运行大模型

如通义千问

# 需要先将大模型下载到OLLAMA_MODELS文件中
# ollama run <模型名称>
ollama run qwen

Step8、关闭 Ollama 服务

service ollama stop

三、离线部署 llama 3.1 70b

Step1、下载模型

国内大模型源文件下载地址 https://modelscope.cn/models

国外大模型源文件下载地址https://huggingface.co/models

下载 Meta-Llama-3.1-70B-Instruct 模型到本地机器，

Step2、上传模型

使用 ftp 把模型文件从本地上传到服务器，

Step3、创建 Modelfile

# 创建一个名为  llama-3.1-70b.Modelfile 的文件，内容如下：
FROM ./llama-3.1-70b

TEMPLATE """{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
{{- if .System }}

{{ .System }}
{{- end }}
{{- if .Tools }}

Cutting Knowledge Date: December 2023

When you receive a tool call response, use the output to format an answer to the orginal user question.

You are a helpful assistant with tool calling capabilities.
{{- end }}<|eot_id|>
{{- end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 }}
{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
{{- if and $.Tools $last }}

Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.

Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.

{{ range $.Tools }}
{{- . }}
{{ end }}
Question: {{ .Content }}<|eot_id|>
{{- else }}

{{ .Content }}<|eot_id|>
{{- end }}{{ if $last }}<|start_header_id|>assistant<|end_header_id|>

{{ end }}
{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
{{- if .ToolCalls }}
{{ range .ToolCalls }}
{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
{{- else }}

{{ .Content }}
{{- end }}{{ if not $last }}<|eot_id|>{{ end }}
{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>

{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>

{{ end }}
{{- end }}
{{- end }}
"""

PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"

FROM (必需的) 引入使用的模型或者模型源文件

PARAMETER(参数) 设置大模型的运行参数

TEMPLATE(提示词模板) 用于大模型请求的prompt提示词模板

SYSTEM 设置的大模型默认的系统消息

ADAPTER 定义适用于模型的（Q）LoRA适配器

LICENSE 指定license.

MESSAGE 指定消息历史

不同模型的 Modelfile 内容不同，可参考 Ollama 官网 参数设置

https://github.com/ollama/ollama/blob/main/docs/modelfile.md

Step4、创建模型

ollama create <your-model-name> -f <./Modelfile>
# 创建存储大模型源文件和modelfile文件的目录
sudo mkdir /data/modelfiles

# 上传文件模型到 /data/modelfiles/llama-3.1-70b/ 
# 上传 llama-3.1-70b-Modelfile /data/modelfiles/

# 进入工作目录
cd /data/modelfiles

# 执行创建命令
ollama create llama3.1:70b -f ./llama-3.1-70b.Modelfile

# 查看创建结果
ollama list

Docker 存储路径跟 /tmp 路径都爆了，先改下 docker 存储路径，

sudo systemctl stop docker


sudo mkdir -p /etc/docker

sudo vim /etc/docker/daemon.json

{
  "data-root": "/data/docker"
}


sudo mv /var/lib/docker /data/docker

sudo systemctl start docker


docker info | grep "Docker Root Dir"

 修改 tmp 临时路径，

https://github.com/ollama/ollama/issues/5026
https://ollama.fan/resources/troubleshooting/#llm-libraries
https://ollama.qianniu.city/doc/Ollama%20%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98%E8%A7%A3%E7%AD%94.html

-- 方法一
# 执行命令
sudo vim ~/.bashrc
# 配置 OLLAMA_TMPDIR 环境变量自定义路径
### ollama tmpdir 改为自定义的路径，默认路径 /tmp 
export OLLAMA_TMPDIR=/data/tmp
# 关键点：变量改这个
export TMPDIR=/data/tmp

# 刷新配置
source ~/.bashrc

sudo systemctl daemon-reload
sudo systemctl restart ollama.service
sudo systemctl status ollama


--- 方法二
# sudo systemctl edit ollama.service
sudo vim /etc/systemd/system/ollama.service

[Service]
Environment="OLLAMA_TMPDIR=/data/tmp"
Environment="OLLAMA_MODELS=/data/ollama_cache"
Environment="TMPDIR=/data/tmp"
Environment="TEMP=/data/tmp"

cd /data
sudo chown -R ollama:ollama tmp
sudo chown -R ollama:ollama ollama_cache


sudo systemctl daemon-reload
sudo systemctl restart ollama

 启动报错，看了日志发现没权限，

# 查看日志
# journalctl -u ollama

sudo chmod -R 777 /data/ollama_cache/blobs
sudo chmod -R 777 /data/tmp

重新创建模型，ok，

Step5、运行模型

ollama run <your-model-name>
# 运行步骤3创建的llama3.1:70b大模型
sudo ollama run llama3.1:70b

