[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-explosion--spacy-models":3,"tool-explosion--spacy-models":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",160411,2,"2026-04-18T23:33:24",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",109154,"2026-04-18T11:18:24",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":76,"owner_email":77,"owner_twitter":76,"owner_website":78,"owner_url":79,"languages":80,"stars":85,"forks":86,"last_commit_at":87,"license":76,"difficulty_score":88,"env_os":89,"env_gpu":89,"env_ram":89,"env_deps":90,"category_tags":94,"github_topics":95,"view_count":32,"oss_zip_url":76,"oss_zip_packed_at":76,"status":17,"created_at":102,"updated_at":103,"faqs":104,"releases":105},9441,"explosion\u002Fspacy-models","spacy-models","💫  Models for the spaCy Natural Language Processing (NLP) library","spacy-models 是专为 spaCy 自然语言处理库打造的预训练模型集合，旨在让开发者无需从零开始训练，即可快速获得高质量的文本分析能力。它有效解决了 NLP 领域中数据准备耗时、训练门槛高以及模型复用难的痛点，用户只需一条命令就能下载并集成针对特定语言和优化目标的模型。\n\n这套资源主要面向人工智能开发者、数据科学家及 NLP 研究人员，同时也适合需要快速构建文本处理功能的技术团队。其核心亮点在于科学严谨的命名规范：通过名称即可直观识别模型的语言、功能类型（如实体识别、句法分析）、训练语料来源（如新闻、网络文本）以及规模大小（是否包含词向量）。此外，模型版本号清晰对应了兼容的 spaCy 主次要版本与具体的模型迭代配置，确保了环境部署的稳定性与可追溯性。无论是进行原型开发还是生产环境部署，spacy-models 都能提供灵活、透明且高效的解决方案，帮助用户轻松跨越从理论到应用的鸿沟。","\u003Ca href=\"https:\u002F\u002Fexplosion.ai\">\u003Cimg src=\"https:\u002F\u002Fexplosion.ai\u002Fassets\u002Fimg\u002Flogo.svg\" width=\"125\" height=\"125\" align=\"right\" \u002F>\u003C\u002Fa>\n\n# spaCy models\n\nThis repository contains\n[releases](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases) of models for\nthe [spaCy](https:\u002F\u002Fgithub.com\u002Fexplosion\u002FspaCy) NLP library. For more info on\nhow to download, install and use the models, see the [models\ndocumentation](https:\u002F\u002Fspacy.io\u002Fusage\u002Fmodels).\n\n> **⚠️ Important note:** Because the models can be very large and consist mostly\n> of binary data, we can't simply provide them as files in a GitHub repository.\n> Instead, we've opted for adding them to\n> [releases](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases) as `.whl` and\n> `.tar.gz` files. This allows us to still maintain a public release history.\n\n## Quickstart\n\nTo install a specific model, run the following command with the model name (for\nexample `en_core_web_sm`):\n\n```bash\npython -m spacy download [model]\n```\n\n- [spaCy v3.x models directory](https:\u002F\u002Fspacy.io\u002Fmodels)\n- [spaCy v3.x model comparison](https:\u002F\u002Fspacy.io\u002Fusage\u002Ffacts-figures#spacy-models)\n- [spaCy v2.x models directory](https:\u002F\u002Fv2.spacy.io\u002Fmodels)\n- [spaCy v2.x model comparison](https:\u002F\u002Fv2.spacy.io\u002Fusage\u002Ffacts-figures#spacy-models)\n- [Individual release notes](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases)\n\nFor the spaCy v1.x models, [see here](#spacy-v1x-releases).\n\n## Model naming conventions\n\nIn general, spaCy expects all model packages to follow the naming convention of\n`[lang]_[name]`. For our provided pipelines, we divide the name into three\ncomponents:\n\n- **type**: Model capabilities:\n  - `core`: a general-purpose model with tagging, parsing, lemmatization and\n    named entity recognition\n  - `dep`: only tagging, parsing and lemmatization\n  - `ent`: only named entity recognition\n  - `sent`: only sentence segmentation\n- **genre**: Type of text the model is trained on (e.g. `web` for web text,\n  `news` for news text)\n- **size**: Model size indicator:\n  - `sm`: no word vectors\n  - `md`: reduced word vector table with 20k unique vectors for ~500k words\n  - `lg`: large word vector table with ~500k entries\n\nFor example, `en_core_web_md` is a medium-sized English model trained on\nwritten web text (blogs, news, comments), that includes a tagger, a dependency\nparser, a lemmatizer, a named entity recognizer and a word vector table with\n20k unique vectors.\n\n### Model versioning\n\nAdditionally, the model versioning reflects both the compatibility with spaCy,\nas well as the model version. A model version `a.b.c` translates to:\n\n- `a`: **spaCy major version**. For example, `2` for spaCy v2.x.\n- `b`: **spaCy minor version**. For example, `3` for spaCy v2.3.x.\n- `c`: **Model version.