{"id":13455925,"url":"https://github.com/datawhalechina/self-llm","last_synced_at":"2025-05-14T08:05:06.837Z","repository":{"id":207486114,"uuid":"719367888","full_name":"datawhalechina/self-llm","owner":"datawhalechina","description":"《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程","archived":false,"fork":false,"pushed_at":"2025-05-08T09:17:33.000Z","size":158873,"stargazers_count":15430,"open_issues_count":135,"forks_count":1732,"subscribers_count":103,"default_branch":"master","last_synced_at":"2025-05-14T08:02:51.195Z","etag":null,"topics":["chatglm","chatglm3","gemma-2b-it","glm-4","internlm2","llama3","llm","lora","minicpm","q-wen","qwen","qwen1-5","qwen2"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/datawhalechina.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-11-16T02:31:29.000Z","updated_at":"2025-05-14T07:41:38.000Z","dependencies_parsed_at":"2023-11-18T16:25:38.192Z","dependency_job_id":"c6309c8c-e0f6-491c-8cf8-eda81914fafe","html_url":"https://github.com/datawhalechina/self-llm","commit_stats":{"total_commits":675,"total_committers":59,"mean_commits":"11.440677966101696","dds":0.7051851851851851,"last_synced_commit":"8f1a2174a393b57ed4138d79e4d8f528746884f4"},"previous_names":["kmno4-zx/llm-quicklydeploy","kmno4-zx/self_llm","datawhalechina/self-llm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datawhalechina%2Fself-llm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datawhalechina%2Fself-llm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datawhalechina%2Fself-llm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datawhalechina%2Fself-llm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/datawhalechina","download_url":"https://codeload.github.com/datawhalechina/self-llm/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254101586,"owners_count":22014907,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chatglm","chatglm3","gemma-2b-it","glm-4","internlm2","llama3","llm","lora","minicpm","q-wen","qwen","qwen1-5","qwen2"],"created_at":"2024-07-31T08:01:13.543Z","updated_at":"2025-05-14T08:05:01.825Z","avatar_url":"https://github.com/datawhalechina.png","language":"Jupyter Notebook","funding_links":[],"categories":["References","A01_文本生成_文本对话","Jupyter Notebook","Frameworks","Repos","Summary","AI应用"],"sub_categories":["大语言对话模型及数据"],"readme":"\u003cdiv align=center\u003e\n  \u003cimg src=\"./images/head-img.png\" \u003e\n  \u003ch1\u003e开源大模型食用指南\u003c/h1\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n中文 | [English](./README_en.md)\n\n\u003c/div\u003e\n\n\n\u0026emsp;\u0026emsp;本项目是一个围绕开源大模型、针对国内初学者、基于 Linux 平台的中国宝宝专属大模型教程，针对各类开源大模型提供包括环境配置、本地部署、高效微调等技能在内的全流程指导，简化开源大模型的部署、使用和应用流程，让更多的普通学生、研究者更好地使用开源大模型，帮助开源、自由的大模型更快融入到普通学习者的生活中。\n\n\u0026emsp;\u0026emsp;本项目的主要内容包括：\n\n  1. 基于 Linux 平台的开源 LLM 环境配置指南，针对不同模型要求提供不同的详细环境配置步骤；\n  2. 针对国内外主流开源 LLM 的部署使用教程，包括 LLaMA、ChatGLM、InternLM 等； \n  3. 开源 LLM 的部署应用指导，包括命令行调用、在线 Demo 部署、LangChain 框架集成等；\n  4. 开源 LLM 的全量微调、高效微调方法，包括分布式全量微调、LoRA、ptuning 等。\n\n\u0026emsp;\u0026emsp;**项目的主要内容就是教程，让更多的学生和未来的从业者了解和熟悉开源大模型的食用方法！任何人都可以提出issue或是提交PR，共同构建维护这个项目。**\n\n\u0026emsp;\u0026emsp;想要深度参与的同学可以联系我们，我们会将你加入到项目的维护者中。\n\n\u003e \u0026emsp;\u0026emsp;***学习建议：本项目的学习建议是，先学习环境配置，然后再学习模型的部署使用，最后再学习微调。因为环境配置是基础，模型的部署使用是基础，微调是进阶。初学者可以选择Qwen1.5，InternLM2，MiniCPM等模型优先学习。***\n\n\u003e 注：如果有同学希望了解大模型的模型构成，以及从零手写RAG、Agent和Eval等任务，可以学习Datawhale的另一个项目[Tiny-Universe](https://github.com/datawhalechina/tiny-universe)，大模型是当下深度学习领域的热点，但现有的大部分大模型教程只在于教给大家如何调用api完成大模型的应用，而很少有人能够从原理层面讲清楚模型结构、RAG、Agent 以及 Eval。所以该仓库会提供全部手写，不采用调用api的形式，完成大模型的 RAG 、 Agent 、Eval 任务。\n\n\u003e 注：考虑到有同学希望在学习本项目之前，希望学习大模型的理论部分，如果想要进一步深入学习 LLM 的理论基础，并在理论的基础上进一步认识、应用 LLM，可以参考 Datawhale 的 [so-large-llm](https://github.com/datawhalechina/so-large-lm.git)课程。