{"data":{"slug":"openmoss-moss","name":"MOSS","tagline":"An open-source, tool-augmented conversational language model from Fudan University","github_url":"https://github.com/OpenMOSS/MOSS","owner":"OpenMOSS","repo":"MOSS","owner_avatar_url":"https://avatars.githubusercontent.com/u/156300419?v=4","primary_language":"Python","stars":12253,"forks":1127,"topics":["chatgpt","deep-learning","dialogue-systems","large-language-models","natural-language-processing","text-generation"],"archived":false,"github_pushed_at":"2026-09-06T06:19:22+00:00","maintenance_label":"Active","stars_delta_30d":39,"url":"https://www.graphcanon.com/tools/openmoss-moss","markdown_url":"https://www.graphcanon.com/tools/openmoss-moss.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openmoss-moss","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openmoss-moss","description":"An open-source, tool-augmented conversational language model from Fudan University","homepage_url":"https://txsun1997.github.io/blogs/moss.html","license":"Apache-2.0","open_issues":243,"watchers":124,"ai_summary":"MOSS is an open-source conversational language model that supports bilingual dialogue and tool invocation. It provides models, dialogue data, deployment, and fine-tuning code.","readme_excerpt":"# MOSS\n<p align=\"center\" width=\"100%\">\n<a href=\"https://txsun1997.github.io/blogs/moss.html\" target=\"_blank\"><img src=\"https://txsun1997.github.io/images/moss.png\" alt=\"MOSS\" style=\"width: 50%; min-width: 300px; display: block; margin: auto;\"></a>\n</p>\n\n\n\n\n\n[[论文](https://link.springer.com/article/10.1007/s11633-024-1502-8)][[中文版](https://github.com/OpenMOSS/MOSS/blob/main/README.md)] [[English](https://github.com/OpenMOSS/MOSS/blob/main/README_en.md)] [[官方微信群](https://github.com/OpenMOSS/MOSS/blob/main/examples/WeChatGroupQR.jpg)]\n\n**MOSS 是支持中英双语对话与工具调用的开源语言模型。本仓库提供 MOSS-003 系列模型、对话数据、部署与微调代码。**\n\n**从这里开始：** [模型下载](#模型) · [硬件要求](#硬件要求) · [本地运行](#robot-本地部署) · [微调](#fire-微调)\n\n查看 OpenMOSS 的更多项目：[MOSS-TTS](https://github.com/OpenMOSS/MOSS-TTS) · [MOSS-VL](https://github.com/OpenMOSS/MOSS-VL) · [MOVA](https://github.com/OpenMOSS/MOVA) · [OpenMOSS](https://github.com/OpenMOSS).\n\n## 目录\n\n- [开源清单](#spiral_notepad-开源清单)\n  - [模型](#模型)\n  - [数据](#数据)\n  - [工程方案](#工程方案)\n- [介绍](#fountain_pen-介绍)\n- [本地部署](#robot-本地部署)\n  - [硬件要求](#硬件要求)\n  - [下载安装](#下载安装)\n  - [使用示例](#使用示例)\n- [微调](#fire-微调)\n  - [软件依赖](#软件依赖)\n  - [使用方法](#使用方法)\n- [友情链接](#link-友情链接)\n- [未来计划](#construction-未来计划)\n- [开源协议](#page_with_curl-开源协议)\n\n----\n\n## :spiral_notepad: 开源清单\n\n### 模型\n\n- [**moss-moon-003-base**](https://huggingface.co/OpenMOSS-Team/moss-moon-003-base): MOSS-003基座模型，在高质量中英文语料上自监督预训练得到，预训练语料包含约700B单词，计算量约6.67x10<sup>22</sup>次浮点数运算。\n- [**moss-moon-003-sft**](https://huggingface.co/OpenMOSS-Team/moss-moon-003-sft): 基座模型在约110万多轮对话数据上微调得到，具有指令遵循能力、多轮对话能力、规避有害请求能力。\n- [**moss-moon-003-sft-plugin**](https://huggingface.co/OpenMOSS-Team/moss-moon-003-sft-plugin): 基座模型在约110万多轮对话数据和约30万插件增强的多轮对话数据上微调得到，在`moss-moon-003-sft`基础上还具备使用搜索引擎、文生图、计算器、解方程等四种插件的能力。\n- [**moss-moon-003-sft-int4**](https://huggingface.co/OpenMOSS-Team/moss-moon-003-sft-int4/tree/main): 4bit量化版本的`moss-moon-003-sft`模型，约占用12GB显存即可进行推理。\n- [**moss-moon-003-sft-int8**](https://huggingface.co/OpenMOSS-Team/moss-moon-003-sft-int8): 8bit量化版本的`moss-moon-003-sft`模型，约占用24GB显存即可进行推理。\n- [**moss-moon-003-sft-plugin-int4**](https://huggingface.co/OpenMOSS-Team/moss-moon-003-sft-plugin-int4): 4bit量化版本的`moss-moon-003-sft-plugin`模型，约占用12GB显存即可进行推理。\n- [**moss-moon-003-sft-plugin-int8**](https://huggingface.co/OpenMOSS-Team/moss-moon-003-sft-plugin-int8): 8bit量化版本的`moss-moon-003-sft-plugin`模型，约占用24GB显存即可进行推理。\n- **moss-moon-003-pm**: 在基于`moss-moon-003-sft`收集到的偏好反馈数据上训练得到的偏好模型，将在近期开源。\n- **moss-moon-003**: 在`moss-moon-003-sft`基础上经过偏好模型`moss-moon-003-pm`训练得到的最终模型，具备更好的事实性和安全性以及更稳定的回复质量，将在近期开源。