Ollama私有化部署大语言模型LLM（上）
目录
一、Ollama介绍
二、安装Ollama
1、标准安装
2、国内加速
三、升级Ollama版本
四、使用Ollama
1、启动ollama服务
systemctl start ollama.service
ollama serve
2、使用ollama命令
ollama run 运行模型
ollama ps 查看正在运行的模型
ollama list 查看已有(已下载)的模型
ollama show 查看已有(已下载)模型信息
五、通过http访问Ollama
1、列出本地已有的模型tag
2、列出本正在运行的模型
3、展示模型详细信息
4、模型推理（生成内容）
generate接口
chat接口
5、可复现回答
6、覆盖默认的system指令
7、携带上下文
8、删除模型
五、查看Ollama服务日志
一、Ollama介绍
Ollama（官方网址：https://ollama.com/）是一个开源的大型语言模型（LLM）服务工具，旨在简化在本地环境中部署和运行这些模型的过程。它支持多种操作系统，包括Windows、macOS和Linux，并且可以通过Docker容器进行管理。Ollama封装了llama.cpp库，并提供与OpenAI兼容的API，支持多种语言模型如Llama 3、Mistral和Gemma。此外，Ollama还支持并行请求和多线程操作，提高了效率。用户可以通过简单的命令行工具或Web界面（Open WebUI、Hollama等）来管理和运行模型。Ollama采用了docker技术以实现简化使用，所以使用ollama命令风格类似docker。
同时，Ollama提供了官方的模型registry中心（网站：https://www.ollama.com/models），上面是官方提供的模型列表（其地位类似于docker的DockerHub）。
二、安装Ollama
1、标准安装
本文以Linux为例，如下图官网，通过一行命令一键完成Linux上完成安装。该句命令的作用是：通过curl从网上获取install.sh并输出至stdout（不将该install.sh保存至本地文件），然后通过sh执行。
除了一键安装，还可以通过下方的“View script source”查看install.sh的内容。可以通过“Manual install instructions”将install.sh中的各步骤通过手工一步步执行，而不是一键完成安装。
注意：需具有sudo权限的普通用户或者root用户执行安装命令。
安装目标目录的基目录为“/usr/local/” 或 “/usr/” 或 “/” 目录下（具体看安装时提示），在基目录下的：
- bin/ollama文件，为可执行文件
- lib/ollama子目录，为所需的lib库。
一键安装会：创建一个ollama用户，还会自动纳入Linux服务管理以随Linux启动而启动；若存在Nvidia GPU硬件则还会安装CUDA等。
2、国内加速
在标准安装的install.sh中，会自动根据当前Linux平台通过“https://ollama.com/download/文件名”下载安装所需的tgz文件（该URL实际最终会通过“https://github.com/ollama/ollama/releases/latest/download/文件名”下载），所需下载的tgz文件大约1~2GB。
然而国内访问github速度通常几百KB/s比较慢，可以通过文件加速器网站下载。下面以加速器网站“https://github.xzc888.top”为例加速（也可使用其他加速器网站），使用该加速器网站的方法是将URL中的“github.com”替换为“github.xzc888.top”。具体安装ollama过程如下：
#将脚本下载，并保存至本地。保存的文件名为“install_ollama.sh”
curl -fsSL https://ollama.com/install.sh -o install_ollama.sh#将该文件中的下载URL前缀替换为加速后的URL前缀
sed -i 's#https://ollama.com/download/#https://github.xzc888.top/ollama/ollama/releases/latest/download/#g' install_ollama.sh#执行ollama安装
sh install_ollama.sh#最后删除临时sh脚本
rm install_ollama.sh
三、升级Ollama版本
若Linux中已经安装ollama，希望升级新版ollama软件，怎么办？
只需再次执行以上安装步骤即可。
四、使用Ollama
类似docker，安装完ollama后需要先启动ollama服务端，然后才能通过命令操作。
1、启动ollama服务
启动ollama服务(服务侧)可以通过：
-
systemctl start ollama.service
通过Linux服务启动，该启动将会使用ollama用户运行进程。该方式启动默认使用/usr/share/ollama/.ollama/models目录作为存放模型的目录。
另：ollama服务通过OLLAMA_HOST环境确定服务侦听，该环境变量默认为127.0.0.1:11434，所以只能供本机访问。为了让其他机器访问也能访问ollama服务。编辑/etc/systemd/system/ollama.service文件，对Environment增加设置OLLAMA_HOST环境变量，如下
然后执行：systemctl daemon-reload; systemctl restart ollama.service 使其生效。
-
ollama serve
直接通过ollama命令启动，该启动方式默认使用启动命令用户的~/.ollama/models目录作为存放模型的目录。
附：ollama服务通过OLLAMA_HOST环境确定服务侦听，该环境变量默认为127.0.0.1:11434，所以只能供本机访问。为了让其他机器访问也能访问ollama服务。先在Linux中设置环境变量export OLLAMA_HOST=0.0.0.0:11434，然后再启动ollama服务。
2、使用ollama命令
除了ollama serve命令为服务侧命令外，其他命令为ollama客户端侧命令。如下（每个命令有对应的环境变量，具体通过命令加--help查看）。
客户端命令通过OLLAMA_HOST环境变量指定ollama服务所在的IP和端口，该环境变量默认为127.0.0.1:11434，可在使用时修改环境变量。
- create Create a model from a Modelfile
- show Show information for a model
- run Run a model
- stop Stop a running model
- pull Pull a model from a registry
- push Push a model to a registry
- list List models
- ps List running models
- cp Copy a model
- rm Remove a model
ollama run 运行模型
使用以下命令运行模型（若本地没有该模型，则自动从ollama官网获取）：
#运行模型（若本地没有该模型，则自动从ollama官网获取）
ollama run qwen2.5-coder
#或者增加--verbose，显示应答耗时、消耗token、token速度等信息
ollama run --verbose qwen2.5-coder
运行后，自动进入输入prompt对话框。如下：
还可以通过斜杠命令，查看模型信息/提示词模版等等。如下：
ollama ps 查看正在运行的模型
ollama list 查看已有(已下载)的模型
ollama show 查看已有(已下载)模型信息
五、通过http访问Ollama
模型提供多个http接口供访问，通过http可以完整使用大模型功能。下面以curl工具进行演示。
1、列出本地已有的模型tag
curl http://localhost:11434/api/tags返回结果（已经格式化排版）如下：
{"models": [{"name": "qwen2.5-coder:latest","model": "qwen2.5-coder:latest","modified_at": "2025-01-09T08:43:12.893109668+08:00","size": 4683087519,"digest": "2b0496514337a3d5901f1d253d01726c890b721e891335a56d6e08cedf3e2cb0","details": {"parent_model": "","format": "gguf","family": "qwen2","families": ["qwen2"],"parameter_size": "7.6B","quantization_level": "Q4_K_M"}}, {"name": "qwen2.5-coder:0.5b","model": "qwen2.5-coder:0.5b","modified_at": "2025-01-08T19:32:09.640283014+08:00","size": 531081760,"digest": "d392ed348d5bb7847eaefe3fcb18e5bcc6433aecb68bf61b6e028d87292ab54f","details": {"parent_model": "","format": "gguf","family": "qwen2","families": ["qwen2"],"parameter_size": "494.03M","quantization_level": "Q8_0"}}]
}
2、列出本正在运行的模型
curl http://localhost:11434/api/ps返回结果（已经格式化排版）如下：