\n\n\u003e 注：如果有同学在学习本课程之后，想要自己动手开发大模型应用。同学们可以参考 Datawhale 的 [动手学大模型应用开发](https://github.com/datawhalechina/llm-universe) 课程，该项目是一个面向小白开发者的大模型应用开发教程，旨在基于阿里云服务器，结合个人知识库助手项目，向同学们完整的呈现大模型应用开发流程。\n\n## 项目意义\n\n\u0026emsp;\u0026emsp;什么是大模型？\n\n\u003e大模型（LLM）狭义上指基于深度学习算法进行训练的自然语言处理（NLP）模型，主要应用于自然语言理解和生成等领域，广义上还包括机器视觉（CV）大模型、多模态大模型和科学计算大模型等。\n\n\u0026emsp;\u0026emsp;百模大战正值火热，开源 LLM 层出不穷。如今国内外已经涌现了众多优秀开源 LLM，国外如 LLaMA、Alpaca，国内如 ChatGLM、BaiChuan、InternLM（书生·浦语）等。开源 LLM 支持用户本地部署、私域微调，每一个人都可以在开源 LLM 的基础上打造专属于自己的独特大模型。\n\n\u0026emsp;\u0026emsp;然而，当前普通学生和用户想要使用这些大模型，需要具备一定的技术能力，才能完成模型的部署和使用。对于层出不穷又各有特色的开源 LLM，想要快速掌握一个开源 LLM 的应用方法，是一项比较有挑战的任务。\n\n\u0026emsp;\u0026emsp;本项目旨在首先基于核心贡献者的经验，实现国内外主流开源 LLM 的部署、使用与微调教程；在实现主流 LLM 的相关部分之后，我们希望充分聚集共创者，一起丰富这个开源 LLM 的世界，打造更多、更全面特色 LLM 的教程。星火点点，汇聚成海。\n\n\u0026emsp;\u0026emsp;***我们希望成为 LLM 与普罗大众的阶梯，以自由、平等的开源精神，拥抱更恢弘而辽阔的 LLM 世界。***\n\n## 项目受众\n\n\u0026emsp;\u0026emsp;本项目适合以下学习者：\n\n* 想要使用或体验 LLM，但无条件获得或使用相关 API；\n* 希望长期、低成本、大量应用 LLM；\n* 对开源 LLM 感兴趣，想要亲自上手开源 LLM；\n* NLP 在学，希望进一步学习 LLM；\n* 希望结合开源 LLM，打造领域特色的私域 LLM；\n* 以及最广大、最普通的学生群体。\n\n## 项目规划及进展\n\n\u0026emsp;\u0026emsp; 本项目拟围绕开源 LLM 应用全流程组织，包括环境配置及使用、部署应用、微调等，每个部分覆盖主流及特点开源 LLM：\n\n### Example 系列\n\n- [Chat-嬛嬛](./examples/Chat-嬛嬛/readme.md)： Chat-甄嬛是利用《甄嬛传》剧本中所有关于甄嬛的台词和语句，基于LLM进行LoRA微调得到的模仿甄嬛语气的聊天语言模型。\n\n- [Tianji-天机](./examples/Tianji-天机/readme.md)：天机是一款基于人情世故社交场景，涵盖提示词工程 、智能体制作、 数据获取与模型微调、RAG 数据清洗与使用等全流程的大语言模型系统应用教程。\n\n- [AMChat](./examples/AMchat-高等数学/readme.md): AM (Advanced Mathematics) chat 是一个集成了数学知识和高等数学习题及其解答的大语言模型。该模型使用 Math 和高等数学习题及其解析融合的数据集，基于 InternLM2-Math-7B 模型，通过 xtuner 微调，专门设计用于解答高等数学问题。\n\n- [数字生命](./examples/数字生命/readme.md): 本项目将以我为原型，利用特制的数据集对大语言模型进行微调，致力于创造一个能够真正反映我的个性特征的AI数字人——包括但不限于我的语气、表达方式和思维模式等等，因此无论是日常聊天还是分享心情，它都以一种既熟悉又舒适的方式交流，仿佛我在他们身边一样。整个流程是可迁移复制的，亮点是数据集的制作。 \n\n### 已支持模型\n\n- [Gemma3](https://huggingface.co/google/gemma-3-4b-it)\n  - [x] [gemma-3-4b-it FastApi 部署调用](./models/Gemma3/01-gemma-3-4b-it%20FastApi%20部署调用.md) @杜森\n  - [x] [gemma-3-4b-it ollama + open-webui部署](./models/Gemma3/03-gemma-3-4b-it-ollama%20+%20open-webui部署.md) @孙超\n  - [x] [gemma-3-4b-it evalscope 智商情商评测](./models/Gemma3/04-Gemma3-4b%20%20evalscope智商情商评测.md) @张龙斐\n  - [x] [gemma-3-4b-it Lora 微调](./models/Gemma3/05-gemma-3-4b-it%20LoRA.md) @荞麦\n  - [x] [gemma-3-4b-it Docker 镜像](https://www.codewithgpu.com/i/datawhalechina/self-llm/self-llm-gemma3) @姜舒凡\n\n- [DeepSeek-R1-Distill](https://www.modelscope.cn/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)\n  - [x] [DeepSeek-R1-Distill-Qwen-7B FastApi 部署调用](./models/DeepSeek-R1-Distill-Qwen/01-DeepSeek-R1-Distill-Qwen-7B%20FastApi%20部署调用.md) @骆秀韬\n  - [x] [DeepSeek-R1-Distill-Qwen-7B Langchain 接入](./models/DeepSeek-R1-Distill-Qwen/02-DeepSeek-R1-Distill-Qwen-7B%20Langchain%20接入.md) @骆秀韬\n  - [x] [DeepSeek-R1-Distill-Qwen-7B WebDemo 部署](./models/DeepSeek-R1-Distill-Qwen/03-DeepSeek-R1-Distill-Qwen-7B%20WebDemo%20部署.md) @骆秀韬\n  - [x] [DeepSeek-R1-Distill-Qwen-7B vLLM 部署调用](./models/DeepSeek-R1-Distill-Qwen/04-DeepSeek-R1-Distill-Qwen-7B%20vLLM%20部署调用.md) @骆秀韬\n\n- [MiniCPM-o-2_6](https://github.com/OpenBMB/MiniCPM-o)\n  - [x] [minicpm-o-2.6 FastApi 部署调用](./models/MiniCPM-o/01MiniCPM-o%202%206%20FastApi部署调用%20.md) @林恒宇\n  - [x] [minicpm-o-2.6 WebDemo 部署](./models/MiniCPM-o/02minicpm-o-2.6WebDemo_streamlit.py) @程宏\n  - [x] [minicpm-o-2.6 多模态语音能力](./models/MiniCPM-o/03-MiniCPM-o-2.6%20多模态语音能力.md) @邓恺俊\n  - [x] [minicpm-o-2.6 可视化 LaTeX_OCR Lora 微调](./models/MiniCPM-o/04-MiniCPM-0-2.6%20Lora微调.md) @林泽毅\n\n- [InternLM3](https://github.com/InternLM/InternLM)\n  - [x] [internlm3-8b-instruct FastApi 部署调用](./models/InternLM3/01-InternLM3-8B-Instruct%20FastAPI.md) @苏向标\n  - [x] [internlm3-8b-instruct