ollama自定义模型容器部署（cpu版）

    docker pull ollama/ollama  # 约1.98G

    # 前一个11435是宿主机要对外暴露的tcp端口，可自定义修改
    docker run -d -p 11435:11434 --name ollama ollama/ollama

    FROM Qwen2.5-3B-Instruct-Q4_K_L.gguf
    
    # set the temperature to 1 [higher is more creative, lower is more coherent]
    PARAMETER temperature 0.7
    PARAMETER top_p 0.8
    PARAMETER repeat_penalty 1.05
    PARAMETER top_k 20
    
    TEMPLATE """{{ if .Messages }}
    {{- if or .System .Tools }}<|im_start|>system
    {{ .System }}
    {{- if .Tools }}
    
    # Tools
    
    You are provided with function signatures within <tools></tools> XML tags:
    <tools>{{- range .Tools }}
    {"type": "function", "function": {{ .Function }}}{{- end }}
    </tools>
    
    For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
    <tool_call>
    {"name": <function-name>, "arguments": <args-json-object>}
    </tool_call>
    {{- end }}<|im_end|>
    {{ end }}
    {{- range $i, $_ := .Messages }}
    {{- $last := eq (len (slice $.Messages $i)) 1 -}}
    {{- if eq .Role "user" }}<|im_start|>user
    {{ .Content }}<|im_end|>
    {{ else if eq .Role "assistant" }}<|im_start|>assistant
    {{ if .Content }}{{ .Content }}
    {{- else if .ToolCalls }}<tool_call>
    {{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
    {{ end }}</tool_call>
    {{- end }}{{ if not $last }}<|im_end|>
    {{ end }}
    {{- else if eq .Role "tool" }}<|im_start|>user
    <tool_response>
    {{ .Content }}
    </tool_response><|im_end|>
    {{ end }}
    {{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
    {{ end }}
    {{- end }}
    {{- else }}
    {{- if .System }}<|im_start|>system
    {{ .System }}<|im_end|>
    {{ end }}{{ if .Prompt }}<|im_start|>user
    {{ .Prompt }}<|im_end|>
    {{ end }}<|im_start|>assistant
    {{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
    
    # set the system message
    SYSTEM """You are Qwen, created by Alibaba Cloud. You are a helpful assistant."""
    
    
    
![](https://ad.itadn.com/c/weblog/blog-img/images/2025-08-16/hsK3HeJyfvjoCwBqA05uTgO9idSr.png)

    # 提前下载好Qwen2.5-3B-Instruct-Q4_K_L.gguf
    # https://hf-mirror.com/bartowski/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q4_K_L.gguf
    docker cp Qwen2.5-3B-Instruct-Q4_K_L.gguf ollama:/root
    # 复制模型注册文件
    docker cp Modelfile ollama:/root

    docker exec -it ollama bash  # 进入容器
    cd /root
    ls  # 查看当前目录 应该存在 Qwen2.5-3B-Instruct-Q4_K_L.gguf 和 Modelfile
    ollama create qwen2.5_3b -f Modelfile  # 模型名称这里可以自定义
    ollama list  # 查看注册模型 应该可以看到qwen2.5_3b

    # linxu可以使用以下curl命令
    curl --location --request POST 'http://127.0.0.1:11435/v1/chat/completions' \
    --header 'Content-Type: application/json' \
    --data '{
    "model": "qwen2.5_3b",
    "messages": [
        {
        "role": "user",
        "content": "你好"
        }
    ],
    "stream": false
    }'
    
    # windows可以在cmd中使用以下curl命令
    curl --request POST "http://127.0.0.1:11435/v1/chat/completions" --header "Content-Type: application/json" --data-raw "{\"model\": \"qwen2.5_3b\",\"messages\": [{\"role\": \"user\",\"content\": \"你好\"}],\"stream\": false}"
    
    
    
![](https://ad.itadn.com/c/weblog/blog-img/images/2025-08-16/TAmz6dWYNKVUcpaJtbn50fr9MoXv.png)

    docker commit ollama qwen2.5-3b_image:v1  # v1为自定义版本号
    docker save -o qwen2.5-3b_image_image_v1.tar qwen2.5-3b_image:v1  # 保存为镜像文件

    zip qwen2.5-3b_image_image_v1.zip qwen2.5-3b_image_image_v1.tar  # 将tar压缩成zip文件，减小体积
    unzip qwen2.5-3b_image_image_v1.zip  # 将zip解压缩成tar文件

    split -b 3G qwen2.5-3b_image_image_v1.tar qwen2.5-3b_image_  # 切割成 my_ollama_image_aa、my_ollama_image_ab、my_ollama_image_ac
    cat qwen2.5-3b_image_* > qwen2.5-3b_image_image_v1.tar  # 将 my_ollama_image_* 多个文件合并成 my_ollama_image_v1.tar
    # windows cmd命令
    # copy /b qwen2.5-3b_image_aa + qwen2.5-3b_image_ab + qwen2.5-3b_image_ac qwen2.5-3b_image_image_v1.tar

    docker load -i qwen2.5-3b_image_image_v1.tar  # 在terminal或cmd(windows)等终端中命令

    # 前台测试
    docker run --rm -p 11435:11434 --name my_ollama qwen2.5-3b_image:v1
    
    # 后台
    docker run -d -p 11435:11434 --name my_ollama qwen2.5-3b_image:v1