{"models": [{"name": "qwen2.5-coder:0.5b","model": "qwen2.5-coder:0.5b","size": 958830592,"digest": "d392ed348d5bb7847eaefe3fcb18e5bcc6433aecb68bf61b6e028d87292ab54f","details": {"parent_model": "","format": "gguf","family": "qwen2","families": ["qwen2"],"parameter_size": "494.03M","quantization_level": "Q8_0"},"expires_at": "2025-01-09T14:31:47.581505612+08:00","size_vram": 0}]
}3、展示模型详细信息
curl -X POST http://localhost:11434/api/show -d '{"name": "qwen2.5-coder:0.5b","verbose": false
}'返回结果（已经格式化排版）如下（如果开启verbose信息会更多）
{"license": "\n Apache License\n Version 2.0, January 2004\n http://www.apache.org/licenses/\n\n TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n 1. Definitions.\n\n \"License\" shall mean the terms and conditions for use, reproduction,\n and distribution as defined by Sections 1 through 9 of this document.\n\n \"Licensor\" shall mean the copyright owner or entity authorized by\n the copyright owner that is granting the License.\n\n \"Legal Entity\" shall mean the union of the acting entity and all\n other entities that control, are controlled by, or are under common\n control with that entity. For the purposes of this definition,\n \"control\" means (i) the power, direct or indirect, to cause the\n direction or management of such entity, whether by contract or\n otherwise, or (ii) ownership of fifty percent (50%) or more of the\n outstanding shares, or (iii) beneficial ownership of such entity.\n\n \"You\" (or \"Your\") shall mean an individual or Legal Entity\n exercising permissions granted by this License.\n\n \"Source\" form shall mean the preferred form for making modifications,\n including but not limited to software source code, documentation\n source, and configuration files.\n\n \"Object\" form shall mean any form resulting from mechanical\n transformation or translation of a Source form, including but\n not limited to compiled object code, generated documentation,\n and conversions to other media types.\n\n \"Work\" shall mean the work of authorship, whether in Source or\n Object form, made available under the License, as indicated by a\n copyright notice that is included in or attached to the work\n (an example is provided in the Appendix below).\n\n \"Derivative Works\" shall mean any work, whether in Source or Object\n form, that is based on (or derived from) the Work and for which the\n editorial revisions, annotations, elaborations, or other modifications\n represent, as a whole, an original work of authorship. For the purposes\n of this License, Derivative Works shall not include works that remain\n separable from, or merely link (or bind by name) to the interfaces of,\n the Work and Derivative Works thereof.\n\n \"Contribution\" shall mean any work of authorship, including\n the original version of the Work and any modifications or additions\n to that Work or Derivative Works thereof, that is intentionally\n submitted to Licensor for inclusion in the Work by the copyright owner\n or by an individual or Legal Entity authorized to submit on behalf of\n the copyright owner. For the purposes of this definition, \"submitted\"\n means any form of electronic, verbal, or written communication sent\n to the Licensor or its representatives, including but not limited to\n communication on electronic mailing lists, source code control systems,\n and issue tracking systems that are managed by, or on behalf of, the\n Licensor for the purpose of discussing and improving the Work, but\n excluding communication that is conspicuously marked or otherwise\n designated in writing by the copyright owner as \"Not a Contribution.\"\n\n \"Contributor\" shall mean Licensor and any individual or Legal Entity\n on behalf of whom a Contribution has been received by Licensor and\n subsequently incorporated within the Work.\n\n 2. Grant of Copyright License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n copyright license to reproduce, prepare Derivative Works of,\n publicly display, publicly perform, sublicense, and distribute the\n Work and such Derivative Works in Source or Object form.\n\n 3. Grant of Patent License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n (except as stated in this section) patent license to make, have made,\n use, offer to sell, sell, import, and otherwise transfer the Work,\n where such license applies only to those patent claims licensable\n by such Contributor that are necessarily infringed by their\n Contribution(s) alone or by combination of their Contribution(s)\n with the Work to which such Contribution(s) was submitted. If You\n institute patent litigation against any entity (including a\n cross-claim or counterclaim in a lawsuit) alleging that the Work\n or a Contribution incorporated within the Work constitutes direct\n or contributory patent infringement, then any patent licenses\n granted to You under this License for that Work shall terminate\n as of the date such litigation is filed.