# 退出命令
/bye

Step6、GPU 启用

如果您的系统中有多个 NVIDIA GPU 并且希望限制 Ollama 使用的子集，您可以将 CUDA_VISIBLE_DEVICES 设置为 GPU 的逗号分隔列表。可以使用数字 ID，但顺序可能会变化，因此 UUID 更可靠。您可以通过运行 nvidia-smi -L 来发现您的 GPU 的 UUID。如果您想忽略 GPU 并强制使用 CPU，请使用无效的 GPU ID（例如，“-1”）

# 查看 GPG
nvidia-smi -L

GPU 0: NVIDIA GeForce RTX 4090 (UUID: GPU-d52b63db-f09a-042f-57b7-37821b0ef749)
GPU 1: NVIDIA GeForce RTX 4090 (UUID: GPU-1b105eed-99be-b347-62bb-1d71b4e1daa3)
GPU 2: NVIDIA GeForce RTX 4090 (UUID: GPU-3ef73b84-a087-d6ea-b607-55797c2058ea)
GPU 3: NVIDIA GeForce RTX 4090 (UUID: GPU-4f8c7d53-5352-f22a-a477-00022499a1da)
GPU 4: NVIDIA GeForce RTX 4090 (UUID: GPU-0d24d3af-14ba-1663-911f-7be082ec3991)
GPU 5: NVIDIA GeForce RTX 4090 (UUID: GPU-81e7f2e2-3461-b33a-5c38-a5ba0cd6f2c4)
GPU 6: NVIDIA GeForce RTX 4090 (UUID: GPU-38529f01-1ebd-222e-8d5b-dd2d0ccd4aac)
GPU 7: NVIDIA GeForce RTX 4090 (UUID: GPU-c25feb89-f89d-afe8-263c-d7887b3b7c31)


#  journalctl -u ollama

# 修改到 2m0s 减少 GPU 占用
# OLLAMA_KEEP_ALIVE:5m0s

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

[Service]
...
Environment="CUDA_VISIBLE_DEVICES=GPU-d52b63db-f09a-042f-57b7-37821b0ef749,GPU-1b105eed-99be-b347-62bb-1d71b4e1daa3,GPU-3ef73b84-a087-d6ea-b607-55797c2058ea,GPU-4f8c7d53-5352-f22a-a477-00022499a1da,GPU-0d24d3af-14ba-1663-911f-7be082ec3991,GPU-81e7f2e2-3461-b33a-5c38-a5ba0cd6f2c4,GPU-38529f01-1ebd-222e-8d5b-dd2d0ccd4aac,GPU-c25feb89-f89d-afe8-263c-d7887b3b7c31"
Environment="OLLAMA_KEEP_ALIVE=2m0s"

sudo systemctl daemon-reload
sudo systemctl restart ollama


http://www.kler.cn/a/560884.html

相关文章：

  • Redis 集群的三种模式：一主一从、一主多从和多主多从
  • 【linux】全志t113平台修改ota升级配置文件，定向选择升级分区
  • AI赋能市场预测：ScriptEcho如何提升数据可视化效率
  • 自由学习记录（38）
  • 自动驾驶之BEV概述
  • 【UCB CS 61B SP24】Lecture 11 - Inheritance 4: Iterators, Object Methods学习笔记
  • 浅析 DeepSeek 开源的 FlashMLA 项目
  • 从三个维度了解 RPC（Remote Procedure Call，远程过程调用）
  • 算法打卡第十二弹——二叉树
  • Unity 协程
  • 【NLP 26、实践 ⑥ 引入bert，判断文本中是否有特定字符出现】
  • Linux 命令大全完整版（12）
  • 论文笔记：Scaling Sentence Embeddings with Large Language Models
  • 服务器能否拒绝非浏览器发起的HTTP请求？
  • 0224-leetcode-459.重复的子字符串、283. 移动零
  • unity学习53：UI的子容器：面板panel
  • 【网络安全】从零开始的CTF生活
  • 一文讲解Redis中的基本数据类型
  • postman并发测试某个接口
  • 计算机毕业设计SpringBoot+Vue.jst在线文档管理系统(源码+LW文档+PPT+讲解)