Langchian接入](./models/InternLM3/02-internlm3-8b-Instruct%20Langchain%20接入.md) @赵文恺\n  - [x] [internlm3-8b-instruct WebDemo 部署](./models/InternLM3/03-InternLM3-8B-Instruct%20WebDemo部署.md) @王泽宇\n  - [x] [internlm3-8b-instruct Lora 微调](./models/InternLM3/04-InternLM3-8B-Instruct%20LoRA.md) @程宏\n  - [x] [internlm3-8b-instruct o1-like推理链实现](./models/InternLM3/05-internlm3-8b-instruct%20与o1%20.md) @陈睿\n\n- [phi4](https://huggingface.co/microsoft/phi-4)\n  - [x] [phi4 FastApi 部署调用](./models/phi4/01-Phi-4%20FastApi%20部署调用.md) @杜森\n  - [x] [phi4 langchain 接入](./models/phi4/02-Phi-4-Langchain接入.md) @小罗\n  - [x] [phi4 WebDemo 部署](./models/phi4/03-Phi-4%20WebDemo部署.md) @杜森\n  - [x] [phi4 Lora 微调](./models/phi4/04-Phi-4-Lora%20微调.md) @郑远婧\n  - [x] [phi4 Lora 微调 NER任务 SwanLab 可视化记录版](./models/phi4/05-Phi-4-Lora%20微调%20命名实体识别.md) @林泽毅\n\n- [Qwen2.5-Coder](https://github.com/QwenLM/Qwen2.5-Coder)\n  - [x] [Qwen2.5-Coder-7B-Instruct FastApi部署调用](./models/Qwen2.5-Coder/01-Qwen2.5-Coder-7B-Instruct%20FastApi%20部署调用.md) @赵文恺\n  - [x] [Qwen2.5-Coder-7B-Instruct Langchian接入](./models/Qwen2.5-Coder/02-Qwen2.5-7B-Instruct%20Langchain%20接入.md) @杨晨旭\n  - [x] [Qwen2.5-Coder-7B-Instruct WebDemo 部署](./models/Qwen2.5-Coder/03-Qwen2.5-Coder-7B-Instruct%20WebDemo部署.md) @王泽宇\n  - [x] [Qwen2.5-Coder-7B-Instruct vLLM 部署](./models/Qwen2.5-Coder/04-Qwen2.5-Coder-7B-Instruct%20vLLM%20部署调用.md) @王泽宇\n  - [x] [Qwen2.5-Coder-7B-Instruct Lora 微调](./models/Qwen2.5-Coder/Qwen2.5-Coder-7B-Instruct%20Lora%20微调.md) @荞麦\n  - [x] [Qwen2.5-Coder-7B-Instruct Lora 微调 SwanLab 可视化记录版](./models/Qwen2.5-Coder/05-Qwen2.5-Coder-7B-Instruct%20Lora%20微调%20SwanLab%20可视化记录版.md) @杨卓\n\n- [Qwen2-vl](https://github.com/QwenLM/Qwen2-VL)\n  - [x] [Qwen2-vl-2B FastApi 部署调用](./models/Qwen2-VL/01-Qwen2-VL-2B-Instruct%20FastApi%20部署调用.md) @姜舒凡\n  - [x] [Qwen2-vl-2B WebDemo 部署](./models/Qwen2-VL/02-Qwen2-VL-2B-Instruct%20Web%20Demo部署.md) @赵伟\n  - [x] [Qwen2-vl-2B vLLM 部署](./models/Qwen2-VL/03-Qwen2-VL-2B-Instruct%20vLLM部署调用.md) @荞麦\n  - [x] [Qwen2-vl-2B Lora 微调](./models/Qwen2-VL/04-Qwen2-VL-2B%20Lora%20微调.md) @李柯辰\n  - [x] [Qwen2-vl-2B Lora 微调 SwanLab 可视化记录版](./models/Qwen2-VL/05-Qwen2-VL-2B-Instruct%20Lora%20微调%20SwanLab%20可视化记录版.md) @林泽毅\n  - [x] [Qwen2-vl-2B Lora 微调案例 - LaTexOCR](./models/Qwen2-VL/06-Qwen2-VL-2B-Instruct%20Lora%20微调案例%20-%20LaTexOCR.md) @林泽毅\n\n- [Qwen2.5](https://github.com/QwenLM/Qwen2.5)\n  - [x] [Qwen2.5-7B-Instruct FastApi 部署调用](./models/Qwen2.5/01-Qwen2.5-7B-Instruct%20FastApi%20部署调用.md) @娄天奥\n  - [x] [Qwen2.5-7B-Instruct langchain 接入](./models/Qwen2.5/02-Qwen2.5-7B-Instruct%20Langchain%20接入.md) @娄天奥\n  - [x] [Qwen2.5-7B-Instruct vLLM 部署调用](./models/Qwen2.5/03-Qwen2.5-7B-Instruct%20vLLM%20部署调用.md) @姜舒凡\n  - [x] [Qwen2.5-7B-Instruct WebDemo 部署](./models/Qwen2.5/04-Qwen2_5-7B-Instruct%20WebDemo部署.md) @高立业\n  - [x] [Qwen2.5-7B-Instruct Lora 微调](./models/Qwen2.5/05-Qwen2.5-7B-Instruct%20Lora%20微调.md) @左春生\n  - [x] [Qwen2.5-7B-Instruct o1-like 推理链实现](./models/Qwen2.5/06-Qwen2.5-7B-Instruct%20o1-like%20推理链实现.md) @姜舒凡\n  - [x] [Qwen2.5-7B-Instruct Lora 微调 SwanLab 可视化记录版](./models/Qwen2.5/07-Qwen2.5-7B-Instruct%20Lora%20微调%20SwanLab可视化记录版.md) @林泽毅\n\n- [Apple OpenELM](https://machinelearning.apple.com/research/openelm)\n  - [x] [OpenELM-3B-Instruct FastApi 部署调用](./models/OpenELM/01-OpenELM-3B-Instruct%20FastApi部署调用.md) @王泽宇\n  - [x] [OpenELM-3B-Instruct Lora 微调](./models/OpenELM/02-OpenELM-3B-Instruct%20Lora微调.md) @王泽宇\n\n- [Llama3_1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)\n  - [x] [Llama3_1-8B-Instruct FastApi 部署调用](./models/Llama3_1/01-Llama3_1-8B-Instruct%20FastApi%20部署调用.md) @不要葱姜蒜\n  - [x] [Llama3_1-8B-Instruct langchain 接入](./models/Llama3_1/02-Llama3_1-8B-Instruct%20langchain接入.md) @张晋\n  - [x] [Llama3_1-8B-Instruct