\n\n 4. Redistribution. You may reproduce and distribute copies of the\n Work or Derivative Works thereof in any medium, with or without\n modifications, and in Source or Object form, provided that You\n meet the following conditions:\n\n (a) You must give any other recipients of the Work or\n Derivative Works a copy of this License; and\n\n (b) You must cause any modified files to carry prominent notices\n stating that You changed the files; and\n\n (c) You must retain, in the Source form of any Derivative Works\n that You distribute, all copyright, patent, trademark, and\n attribution notices from the Source form of the Work,\n excluding those notices that do not pertain to any part of\n the Derivative Works; and\n\n (d) If the Work includes a \"NOTICE\" text file as part of its\n distribution, then any Derivative Works that You distribute must\n include a readable copy of the attribution notices contained\n within such NOTICE file, excluding those notices that do not\n pertain to any part of the Derivative Works, in at least one\n of the following places: within a NOTICE text file distributed\n as part of the Derivative Works; within the Source form or\n documentation, if provided along with the Derivative Works; or,\n within a display generated by the Derivative Works, if and\n wherever such third-party notices normally appear. The contents\n of the NOTICE file are for informational purposes only and\n do not modify the License. You may add Your own attribution\n notices within Derivative Works that You distribute, alongside\n or as an addendum to the NOTICE text from the Work, provided\n that such additional attribution notices cannot be construed\n as modifying the License.\n\n You may add Your own copyright statement to Your modifications and\n may provide additional or different license terms and conditions\n for use, reproduction, or distribution of Your modifications, or\n for any such Derivative Works as a whole, provided Your use,\n reproduction, and distribution of the Work otherwise complies with\n the conditions stated in this License.\n\n 5. Submission of Contributions. Unless You explicitly state otherwise,\n any Contribution intentionally submitted for inclusion in the Work\n by You to the Licensor shall be under the terms and conditions of\n this License, without any additional terms or conditions.\n Notwithstanding the above, nothing herein shall supersede or modify\n the terms of any separate license agreement you may have executed\n with Licensor regarding such Contributions.\n\n 6. Trademarks. This License does not grant permission to use the trade\n names, trademarks, service marks, or product names of the Licensor,\n except as required for reasonable and customary use in describing the\n origin of the Work and reproducing the content of the NOTICE file.\n\n 7. Disclaimer of Warranty. Unless required by applicable law or\n agreed to in writing, Licensor provides the Work (and each\n Contributor provides its Contributions) on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n implied, including, without limitation, any warranties or conditions\n of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n PARTICULAR PURPOSE. You are solely responsible for determining the\n appropriateness of using or redistributing the Work and assume any\n risks associated with Your exercise of permissions under this License.\n\n 8. Limitation of Liability. In no event and under no legal theory,\n whether in tort (including negligence), contract, or otherwise,\n unless required by applicable law (such as deliberate and grossly\n negligent acts) or agreed to in writing, shall any Contributor be\n liable to You for damages, including any direct, indirect, special,\n incidental, or consequential damages of any character arising as a\n result of this License or out of the use or inability to use the\n Work (including but not limited to damages for loss of goodwill,\n work stoppage, computer failure or malfunction, or any and all\n other commercial damages or losses), even if such Contributor\n has been advised of the possibility of such damages.