** Different model config: e.g. from being trained on\n  different data, with different parameters, for different numbers of\n  iterations, with different vectors, etc.\n\nFor a detailed compatibility overview, see the\n[`compatibility.json`](compatibility.json). This is also the source of spaCy's\ninternal compatibility check, performed when you run the `download` command.\n\n### Support for older versions\n\nIf you're using an older version (v1.6.0 or below), you can still download and\ninstall the old models from within spaCy using `python -m spacy.en.download all`\nor `python -m spacy.de.download all`. The `.tar.gz` archives are also\n[attached to the v1.6.0 release](https:\u002F\u002Fgithub.com\u002Fexplosion\u002FspaCy\u002Ftree\u002Fv1.6.0).\nTo download and install the models manually, unpack the archive, drop the\ncontained directory into `spacy\u002Fdata` and load the model via `spacy.load('en')`\nor `spacy.load('de')`.\n\n## Downloading models\n\nTo increase transparency and make it easier to use spaCy with your own models,\nall data is now available as direct downloads, organised in\n[individual releases](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases). spaCy\n1.7 also supports installing and loading models as **Python packages**. You can\nnow choose how and where you want to keep the data files, and set up \"shortcut\nlinks\" to load models by name from within spaCy. For more info on this, see the\nnew [models documentation](https:\u002F\u002Fspacy.io\u002Fusage\u002Fmodels).\n\n```bash\n# download best-matching version of specific model for your spaCy installation\npython -m spacy download en_core_web_sm\n\n# pip install .whl or .tar.gz archive from path or URL\npip install \u002FUsers\u002Fyou\u002Fen_core_web_sm-3.0.0.tar.gz\npip install \u002FUsers\u002Fyou\u002Fen_core_web_sm-3.0.0-py3-none-any.whl\npip install https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_sm-3.0.0\u002Fen_core_web_sm-3.0.0.tar.gz\npip install https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_sm-3.0.0\u002Fen_core_web_sm-3.0.0-py3-none-any.whl\n```\n\n## Loading and using models\n\nTo load a model, use `spacy.load()` with the model name, a shortcut link or\na path to the model data directory.\n\n```python\nimport spacy\nnlp = spacy.load(\"en_core_web_sm\")\ndoc = nlp(u\"This is a sentence.\")\n```\n\nYou can also `import` a model directly via its full name and then call its\n`load()` method with no arguments. This should also work for older models\nin previous versions of spaCy.\n\n```python\nimport spacy\nimport en_core_web_sm\n\nnlp = en_core_web_sm.load()\ndoc = nlp(u\"This is a sentence.\")\n```\n\n## Manual download and installation\n\nIn some cases, you might prefer downloading the data manually, for example to\nplace it into a custom directory. You can download the model via your browser\nfrom the [latest releases](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases),\nor configure your own download script using the URL of the archive file. The\narchive consists of a model directory that contains another directory with the\nmodel data.\n\n```yaml\n└── en_core_web_md-3.0.0.tar.gz       # downloaded archive\n    ├── setup.py                      # setup file for pip installation\n    ├── meta.json                     # copy of pipeline meta\n    └── en_core_web_md                # 📦 pipeline package\n        ├── __init__.py               # init for pip installation\n        └── en_core_web_md-3.0.0      # pipeline data\n            ├── config.cfg            # pipeline config\n            ├── meta.json             # pipeline meta\n            └── ...                   # directories with component data\n```\n\n**📖 For more info and examples, check out the [models documentation](https:\u002F\u002Fspacy.io\u002Fusage\u002Fmodels).