WebDemo 部署](./models/Llama3_1/03-Llama3_1-8B-Instruct%20WebDemo部署.md) @张晋\n  - [x] [Llama3_1-8B-Instruct Lora 微调](./models/Llama3_1/04-Llama3_1-8B--Instruct%20Lora%20微调.md) @不要葱姜蒜\n  - [x] [动手转换GGUF模型并使用Ollama本地部署](./models/Llama3_1/动手转换GGUF模型并使用Ollama本地部署.md) @Gaoboy\n\n- [Gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it)\n  - [x] [Gemma-2-9b-it FastApi 部署调用](./models/Gemma2/01-Gemma-2-9b-it%20FastApi%20部署调用.md) @不要葱姜蒜\n  - [x] [Gemma-2-9b-it langchain 接入](./models/Gemma2/02-Gemma-2-9b-it%20langchain%20接入.md) @不要葱姜蒜\n  - [x] [Gemma-2-9b-it WebDemo 部署](./models/Gemma2/03-Gemma-2-9b-it%20WebDemo%20部署.md) @不要葱姜蒜\n  - [x] [Gemma-2-9b-it Peft Lora 微调](./models/Gemma2/04-Gemma-2-9b-it%20peft%20lora微调.md) @不要葱姜蒜\n\n- [Yuan2.0](https://github.com/IEIT-Yuan/Yuan-2.0)\n  - [x] [Yuan2.0-2B FastApi 部署调用](./models/Yuan2.0/01-Yuan2.0-2B%20FastApi%20部署调用.md) @张帆\n  - [x] [Yuan2.0-2B Langchain 接入](./models/Yuan2.0/02-Yuan2.0-2B%20Langchain%20接入.md) @张帆\n  - [x] [Yuan2.0-2B WebDemo部署](./models/Yuan2.0/03-Yuan2.0-2B%20WebDemo部署.md) @张帆\n  - [x] [Yuan2.0-2B vLLM部署调用](./models/Yuan2.0/04-Yuan2.0-2B%20vLLM部署调用.md) @张帆\n  - [x] [Yuan2.0-2B Lora微调](./models/Yuan2.0/05-Yuan2.0-2B%20Lora微调.md) @张帆\n\n- [Yuan2.0-M32](https://github.com/IEIT-Yuan/Yuan2.0-M32)\n  - [x] [Yuan2.0-M32 FastApi 部署调用](./models/Yuan2.0-M32/01-Yuan2.0-M32%20FastApi%20部署调用.md) @张帆\n  - [x] [Yuan2.0-M32 Langchain 接入](./models/Yuan2.0-M32/02-Yuan2.0-M32%20Langchain%20接入.md) @张帆\n  - [x] [Yuan2.0-M32 WebDemo部署](./models/Yuan2.0-M32/03-Yuan2.0-M32%20WebDemo部署.md) @张帆\n\n- [DeepSeek-Coder-V2](https://github.com/deepseek-ai/DeepSeek-Coder-V2)\n  - [x] [DeepSeek-Coder-V2-Lite-Instruct FastApi 部署调用](./models/DeepSeek-Coder-V2/01-DeepSeek-Coder-V2-Lite-Instruct%20FastApi%20部署调用.md) @姜舒凡\n  - [x] [DeepSeek-Coder-V2-Lite-Instruct langchain 接入](./models/DeepSeek-Coder-V2/02-DeepSeek-Coder-V2-Lite-Instruct%20接入%20LangChain.md) @姜舒凡\n  - [x] [DeepSeek-Coder-V2-Lite-Instruct WebDemo 部署](./models/DeepSeek-Coder-V2/03-DeepSeek-Coder-V2-Lite-Instruct%20WebDemo%20部署.md) @Kailigithub\n  - [x] [DeepSeek-Coder-V2-Lite-Instruct Lora 微调](./models/DeepSeek-Coder-V2/04-DeepSeek-Coder-V2-Lite-Instruct%20Lora%20微调.md) @余洋\n\n- [哔哩哔哩 Index-1.9B](https://github.com/bilibili/Index-1.9B)\n  - [x] [Index-1.9B-Chat FastApi 部署调用](./models/bilibili_Index-1.9B/01-Index-1.9B-chat%20FastApi%20部署调用.md) @邓恺俊\n  - [x] [Index-1.9B-Chat langchain 接入](./models/bilibili_Index-1.9B/02-Index-1.9B-Chat%20接入%20LangChain.md) @张友东\n  - [x] [Index-1.9B-Chat WebDemo 部署](./models/bilibili_Index-1.9B/03-Index-1.9B-chat%20WebDemo部署.md) @程宏\n  - [x] [Index-1.9B-Chat Lora 微调](./models/bilibili_Index-1.9B/04-Index-1.9B-Chat%20Lora%20微调.md) @姜舒凡\n\n- [Qwen2](https://github.com/QwenLM/Qwen2)\n  - [x] [Qwen2-7B-Instruct FastApi 部署调用](./models/Qwen2/01-Qwen2-7B-Instruct%20FastApi%20部署调用.md) @康婧淇\n  - [x] [Qwen2-7B-Instruct langchain 接入](./models/Qwen2/02-Qwen2-7B-Instruct%20Langchain%20接入.md) @不要葱姜蒜\n  - [x] [Qwen2-7B-Instruct WebDemo 部署](./models/Qwen2/03-Qwen2-7B-Instruct%20WebDemo部署.md) @三水\n  - [x] [Qwen2-7B-Instruct vLLM 部署调用](./models/Qwen2/04-Qwen2-7B-Instruct%20vLLM%20部署调用.md) @姜舒凡\n  - [x] [Qwen2-7B-Instruct Lora 微调](./models/Qwen2/05-Qwen2-7B-Instruct%20Lora%20微调.md) @散步\n\n- [GLM-4](https://github.com/THUDM/GLM-4.git)\n  - [x] [GLM-4-9B-chat FastApi 部署调用](./models/GLM-4/01-GLM-4-9B-chat%20FastApi%20部署调用.md) @张友东\n  - [x] [GLM-4-9B-chat langchain 接入](./models/GLM-4/02-GLM-4-9B-chat%20langchain%20接入.md) @谭逸珂\n  - [x] [GLM-4-9B-chat WebDemo 部署](./models/GLM-4/03-GLM-4-9B-Chat%20WebDemo.md) @何至轩\n  - [x] [GLM-4-9B-chat vLLM 部署](./models/GLM-4/04-GLM-4-9B-Chat%20vLLM%20部署调用.md) @王熠明\n  - [x] [GLM-4-9B-chat Lora 微调](./models/GLM-4/05-GLM-4-9B-chat%20Lora%20微调.md) @肖鸿儒\n  - [x] [GLM-4-9B-chat-hf Lora 微调](./models/GLM-4/05-GLM-4-9B-chat-hf%20Lora%20微调.md) @付志远\n\n\n- [Qwen 1.5](https://github.com/QwenLM/Qwen1.5.git)\n  - [x] [Qwen1.5-7B-chat FastApi 部署调用](./models/Qwen1.5/01-Qwen1.5-7B-Chat%20FastApi%20部署调用.md) @颜鑫\n  - [x] [Qwen1.5-7B-chat langchain 接入](./models/Qwen1.5/02-Qwen1.5-7B-Chat%20接入langchain搭建知识库助手.md) @颜鑫\n  - [x] [Qwen1.5-7B-chat WebDemo 部署](./models/Qwen1.5/03-Qwen1.5-7B-Chat%20WebDemo.md) @颜鑫\n  - [x] [Qwen1.5-7B-chat Lora 微调](./models/Qwen1.5/04-Qwen1.5-7B-chat%20Lora%20微调.md) @不要葱姜蒜\n  - [x] [Qwen1.5-72B-chat-GPTQ-Int4 部署环境](./models/Qwen1.5/05-Qwen1.5-7B-Chat-GPTQ-Int4%20%20WebDemo.md) @byx020119\n  - [x] [Qwen1.5-MoE-chat Transformers 部署调用](./models/Qwen1.5/06-Qwen1.5-MoE-A2.7B.md) @丁悦\n  - [x] [Qwen1.5-7B-chat vLLM推理部署](./models/Qwen1.5/07-Qwen1.5-7B-Chat%20vLLM%20推理部署调用.md) @高立业\n  - [x] [Qwen1.5-7B-chat Lora 微调 接入SwanLab实验管理平台](./models/Qwen1.5/08-Qwen1.5-7B-chat%20LoRA微调接入实验管理.md) @黄柏特\n\n- [谷歌-Gemma](https://huggingface.co/google/gemma-7b-it)\n  - [x] [gemma-2b-it FastApi 部署调用 ](./models/Gemma/01-Gemma-2B-Instruct%20FastApi%20部署调用.md) @东东\n  - [x] [gemma-2b-it langchain 接入 ](./models/Gemma/02-Gemma-2B-Instruct%20langchain%20接入.md) @东东\n  - [x] [gemma-2b-it WebDemo 部署 ](./models/Gemma/03-Gemma-2B-Instruct%20WebDemo%20部署.md) @东东\n  - [x] [gemma-2b-it Peft Lora 微调 ](./models/Gemma/04-Gemma-2B-Instruct%20Lora微调.md) @东东\n\n- [phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)\n  - [x] [Phi-3-mini-4k-instruct FastApi 部署调用](./models/phi-3/01-Phi-3-mini-4k-instruct%20FastApi%20部署调用.md) @郑皓桦\n  - [x] [Phi-3-mini-4k-instruct langchain 接入](./models/phi-3/02-Phi-3-mini-4k-instruct%20langchain%20接入.md) @郑皓桦\n  - [x] [Phi-3-mini-4k-instruct WebDemo 部署](./models/phi-3/03-Phi-3-mini-4k-instruct%20WebDemo部署.md) @丁悦\n  - [x] [Phi-3-mini-4k-instruct Lora 微调](./models/phi-3/04-Phi-3-mini-4k-Instruct%20Lora%20微调.md) @丁悦\n\n- [CharacterGLM-6B](https://github.com/thu-coai/CharacterGLM-6B)\n  - [x] [CharacterGLM-6B Transformers 部署调用](./models/CharacterGLM/01-CharacterGLM-6B%20Transformer部署调用.md) @孙健壮\n  - [x] [CharacterGLM-6B FastApi 部署调用](./models/CharacterGLM/02-CharacterGLM-6B%20FastApi部署调用.md) @孙健壮\n  - [x] [CharacterGLM-6B webdemo 部署](./models/CharacterGLM/03-CharacterGLM-6B-chat.md) @孙健壮\n  - [x] [CharacterGLM-6B Lora 微调](./models/CharacterGLM/04-CharacterGLM-6B%20Lora微调.md) @孙健壮\n\n- [LLaMA3-8B-Instruct](https://github.com/meta-llama/llama3.git)\n  - [x] [LLaMA3-8B-Instruct FastApi 部署调用](./models/LLaMA3/01-LLaMA3-8B-Instruct%20FastApi%20部署调用.md) @高立业\n  - [X] [LLaMA3-8B-Instruct langchain 接入](./models/LLaMA3/02-LLaMA3-8B-Instruct%20langchain%20接入.md) @不要葱姜蒜\n  - [x] [LLaMA3-8B-Instruct WebDemo 部署](./models/LLaMA3/03-LLaMA3-8B-Instruct%20WebDemo%20部署.md) @不要葱姜蒜\n  - [x] [LLaMA3-8B-Instruct Lora 微调](./models/LLaMA3/04-LLaMA3-8B-Instruct%20Lora%20微调.md) @高立业\n\n- [XVERSE-7B-Chat](https://modelscope.cn/models/xverse/XVERSE-7B-Chat/summary)\n  - [x] [XVERSE-7B-Chat transformers 部署调用](./models/XVERSE/01-XVERSE-7B-chat%20Transformers推理.md) @郭志航\n  - [x] [XVERSE-7B-Chat FastApi 部署调用](./models/XVERSE/02-XVERSE-7B-chat%20FastAPI部署.md) @郭志航\n  - [x] [XVERSE-7B-Chat langchain 接入](./models/XVERSE/03-XVERSE-7B-chat%20langchain%20接入.md) @郭志航\n  - [x] [XVERSE-7B-Chat WebDemo 部署](./models/XVERSE/04-XVERSE-7B-chat%20WebDemo%20部署.md) @郭志航\n  - [x] [XVERSE-7B-Chat Lora 微调](./models/XVERSE/05-XVERSE-7B-Chat%20Lora%20微调.md) @郭志航\n\n- [TransNormerLLM](https://github.com/OpenNLPLab/TransnormerLLM.git)\n  - [X] [TransNormerLLM-7B-Chat FastApi 部署调用](./models/TransNormer/01-TransNormer-7B%20FastApi%20部署调用.md) @王茂霖\n  - [X] [TransNormerLLM-7B-Chat langchain 接入](./models/TransNormer/02-TransNormer-7B%20接入langchain搭建知识库助手.md) @王茂霖\n  - [X] [TransNormerLLM-7B-Chat WebDemo 部署](./models/TransNormer/03-TransNormer-7B%20WebDemo.md) @王茂霖\n  - [x] [TransNormerLLM-7B-Chat Lora 微调](./models/TransNormer/04-TrasnNormer-7B%20Lora%20微调.md) @王茂霖\n\n- [BlueLM Vivo 蓝心大模型](https://github.com/vivo-ai-lab/BlueLM.git)\n  - [x] [BlueLM-7B-Chat FatApi 部署调用](./models/BlueLM/01-BlueLM-7B-Chat%20FastApi%20部署.md) @郭志航\n  - [x] [BlueLM-7B-Chat langchain 接入](./models/BlueLM/02-BlueLM-7B-Chat%20langchain%20接入.md) @郭志航\n  - [x] [BlueLM-7B-Chat WebDemo 部署](./models/BlueLM/03-BlueLM-7B-Chat%20WebDemo%20部署.md) @郭志航\n  - [x] [BlueLM-7B-Chat Lora 微调](./models/BlueLM/04-BlueLM-7B-Chat%20Lora%20微调.md) @郭志航\n\n- [InternLM2](https://github.com/InternLM/InternLM)\n  - [x] [InternLM2-7B-chat FastApi 部署调用](./models/InternLM2/01-InternLM2-7B-chat%20FastAPI部署.md) @不要葱姜蒜\n  - [x] [InternLM2-7B-chat langchain 接入](./models/InternLM2/02-InternLM2-7B-chat%20langchain%20接入.md) @不要葱姜蒜\n  - [x] [InternLM2-7B-chat WebDemo 部署](./models/InternLM2/03-InternLM2-7B-chat%20WebDemo%20部署.md) @郑皓桦\n  - [x] [InternLM2-7B-chat Xtuner Qlora 微调](./models/InternLM2/04-InternLM2-7B-chat%20Xtuner%20Qlora%20微调.md) @郑皓桦\n\n- [DeepSeek 深度求索](https://github.com/deepseek-ai/DeepSeek-LLM)\n  - [x] [DeepSeek-7B-chat FastApi 部署调用](./models/DeepSeek/01-DeepSeek-7B-chat%20FastApi.md) @不要葱姜蒜\n  - [x] [DeepSeek-7B-chat langchain 接入](./models/DeepSeek/02-DeepSeek-7B-chat%20langchain.md) @不要葱姜蒜\n  - [x] [DeepSeek-7B-chat WebDemo](./models/DeepSeek/03-DeepSeek-7B-chat%20WebDemo.md) @不要葱姜蒜\n  - [x] [DeepSeek-7B-chat Lora 微调](./models/DeepSeek/04-DeepSeek-7B-chat%20Lora%20微调.md) @不要葱姜蒜\n  - [x] [DeepSeek-7B-chat 4bits量化 Qlora 微调](./models/DeepSeek/05-DeepSeek-7B-chat%204bits量化%20Qlora%20微调.md) @不要葱姜蒜\n  - [x] [DeepSeek-MoE-16b-chat Transformers 部署调用](./models/DeepSeek/06-DeepSeek-MoE-16b-chat%20Transformer部署调用.md) @Kailigithub\n  - [x] [DeepSeek-MoE-16b-chat FastApi 部署调用](./models/DeepSeek/06-DeepSeek-MoE-16b-chat%20FastApi.md) @Kailigithub\n  - [x] [DeepSeek-coder-6.7b finetune colab](./models/DeepSeek/07-deepseek_fine_tune.ipynb) @Swiftie\n  - [x] [Deepseek-coder-6.7b webdemo colab](./models/DeepSeek/08-deepseek_web_demo.ipynb) @Swiftie\n\n- [MiniCPM](https://github.com/OpenBMB/MiniCPM.git)\n  - [x] [MiniCPM-2B-chat transformers 部署调用](./models/MiniCPM/MiniCPM-2B-chat%20transformers%20部署调用.md) @Kailigithub \n  - [x] [MiniCPM-2B-chat FastApi 部署调用](./models/MiniCPM/MiniCPM-2B-chat%20FastApi%20部署调用.md) @Kailigithub \n  - [x] [MiniCPM-2B-chat langchain 接入](./models/MiniCPM/MiniCPM-2B-chat%20langchain接入.md) @不要葱姜蒜 \n  - [x] [MiniCPM-2B-chat webdemo 部署](./models/MiniCPM/MiniCPM-2B-chat%20WebDemo部署.md) @Kailigithub \n  - [x] [MiniCPM-2B-chat Lora \u0026\u0026 Full 微调](./models/MiniCPM/MiniCPM-2B-chat%20Lora%20\u0026\u0026%20Full%20微调.md) @不要葱姜蒜 \n  - [x] 官方友情链接：[面壁小钢炮MiniCPM教程](https://modelbest.feishu.cn/wiki/D2tFw8Pcsi5CIzkaHNacLK64npg) @OpenBMB \n  - [x] 官方友情链接：[MiniCPM-Cookbook](https://github.com/OpenBMB/MiniCPM-CookBook) @OpenBMB\n\n- [Qwen-Audio](https://github.com/QwenLM/Qwen-Audio.git)\n  - [x] [Qwen-Audio FastApi 部署调用](./models/Qwen-Audio/01-Qwen-Audio-chat%20FastApi.md) @陈思州\n  - [x] [Qwen-Audio WebDemo](./models/Qwen-Audio/02-Qwen-Audio-chat%20WebDemo.md) @陈思州\n\n- [Qwen](https://github.com/QwenLM/Qwen.git)\n  - [x] [Qwen-7B-chat Transformers 部署调用](./models/Qwen/01-Qwen-7B-Chat%20Transformers部署调用.md) @李娇娇\n  - [x] [Qwen-7B-chat FastApi 部署调用](./models/Qwen/02-Qwen-7B-Chat%20FastApi%20部署调用.md) @李娇娇\n  - [x] [Qwen-7B-chat WebDemo](./models/Qwen/03-Qwen-7B-Chat%20WebDemo.md) @李娇娇\n  - [x] [Qwen-7B-chat Lora 微调](./models/Qwen/04-Qwen-7B-Chat%20Lora%20微调.md) @不要葱姜蒜\n  - [x] [Qwen-7B-chat ptuning 微调](./models/Qwen/05-Qwen-7B-Chat%20Ptuning%20微调.md) @肖鸿儒\n  - [x] [Qwen-7B-chat 