\n\n 9. Accepting Warranty or Additional Liability. While redistributing\n the Work or Derivative Works thereof, You may choose to offer,\n and charge a fee for, acceptance of support, warranty, indemnity,\n or other liability obligations and/or rights consistent with this\n License. However, in accepting such obligations, You may act only\n on Your own behalf and on Your sole responsibility, not on behalf\n of any other Contributor, and only if You agree to indemnify,\n defend, and hold each Contributor harmless for any liability\n incurred by, or claims asserted against, such Contributor by reason\n of your accepting any such warranty or additional liability.\n\n END OF TERMS AND CONDITIONS\n\n APPENDIX: How to apply the Apache License to your work.\n\n To apply the Apache License to your work, attach the following\n boilerplate notice, with the fields enclosed by brackets \"[]\"\n replaced with your own identifying information. (Don't include\n the brackets!) The text should be enclosed in the appropriate\n comment syntax for the file format. We also recommend that a\n file or class name and description of purpose be included on the\n same \"printed page\" as the copyright notice for easier\n identification within third-party archives.\n\n Copyright 2024 Alibaba Cloud\n\n Licensed under the Apache License, Version 2.0 (the \"License\");\n you may not use this file except in compliance with the License.\n You may obtain a copy of the License at\n\n http://www.apache.org/licenses/LICENSE-2.0\n\n Unless required by applicable law or agreed to in writing, software\n distributed under the License is distributed on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n See the License for the specific language governing permissions and\n limitations under the License.","modelfile": "# Modelfile generated by \"ollama show\"\n# To build a new Modelfile based on this, replace FROM with:\n# FROM qwen2.5-coder:0.5b\n\nFROM /usr/share/ollama/.ollama/models/blobs/sha256-828125e28bf46a219fa4f75b6982cb0c41fd9187467abe91c9b175287945b7ef\nTEMPLATE \"\"\"{{- if .Suffix }}\u003c|fim_prefix|\u003e{{ .Prompt }}\u003c|fim_suffix|\u003e{{ .Suffix }}\u003c|fim_middle|\u003e\n{{- else if .Messages }}\n{{- if or .System .Tools }}\u003c|im_start|\u003esystem\n{{- if .System }}\n{{ .System }}\n{{- end }}\n{{- if .Tools }}\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within \u003ctools\u003e\u003c/tools\u003e XML tags:\n\u003ctools\u003e\n{{- range .Tools }}\n{\"type\": \"function\", \"function\": {{ .Function }}}\n{{- end }}\n\u003c/tools\u003e\n\nFor each function call, return a json object with function name and arguments within \u003ctool_call\u003e\u003c/tool_call\u003e XML tags:\n\u003ctool_call\u003e\n{\"name\": \u003cfunction-name\u003e, \"arguments\": \u003cargs-json-object\u003e}\n\u003c/tool_call\u003e\n{{- end }}\u003c|im_end|\u003e\n{{ end }}\n{{- range $i, $_ := .Messages }}\n{{- $last := eq (len (slice $.Messages $i)) 1 -}}\n{{- if eq .Role \"user\" }}\u003c|im_start|\u003euser\n{{ .Content }}\u003c|im_end|\u003e\n{{ else if eq .Role \"assistant\" }}\u003c|im_start|\u003eassistant\n{{ if .Content }}{{ .Content }}\n{{- else if .ToolCalls }}\u003ctool_call\u003e\n{{ range .ToolCalls }}{\"name\": \"{{ .Function.Name }}\", \"arguments\": {{ .Function.Arguments }}}\n{{ end }}\u003c/tool_call\u003e\n{{- end }}{{ if not $last }}\u003c|im_end|\u003e\n{{ end }}\n{{- else if eq .Role \"tool\" }}\u003c|im_start|\u003euser\n\u003ctool_response\u003e\n{{ .Content }}\n\u003c/tool_response\u003e\u003c|im_end|\u003e\n{{ end }}\n{{- if and (ne .Role \"assistant\") $last }}\u003c|im_start|\u003eassistant\n{{ end }}\n{{- end }}\n{{- else }}\n{{- if .System }}\u003c|im_start|\u003esystem\n{{ .System }}\u003c|im_end|\u003e\n{{ end }}{{ if .Prompt }}\u003c|im_start|\u003euser\n{{ .Prompt }}\u003c|im_end|\u003e\n{{ end }}\u003c|im_start|\u003eassistant\n{{ end }}{{ .Response }}{{ if .Response }}\u003c|im_end|\u003e{{ end }}\"\"\"\nSYSTEM You are Qwen, created by Alibaba Cloud. You are a helpful assistant.\nLICENSE \"\"\"\n Apache License\n Version 2.0, January 2004\n http://www.apache.org/licenses/\n\n TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n 1. Definitions.\n\n \"License\" shall mean the terms and conditions for use, reproduction,\n and distribution as defined by Sections 1 through 9 of this document.\n\n \"Licensor\" shall mean the copyright owner or entity authorized by\n the copyright owner that is granting the License.