\n- **moss-moon-003-plugin**: 在`moss-moon-003-sft-plugin`基础上经过偏好模型`moss-moon-003-pm`训练得到的最终模型，具备更强的意图理解能力和插件使用能力，将在近期开源。\n\n### 数据\n\n- [**moss-002-sft-data**](https://huggingface.co/datasets/OpenMOSS-Team/moss-002-sft-data): MOSS-002所使用的多轮对话数据，覆盖有用性、忠实性、无害性三个层面，包含由`text-davinci-003`生成的约57万条英文对话和59万条中文对话。\n- [**moss-003-sft-data**](https://github.com/OpenMOSS/MOSS/tree/main/SFT_data): `moss-moon-003-sft`所使用的多轮对话数据，基于MOSS-002内测阶段采集的约10万用户输入数据和`gpt-3.5-turbo`构造而成，相比`moss-002-sft-data`，`moss-003-sft-data`更加符合真实用户意图分布，包含更细粒度的有用性类别标记、更广泛的无害性数据和更长对话轮数，约含110万条对话数据。完整数据已全部开源。\n- [**moss-003-sft-plugin-data**](https://github.com/OpenMOSS/MOSS/tree/main/SFT_data/conversations/conversation_with_plugins): `moss-moon-003-sft-plugin`所使用的插件增强的多轮对话数据，包含支持搜索引擎、文生图、计算器、解方程等四个插件在内的约30万条多轮对话数据。已[开源](https://huggingface.co/datasets/OpenMOSS-Team/moss-003-sft-data/tree/main)所有数据。\n- **moss-003-pm-data**: `moss-moon-003-pm`所使用的偏好数据，包含在约18万额外对话上下文数据及使用`moss-moon-003-sft`所产生的回复数据上构造得到的偏好对比数据，将在近期开源。\n\n### 工程方案\n\n- [**MOSS Vortex**](https://github.com/OpenLMLab/MOSS_Vortex) - MOSS部署和推理方案\n- [**MOSS WebSearchTool**](https://github.com/OpenLMLab/MOSS_WebSearchTool) - MOSS搜索引擎插件部署方案\n- [**MOSS Frontend**](https://github.com/singularity-s0/MOSS_frontend) - 基于flutter实现的MOSS-003前端界面\n- [**MOSS Backend**](https://github.com/JingYiJun/MOSS_backend) - 基于Go实现的MOSS-003后端\n\n## :fountain_pen: 介绍\n\nMOSS是一个支持中英双语和多种插件的开源对话语言模型，`moss-moon`系列模型具有160亿参数，在FP16精度下可在单张A100/A800或两张3090显卡运行，在INT4/8精度下可在单张3090显","github_created_at":"2023-04-15T14:07:44+00:00","created_at":"2026-07-07T17:33:56.154784+00:00","updated_at":"2026-09-20T04:33:38.046267+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"chatgpt","name":"chatgpt"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"dialogue-systems","name":"dialogue-systems"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"natural-language-processing","name":"natural language processing"},{"slug":"text-generation","name":"text-generation"}],"trust":{"provenance":{"is_fork":false,"github_id":628296906,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:49:17.687Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":12,"last_release_at":null,"stars_delta_30d":39,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":80,"high_count":0,"last_scan_at":"2026-09-18T08:49:19.330Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:49:16.616Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:49:16.616Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:49:16.616Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use MOSS when you need a conversational language model that supports both Chinese and English dialogue.","Consider MOSS if you require a model that can invoke external tools such as search engines, image generation, calculators, and equation solvers.","Use MOSS for projects that benefit from a model fine-tuned on a large dataset of over 110 million dialogues, ensuring better command-following, multi-turn dialogue, and harmful request avoidance."],"when_not_to_use":["Avoid MOSS if your project requires a model that is not open-source or if you prefer proprietary solutions.","Do not use MOSS if your application does not require support for tool invocation or if you need a model that is not bilingual.","If your project has strict hardware limitations and cannot meet the minimum requirements for running MOSS, such as the need for at least 12GB of GPU memory for the 4-bit quantized version, consider a轻"],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:21:01.613Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"MOSS is an open-source conversational language model from Fudan University that supports bilingual dialogue and tool invocation. It offers various models, dialogue data, deployment, and fine-tuning code."}]}}