全量微调](./models/Qwen/06-Qwen-7B-chat%20全量微调.md) @不要葱姜蒜\n  - [x] [Qwen-7B-Chat 接入langchain搭建知识库助手](./models/Qwen/07-Qwen-7B-Chat%20接入langchain搭建知识库助手.md) @李娇娇\n  - [x] [Qwen-7B-chat 低精度训练](./models/Qwen/08-Qwen-7B-Chat%20Lora%20低精度微调.md) @肖鸿儒\n  - [x] [Qwen-1_8B-chat CPU 部署](./models/Qwen/09-Qwen-1_8B-chat%20CPU%20部署%20.md) @散步\n\n- [Yi 零一万物](https://github.com/01-ai/Yi.git)\n  - [x] [Yi-6B-chat FastApi 部署调用](./models/Yi/01-Yi-6B-Chat%20FastApi%20部署调用.md) @李柯辰\n  - [x] [Yi-6B-chat langchain接入](./models/Yi/02-Yi-6B-Chat%20接入langchain搭建知识库助手.md) @李柯辰\n  - [x] [Yi-6B-chat WebDemo](./models/Yi/03-Yi-6B-chat%20WebDemo.md) @肖鸿儒\n  - [x] [Yi-6B-chat Lora 微调](./models/Yi/04-Yi-6B-Chat%20Lora%20微调.md) @李娇娇\n\n- [Baichuan 百川智能](https://www.baichuan-ai.com/home)\n  - [x] [Baichuan2-7B-chat FastApi 部署调用](./BaiChuan/01-Baichuan2-7B-chat%2BFastApi%2B%E9%83%A8%E7%BD%B2%E8%B0%83%E7%94%A8.md) @惠佳豪\n  - [x] [Baichuan2-7B-chat WebDemo](./models/BaiChuan/02-Baichuan-7B-chat%2BWebDemo.md) @惠佳豪\n  - [x] [Baichuan2-7B-chat 接入 LangChain 框架](./models/BaiChuan/03-Baichuan2-7B-chat%E6%8E%A5%E5%85%A5LangChain%E6%A1%86%E6%9E%B6.md) @惠佳豪\n  - [x] [Baichuan2-7B-chat Lora 微调](./models/BaiChuan/04-Baichuan2-7B-chat%2Blora%2B%E5%BE%AE%E8%B0%83.md) @惠佳豪\n\n- [InternLM](https://github.com/InternLM/InternLM.git)\n  - [x] [InternLM-Chat-7B Transformers 部署调用](./models/InternLM/01-InternLM-Chat-7B%20Transformers%20部署调用.md) @小罗\n  - [x] [InternLM-Chat-7B FastApi 部署调用](./models/InternLM/02-internLM-Chat-7B%20FastApi.md) @不要葱姜蒜\n  - [x] [InternLM-Chat-7B WebDemo](./models/InternLM/03-InternLM-Chat-7B.md) @不要葱姜蒜\n  - [x] [Lagent+InternLM-Chat-7B-V1.1 WebDemo](./models/InternLM/04-Lagent+InternLM-Chat-7B-V1.1.md) @不要葱姜蒜\n  - [x] [浦语灵笔图文理解\u0026创作 WebDemo](./models/InternLM/05-浦语灵笔图文理解\u0026创作.md) @不要葱姜蒜\n  - [x] [InternLM-Chat-7B 接入 LangChain 框架](./models/InternLM/06-InternLM接入LangChain搭建知识库助手.md) @Logan Zou\n\n- [Atom (llama2)](https://hf-mirror.com/FlagAlpha/Atom-7B-Chat)\n  - [x] [Atom-7B-chat WebDemo](./models/Atom/01-Atom-7B-chat-WebDemo.md) @Kailigithub\n  - [x] [Atom-7B-chat Lora 微调](./models/Atom/02-Atom-7B-Chat%20Lora%20微调.md) @Logan Zou\n  - [x] [Atom-7B-Chat 接入langchain搭建知识库助手](./models/Atom/03-Atom-7B-Chat%20接入langchain搭建知识库助手.md) @陈思州\n  - [x] [Atom-7B-chat 全量微调](./models/Atom/04-Atom-7B-chat%20全量微调.md) @Logan Zou\n\n- [ChatGLM3](https://github.com/THUDM/ChatGLM3.git)\n  - [x] [ChatGLM3-6B Transformers 部署调用](./models/ChatGLM/01-ChatGLM3-6B%20Transformer部署调用.md) @丁悦\n  - [x] [ChatGLM3-6B FastApi 部署调用](./models/ChatGLM/02-ChatGLM3-6B%20FastApi部署调用.md) @丁悦\n  - [x] [ChatGLM3-6B chat WebDemo](./models/ChatGLM/03-ChatGLM3-6B-chat.md) @不要葱姜蒜\n  - [x] [ChatGLM3-6B Code Interpreter WebDemo](./models/ChatGLM/04-ChatGLM3-6B-Code-Interpreter.md) @不要葱姜蒜\n  - [x] [ChatGLM3-6B 接入 LangChain 框架](./models/ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手.md) @Logan Zou\n  - [x] [ChatGLM3-6B Lora 微调](./models/ChatGLM/06-ChatGLM3-6B-Lora微调.md) @肖鸿儒\n\n### 通用环境配置\n\n- [x] [pip、conda 换源](./models/General-Setting/01-pip、conda换源.md) @不要葱姜蒜\n- [x] [AutoDL 开放端口](./models/General-Setting/02-AutoDL开放端口.md) @不要葱姜蒜\n\n- 模型下载\n  - [x] [hugging face](./models/General-Setting/03-模型下载.md) @不要葱姜蒜\n  - [x] [hugging face](./General-Setting/03-模型下载.md) 镜像下载 @不要葱姜蒜\n  - [x] [modelscope](./models/General-Setting/03-模型下载.md) @不要葱姜蒜\n  - [x] [git-lfs](./models/General-Setting/03-模型下载.md) @不要葱姜蒜\n  - [x] [Openxlab](./models/General-Setting/03-模型下载.md)\n- Issue \u0026\u0026 PR\n  - [x] [Issue 提交](./models/General-Setting/04-Issue\u0026PR\u0026update.md) @肖鸿儒\n  - [x] [PR 提交](./models/General-Setting/04-Issue\u0026PR\u0026update.md) @肖鸿儒\n  - [x] [fork更新](./models/General-Setting/04-Issue\u0026PR\u0026update.md) @肖鸿儒\n\n## 致谢\n\n### 