\n\n \"Legal Entity\" shall mean the union of the acting entity and all\n other entities that control, are controlled by, or are under common\n control with that entity. For the purposes of this definition,\n \"control\" means (i) the power, direct or indirect, to cause the\n direction or management of such entity, whether by contract or\n otherwise, or (ii) ownership of fifty percent (50%) or more of the\n outstanding shares, or (iii) beneficial ownership of such entity.\n\n \"You\" (or \"Your\") shall mean an individual or Legal Entity\n exercising permissions granted by this License.\n\n \"Source\" form shall mean the preferred form for making modifications,\n including but not limited to software source code, documentation\n source, and configuration files.\n\n \"Object\" form shall mean any form resulting from mechanical\n transformation or translation of a Source form, including but\n not limited to compiled object code, generated documentation,\n and conversions to other media types.\n\n \"Work\" shall mean the work of authorship, whether in Source or\n Object form, made available under the License, as indicated by a\n copyright notice that is included in or attached to the work\n (an example is provided in the Appendix below).\n\n \"Derivative Works\" shall mean any work, whether in Source or Object\n form, that is based on (or derived from) the Work and for which the\n editorial revisions, annotations, elaborations, or other modifications\n represent, as a whole, an original work of authorship. For the purposes\n of this License, Derivative Works shall not include works that remain\n separable from, or merely link (or bind by name) to the interfaces of,\n the Work and Derivative Works thereof.\n\n \"Contribution\" shall mean any work of authorship, including\n the original version of the Work and any modifications or additions\n to that Work or Derivative Works thereof, that is intentionally\n submitted to Licensor for inclusion in the Work by the copyright owner\n or by an individual or Legal Entity authorized to submit on behalf of\n the copyright owner. For the purposes of this definition, \"submitted\"\n means any form of electronic, verbal, or written communication sent\n to the Licensor or its representatives, including but not limited to\n communication on electronic mailing lists, source code control systems,\n and issue tracking systems that are managed by, or on behalf of, the\n Licensor for the purpose of discussing and improving the Work, but\n excluding communication that is conspicuously marked or otherwise\n designated in writing by the copyright owner as \"Not a Contribution.\"\n\n \"Contributor\" shall mean Licensor and any individual or Legal Entity\n on behalf of whom a Contribution has been received by Licensor and\n subsequently incorporated within the Work.\n\n 2. Grant of Copyright License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n copyright license to reproduce, prepare Derivative Works of,\n publicly display, publicly perform, sublicense, and distribute the\n Work and such Derivative Works in Source or Object form.\n\n 3. Grant of Patent License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n (except as stated in this section) patent license to make, have made,\n use, offer to sell, sell, import, and otherwise transfer the Work,\n where such license applies only to those patent claims licensable\n by such Contributor that are necessarily infringed by their\n Contribution(s) alone or by combination of their Contribution(s)\n with the Work to which such Contribution(s) was submitted. If You\n institute patent litigation against any entity (including a\n cross-claim or counterclaim in a lawsuit) alleging that the Work\n or a Contribution incorporated within the Work constitutes direct\n or contributory patent infringement, then any patent licenses\n granted to You under this License for that Work shall terminate\n as of the date such litigation is filed.\n\n 4. Redistribution. You may reproduce and distribute copies of the\n Work or Derivative Works thereof in any medium, with or without\n modifications, and in Source or Object form, provided that You\n meet the following conditions:\n\n (a) You must give any other recipients of the Work or\n Derivative Works a copy of this License; and\n\n (b) You must cause any modified files to carry prominent notices\n stating that You changed the files; and\n\n (c) You must retain, in the Source form of any Derivative Works\n that You distribute, all copyright, patent, trademark, and\n attribution notices from the Source form of the Work,\n excluding those notices that do not pertain to any part of\n the Derivative Works; and\n\n (d) If the Work includes a \"NOTICE\" text file as part of its\n distribution, then any Derivative Works that You distribute must\n include a readable copy of the attribution notices contained\n within such NOTICE file, excluding those notices that do not\n pertain to any part of the Derivative Works, in at least one\n of the following places: within a NOTICE text file distributed\n as part of the Derivative Works; within the Source form or\n documentation, if provided along with the Derivative Works; or,\n within a display generated by the Derivative Works, if and\n wherever such third-party notices normally appear. The contents\n of the NOTICE file are for informational purposes only and\n do not modify the License. You may add Your own attribution\n notices within Derivative Works that You distribute, alongside\n or as an addendum to the NOTICE text from the Work, provided\n that such additional attribution notices cannot be construed\n as modifying the License.\n\n You may add Your own copyright statement to Your modifications and\n may provide additional or different license terms and conditions\n for use, reproduction, or distribution of Your modifications, or\n for any such Derivative Works as a whole, provided Your use,\n reproduction, and distribution of the Work otherwise complies with\n the conditions stated in this License.\n\n 5. Submission of Contributions. Unless You explicitly state otherwise,\n any Contribution intentionally submitted for inclusion in the Work\n by You to the Licensor shall be under the terms and conditions of\n this License, without any additional terms or conditions.\n Notwithstanding the above, nothing herein shall supersede or modify\n the terms of any separate license agreement you may have executed\n with Licensor regarding such Contributions.\n\n 6. Trademarks. This License does not grant permission to use the trade\n names, trademarks, service marks, or product names of the Licensor,\n except as required for reasonable and customary use in describing the\n origin of the Work and reproducing the content of the NOTICE file.\n\n 7. Disclaimer of Warranty. Unless required by applicable law or\n agreed to in writing, Licensor provides the Work (and each\n Contributor provides its Contributions) on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n implied, including, without limitation, any warranties or conditions\n of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n PARTICULAR PURPOSE. You are solely responsible for determining the\n appropriateness of using or redistributing the Work and assume any\n risks associated with Your exercise of permissions under this License.\n\n 8. Limitation of Liability. In no event and under no legal theory,\n whether in tort (including negligence), contract, or otherwise,\n unless required by applicable law (such as deliberate and grossly\n negligent acts) or agreed to in writing, shall any Contributor be\n liable to You for damages, including any direct, indirect, special,\n incidental, or consequential damages of any character arising as a\n result of this License or out of the use or inability to use the\n Work (including but not limited to damages for loss of goodwill,\n work stoppage, computer failure or malfunction, or any and all\n other commercial damages or losses), even if such Contributor\n has been advised of the possibility of such damages.\n\n 9. Accepting Warranty or Additional Liability. While redistributing\n the Work or Derivative Works thereof, You may choose to offer,\n and charge a fee for, acceptance of support, warranty, indemnity,\n or other liability obligations and/or rights consistent with this\n License. However, in accepting such obligations, You may act only\n on Your own behalf and on Your sole responsibility, not on behalf\n of any other Contributor, and only if You agree to indemnify,\n defend, and hold each Contributor harmless for any liability\n incurred by, or claims asserted against, such Contributor by reason\n of your accepting any such warranty or additional liability.\n\n END OF TERMS AND CONDITIONS\n\n APPENDIX: How to apply the Apache License to your work.\n\n To apply the Apache License to your work, attach the following\n boilerplate notice, with the fields enclosed by brackets \"[]\"\n replaced with your own identifying information. (Don't include\n the brackets!) The text should be enclosed in the appropriate\n comment syntax for the file format. We also recommend that a\n file or class name and description of purpose be included on the\n same \"printed page\" as the copyright notice for easier\n identification within third-party archives.