核心贡献者\n\n- [宋志学(不要葱姜蒜)-项目负责人](https://github.com/KMnO4-zx) （Datawhale成员-中国矿业大学(北京)）\n- [邹雨衡-项目负责人](https://github.com/logan-zou) （Datawhale成员-对外经济贸易大学）\n- [肖鸿儒](https://github.com/Hongru0306) （Datawhale成员-同济大学）\n- [郭志航](https://github.com/acwwt)（内容创作者）\n- [林泽毅](https://github.com/Zeyi-Lin)（内容创作者-SwanLab产品负责人）\n- [张帆](https://github.com/zhangfanTJU)（内容创作者-Datawhale成员）\n- [姜舒凡](https://github.com/Tsumugii24)（内容创作者-Datawhale成员）\n- [李娇娇](https://github.com/Aphasia0515) （Datawhale成员）\n- [丁悦](https://github.com/dingyue772) （Datawhale-鲸英助教）\n- [王泽宇](https://github.com/moyitech)（内容创作者-太原理工大学-鲸英助教）\n- [惠佳豪](https://github.com/L4HeyXiao) （Datawhale-宣传大使）\n- [王茂霖](https://github.com/mlw67)（内容创作者-Datawhale成员）\n- [孙健壮](https://github.com/Caleb-Sun-jz)（内容创作者-对外经济贸易大学）\n- [东东](https://github.com/LucaChen)（内容创作者-谷歌开发者机器学习技术专家）\n- [高立业](https://github.com/0-yy-0)（内容创作者-DataWhale成员）\n- [荞麦](https://github.com/yeyeyeyeeeee)（内容创作者-Datawhale成员）\n- [Kailigithub](https://github.com/Kailigithub) （Datawhale成员）\n- [郑皓桦](https://github.com/BaiYu96) （内容创作者）\n- [李柯辰](https://github.com/Joe-2002) （Datawhale成员）\n- [程宏](https://github.com/chg0901)（内容创作者-Datawhale意向成员）\n- [骆秀韬](https://github.com/anine09)（内容创作者-Datawhale成员-似然实验室）\n- [陈思州](https://github.com/jjyaoao) （Datawhale成员）\n- [散步](https://github.com/sanbuphy) （Datawhale成员）\n- [颜鑫](https://github.com/thomas-yanxin) （Datawhale成员）\n- [杜森](https://github.com/study520ai520)（内容创作者-Datawhale成员-南阳理工学院）\n- [Swiftie](https://github.com/cswangxiaowei) （小米NLP算法工程师）\n- [黄柏特](https://github.com/KashiwaByte)（内容创作者-西安电子科技大学）\n- [张友东](https://github.com/AXYZdong)（内容创作者-Datawhale成员）\n- [余洋](https://github.com/YangYu-NUAA)（内容创作者-Datawhale成员）\n- [张晋](https://github.com/Jin-Zhang-Yaoguang)（内容创作者-Datawhale成员）\n- [娄天奥](https://github.com/lta155)（内容创作者-中国科学院大学-鲸英助教）\n- [左春生](https://github.com/LinChentang)（内容创作者-Datawhale成员）\n- [杨卓](https://github.com/little1d)（内容创作者-西安电子科技大学-鲸英助教）\n- [小罗](https://github.com/lyj11111111) （内容创作者-Datawhale成员）\n- [邓恺俊](https://github.com/Kedreamix)（内容创作者-Datawhale成员）\n- [赵文恺](https://github.com/XiLinky)（内容创作者-太原理工大学-鲸英助教）\n- [付志远](https://github.com/comfzy)（内容创作者-海南大学）\n- [郑远婧](https://github.com/isaacahahah)（内容创作者-鲸英助教-福州大学）\n- [谭逸珂](https://github.com/LikeGiver)（内容创作者-对外经济贸易大学）\n- [王熠明](https://github.com/Bald0Wang)（内容创作者-Datawhale成员）\n- [何至轩](https://github.com/pod2c)（内容创作者-鲸英助教）\n- [康婧淇](https://github.com/jodie-kang)（内容创作者-Datawhale成员）\n- [三水](https://github.com/sssanssss)（内容创作者-鲸英助教）\n- [杨晨旭](https://github.com/langlibai66)（内容创作者-太原理工大学-鲸英助教）\n- [赵伟](https://github.com/2710932616)（内容创作者-鲸英助教）\n- [苏向标](https://github.com/gzhuuser)（内容创作者-广州大学-鲸英助教）\n- [陈睿](https://github.com/riannyway)（内容创作者-西交利物浦大学-鲸英助教）\n- [林恒宇](https://github.com/LINHYYY)（内容创作者-广东东软学院-鲸英助教）\n- [张龙斐](https://github.com/Feimike09)（内容创作者-鲸英助教）\n- [孙超](https://github.com/anarchysaiko)（内容创作者-Datawhale成员）\n\n\u003e 注：排名根据贡献程度排序\n\n### 其他\n\n- 特别感谢[@Sm1les](https://github.com/Sm1les)对本项目的帮助与支持\n- 部分lora代码和讲解参考仓库：https://github.com/zyds/transformers-code.git\n- 如果有任何想法可以联系我们 DataWhale 也欢迎大家多多提出 issue\n- 特别感谢以下为教程做出贡献的同学！\n\n\n\u003cdiv align=center style=\"margin-top: 30px;\"\u003e\n  \u003ca href=\"https://github.com/datawhalechina/self-llm/graphs/contributors\"\u003e\n    \u003cimg src=\"https://contrib.rocks/image?repo=datawhalechina/self-llm\" /\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\n### Star History\n\n\u003cdiv align=center style=\"margin-top: 30px;\"\u003e\n  \u003cimg src=\"./images/star-history-2024129.png\"/\u003e\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatawhalechina%2Fself-llm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdatawhalechina%2Fself-llm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatawhalechina%2Fself-llm/lists"}