\n\n Copyright 2024 Alibaba Cloud\n\n Licensed under the Apache License, Version 2.0 (the \"License\");\n you may not use this file except in compliance with the License.\n You may obtain a copy of the License at\n\n http://www.apache.org/licenses/LICENSE-2.0\n\n Unless required by applicable law or agreed to in writing, software\n distributed under the License is distributed on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n See the License for the specific language governing permissions and\n limitations under the License.\"\"\"\n","template": "{{- if .Suffix }}\u003c|fim_prefix|\u003e{{ .Prompt }}\u003c|fim_suffix|\u003e{{ .Suffix }}\u003c|fim_middle|\u003e\n{{- else if .Messages }}\n{{- if or .System .Tools }}\u003c|im_start|\u003esystem\n{{- if .System }}\n{{ .System }}\n{{- end }}\n{{- if .Tools }}\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within \u003ctools\u003e\u003c/tools\u003e XML tags:\n\u003ctools\u003e\n{{- range .Tools }}\n{\"type\": \"function\", \"function\": {{ .Function }}}\n{{- end }}\n\u003c/tools\u003e\n\nFor each function call, return a json object with function name and arguments within \u003ctool_call\u003e\u003c/tool_call\u003e XML tags:\n\u003ctool_call\u003e\n{\"name\": \u003cfunction-name\u003e, \"arguments\": \u003cargs-json-object\u003e}\n\u003c/tool_call\u003e\n{{- end }}\u003c|im_end|\u003e\n{{ end }}\n{{- range $i, $_ := .Messages }}\n{{- $last := eq (len (slice $.Messages $i)) 1 -}}\n{{- if eq .Role \"user\" }}\u003c|im_start|\u003euser\n{{ .Content }}\u003c|im_end|\u003e\n{{ else if eq .Role \"assistant\" }}\u003c|im_start|\u003eassistant\n{{ if .Content }}{{ .Content }}\n{{- else if .ToolCalls }}\u003ctool_call\u003e\n{{ range .ToolCalls }}{\"name\": \"{{ .Function.Name }}\", \"arguments\": {{ .Function.Arguments }}}\n{{ end }}\u003c/tool_call\u003e\n{{- end }}{{ if not $last }}\u003c|im_end|\u003e\n{{ end }}\n{{- else if eq .Role \"tool\" }}\u003c|im_start|\u003euser\n\u003ctool_response\u003e\n{{ .Content }}\n\u003c/tool_response\u003e\u003c|im_end|\u003e\n{{ end }}\n{{- if and (ne .Role \"assistant\") $last }}\u003c|im_start|\u003eassistant\n{{ end }}\n{{- end }}\n{{- else }}\n{{- if .System }}\u003c|im_start|\u003esystem\n{{ .System }}\u003c|im_end|\u003e\n{{ end }}{{ if .Prompt }}\u003c|im_start|\u003euser\n{{ .Prompt }}\u003c|im_end|\u003e\n{{ end }}\u003c|im_start|\u003eassistant\n{{ end }}{{ .Response }}{{ if .Response }}\u003c|im_end|\u003e{{ end }}","system": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant.","details": {"parent_model": "","format": "gguf","family": "qwen2","families": ["qwen2"],"parameter_size": "494.03M","quantization_level": "Q8_0"},"model_info": {"general.architecture": "qwen2","general.base_model.0.name": "Qwen2.5 Coder 0.5B","general.base_model.0.organization": "Qwen","general.base_model.0.repo_url": "https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B","general.base_model.count": 1,"general.basename": "Qwen2.5-Coder","general.file_type": 7,"general.finetune": "Instruct","general.languages": ["en"],"general.license": "apache-2.0","general.license.link": "https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct/blob/main/LICENSE","general.parameter_count": 494032768,"general.quantization_version": 2,"general.size_label": "0.5B","general.tags": ["code", "codeqwen", "chat", "qwen", "qwen-coder", "text-generation"],"general.type": "model","qwen2.attention.head_count": 14,"qwen2.attention.head_count_kv": 2,"qwen2.attention.layer_norm_rms_epsilon": 0.000001,"qwen2.block_count": 24,"qwen2.context_length": 32768,"qwen2.embedding_length": 896,"qwen2.feed_forward_length": 4864,"qwen2.rope.freq_base": 1000000,"tokenizer.ggml.add_bos_token": false,"tokenizer.ggml.bos_token_id": 151643,"tokenizer.ggml.eos_token_id": 151645,"tokenizer.ggml.merges": null,"tokenizer.ggml.model": "gpt2","tokenizer.ggml.padding_token_id": 151643,"tokenizer.ggml.pre": "qwen2","tokenizer.ggml.token_type": null,"tokenizer.ggml.tokens": null},"modified_at": "2025-01-08T19:32:09.640283014+08:00"
}
4、模型推理（生成内容）
ollama中的原生模型推理（不含OpenAI兼容）方式通过两个接口实现，一个是/api/generate，另一个是/api/chat。两者区别在于，使用前者需要提供完整的Prompt字符串，而使用后者实际上只需要提供类似{"role": "user", "content": "why is the sky blue?"}这样的输入，而真正输入大模型的Prompt由ollama自动生成，简而言之，前者自由度和灵活性更高，后者易用性更好。分别演示如下：
generate接口
curl -X POST http://localhost:11434/api/generate -d '{"model": "qwen2.5-coder:0.5b","prompt": "你是谁?","stream": false
}'generate返回结果（已经格式化排版）如下：
{"model": "qwen2.5-coder:0.5b","created_at": "2025-01-09T06:25:24.240792825Z","response": "我是Qwen，由阿里云开发的AI助手，专注于理解和生成文本。","done": true,"done_reason": "stop","context": [151644, 8948, 198, 2610, 525, 1207, 16948, 11, 3465, 553, 54364, 14817, 13, 1446, 525, 264, 10950, 17847, 13, 151645, 198, 151644, 872, 198, 105043, 100165, 30, 151645, 198, 151644, 77091, 198, 104198, 48, 16948, 3837, 67071, 102661, 99718, 100013, 9370, 15469, 110498, 3837, 107782, 115167, 43959, 108704, 1773],"total_duration": 857877710,"load_duration": 14625325,"prompt_eval_count": 32,"prompt_eval_duration": 175000000,"eval_count": 18,"eval_duration": 665000000
}chat接口
curl -X POST http://localhost:11434/api/chat -d '{"model": "qwen2.5-coder:0.5b","messages": [{"role": "user","content": "你是谁?"}],"stream": false
}'chat返回结果（已经格式化排版）如下：
{"model": "qwen2.5-coder:0.5b","created_at": "2025-01-09T06:38:41.195407315Z","message": {"role": "assistant","content": "我是由阿里云研发的人工智能助手Qwen。"},"done_reason": "stop","done": true,"total_duration": 508747638,"load_duration": 20794125,"prompt_eval_count": 32,"prompt_eval_duration": 32000000,"eval_count": 13,"eval_duration": 447000000
}5、可复现回答
通常模型对于同样的问题，每次回答的内容是不同的。可以通过下面指定相同options使相同的问题每次回答内容相同，实现可复现。
curl -X POST http://localhost:11434/api/chat -d '{"model": "qwen2.5-coder:0.5b","messages": [{"role": "user","content": "你是谁?"}],"stream": false,"options": {"seed": 101,"temperature": 0.5,"top_p":0.85,"top_k":20}
}'返回结果（已经格式化排版）如下
{"model": "qwen2.5-coder:0.5b","created_at": "2025-01-09T07:07:21.330267763Z","message": {"role": "assistant","content": "我是阿里云自主研发的人工智能助手，旨在帮助用户解决问题和获取信息。如果您有任何问题或需要帮助，请随时告诉我！"},"done_reason": "stop","done": true,"total_duration": 950157406,"load_duration": 14133236,"prompt_eval_count": 32,"prompt_eval_duration": 41000000,"eval_count": 28,"eval_duration": 886000000
}
6、覆盖默认的system指令
curl -X POST http://localhost:11434/api/chat -d '{"model": "qwen2.5-coder:0.5b","messages": [{"role": "system","content": "You are a warm-hearted biochemist and from Australia."},{"role": "user","content": "你是谁?"}],"stream": false
}'返回结果（已经格式化排版）如下
{"model": "qwen2.5-coder:0.5b","created_at": "2025-01-09T06:46:04.627016664Z","message": {"role": "assistant","content": "我是来自澳大利亚的生物chemist，我的专业领域是微生物学和免疫学。"},"done_reason": "stop","done": true,"total_duration": 580484699,"load_duration": 15906548,"prompt_eval_count": 27,"prompt_eval_duration": 35000000,"eval_count": 18,"eval_duration": 520000000
}
7、携带上下文
第一轮
curl -X POST http://localhost:11434/api/chat -d '{"model": "qwen2.5-coder:0.5b","messages": [{"role": "system","content": "You are a warm-hearted doctor, and you only speak Chinese."},{"role": "user","content": "李华在公园时不小心把腿摔断了，已经去医院治疗，一般要多长时间能恢复？"}],"stream": false
}'第一轮返回结果（已经格式化排版）如下
{"model": "qwen2.5-coder:0.5b","created_at": "2025-01-09T06:56:07.051752359Z","message": {"role": "assistant","content": "恢复时间因人而异。通常情况下，腿部受伤后1-2周内是恢复的最佳时期。具体恢复时间取决于患者的个人情况、病情严重程度以及医生的建议。\n\n以下是一些一般性的时间表：\n\n1. **轻度损伤**：如果膝盖和踝部没有明显损坏，可能只需要一周。\n2. **中重度损伤**：如果膝盖和踝部的磨损严重，或者有明显的疼痛或不适，可能需要更长时间。\n\n如果情况较复杂，可能需要进一步检查以确定问题的具体性质，并根据医生的建议进行治疗。最重要的是保持积极的心态，及时就医以获得专业的帮助。"},"done_reason": "stop","done": true,"total_duration": 4360104102,"load_duration": 16847719,"prompt_eval_count": 49,"prompt_eval_duration": 80000000,"eval_count": 133,"eval_duration": 4254000000
}第二轮
curl -X POST http://localhost:11434/api/chat -d '{"model": "qwen2.5-coder:0.5b","messages": [{"role": "system","content": "You are a warm-hearted assistant, and you only speak Chinese."},{"role": "user","content": "李华在公园时不小心把腿摔断了，已经去医院治疗，一般要多长时间能恢复？"},{"role": "assistant","content": "恢复时间因人而异。通常情况下，腿部受伤后1-2周内是恢复的最佳时期。具体恢复时间取决于患者的个人情况、病情严重程度以及医生的建议。\n\n以下是一些一般性的时间表：\n\n1. **轻度损伤**：如果膝盖和踝部没有明显损坏，可能只需要一周。\n2. **中重度损伤**：如果膝盖和踝部的磨损严重，或者有明显的疼痛或不适，可能需要更长时间。\n\n如果情况较复杂，可能需要进一步检查以确定问题的具体性质，并根据医生的建议进行治疗。最重要的是保持积极的心态，及时就医以获得专业的帮助。"},{"role": "user","content": "李华因为什么要去医院？"}],"stream": false
}'第二轮返回结果（已经格式化排版）如下
{"model": "qwen2.5-coder:0.5b","created_at": "2025-01-09T06:59:23.493656678Z","message": {"role": "assistant","content": "李华因腿摔断了前往医院治疗。"},"done_reason": "stop","done": true,"total_duration": 486334504,"load_duration": 16855321,"prompt_eval_count": 198,"prompt_eval_duration": 84000000,"eval_count": 12,"eval_duration": 346000000
}
8、删除模型
curl -X DELETE http://localhost:11434/api/delete -d '{"name": "qwen2.5-coder:0.5b"}'返回结果无则表示删除成功。
五、查看Ollama服务日志
在Linux上，可以通过以下命令查看ollama服务的日志：
# -u指定服务，--no-pager不分页，-f实时刷日志
sudo journalctl -u ollama.service --no-pager