**\n\n## spaCy v1.x Releases\n\n| Date         | Model                 | Version | Dep | Ent | Vec |    Size | License  |                                       |                                      |\n| ------------ | --------------------- | ------- | :-: | :-: | :-: | ------: | -------- | ------------------------------------- | ------------------------------------ |\n| `2017-06-06` | `es_core_web_md`      | 1.0.0   |  X  |  X  |  X  |  377 MB | CC BY-SA | [![][i]][i-es_core_web_md-1.0.0]      | [![][dl]][es_core_web_md-1.0.0]      |\n| `2017-04-26` | `fr_depvec_web_lg`    | 1.0.0   |  X  |     |  X  | 1.33 GB | CC BY-NC | [![][i]][i-fr_depvec_web_lg-1.0.0]    | [![][dl]][fr_depvec_web_lg-1.0.0]    |\n| `2017-03-21` | `en_core_web_md`      | 1.2.1   |  X  |  X  |  X  |    1 GB | CC BY-SA | [![][i]][i-en_core_web_md-1.2.1]      | [![][dl]][en_core_web_md-1.2.1]      |\n| `2017-03-21` | `en_depent_web_md`    | 1.2.1   |  X  |  X  |     |  328 MB | CC BY-SA | [![][i]][i-en_depent_web_md-1.2.1]    | [![][dl]][en_depent_web_md-1.2.1]    |\n| `2017-03-17` | `en_core_web_sm`      | 1.2.0   |  X  |  X  |  X  |   50 MB | CC BY-SA | [![][i]][i-en_core_web_sm-1.2.0]      | [![][dl]][en_core_web_sm-1.2.0]      |\n| `2017-03-17` | `en_core_web_md`      | 1.2.0   |  X  |  X  |  X  |    1 GB | CC BY-SA | [![][i]][i-en_core_web_md-1.2.0]      | [![][dl]][en_core_web_md-1.2.0]      |\n| `2017-03-17` | `en_depent_web_md`    | 1.2.0   |  X  |  X  |     |  328 MB | CC BY-SA | [![][i]][i-en_depent_web_md-1.2.0]    | [![][dl]][en_depent_web_md-1.2.0]    |\n| `2016-05-10` | `de_core_news_md`     | 1.0.0   |  X  |  X  |  X  |  645 MB | CC BY-SA | [![][i]][i-de_core_news_md-1.0.0]     | [![][dl]][de_core_news_md-1.0.0]     |\n| `2016-03-08` | `en_vectors_glove_md` | 1.0.0   |     |     |  X  |  727 MB | CC BY-SA | [![][i]][i-en_vectors_glove_md-1.0.0] | [![][dl]][en_vectors_glove_md-1.0.0] |\n\n[es_core_web_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fes_core_web_md-1.0.0\u002Fes_core_web_md-1.0.0.tar.gz\n[fr_depvec_web_lg-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Ffr_depvec_web_lg-1.0.0\u002Ffr_depvec_web_lg-1.0.0.tar.gz\n[en_core_web_md-1.2.1]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_md-1.2.1\u002Fen_core_web_md-1.2.1.tar.gz\n[en_depent_web_md-1.2.1]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_depent_web_md-1.2.1\u002Fen_depent_web_md-1.2.1.tar.gz\n[en_core_web_sm-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_sm-1.2.0\u002Fen_core_web_sm-1.2.0.tar.gz\n[en_core_web_md-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_md-1.2.0\u002Fen_core_web_md-1.2.0.tar.gz\n[en_depent_web_md-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_depent_web_md-1.2.0\u002Fen_depent_web_md-1.2.0.tar.gz\n[de_core_news_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fde_core_news_md-1.0.0\u002Fde_core_news_md-1.0.0.tar.gz\n[en_vectors_glove_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_vectors_glove_md-1.0.0\u002Fen_vectors_glove_md-1.0.0.tar.gz\n[i-es_core_web_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fes_core_web_md-1.0.0\n[i-fr_depvec_web_lg-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Ffr_depvec_web_lg-1.0.0\n[i-en_core_web_md-1.2.1]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_core_web_md-1.2.1\n[i-en_depent_web_md-1.2.1]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_depent_web_md-1.2.1\n[i-en_core_web_sm-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_core_web_sm-1.2.0\n[i-en_core_web_md-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_core_web_md-1.2.0\n[i-en_depent_web_md-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_depent_web_md-1.2.0\n[i-de_core_news_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fde_core_news_md-1.0.0\n[i-en_vectors_glove_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_vectors_glove_md-1.0.0\n[dl]: http:\u002F\u002Fi.imgur.com\u002FgQvPgr0.png\n[i]: http:\u002F\u002Fi.imgur.com\u002FOpLOcKn.png\n\n### Model naming conventions for v1.x models\n\n- **type**: Model capabilities (e.g. `core` for general-purpose model with\n  vocabulary, syntax, entities and word vectors, or `depent` for only vocab,\n  syntax and entities)\n- **genre**: Type of text the model is trained on (e.g. `web` for web text,\n  `news` for news text)\n- **size**: Model size indicator (`sm`, `md` or `lg`)\n\nFor example, `en_depent_web_md` is a medium-sized English model trained on\nwritten web text (blogs, news, comments), that includes vocabulary, syntax and\nentities.\n\n## Issues and bug reports\n\nTo report an issue with a model, please open an issue on the\n[spaCy issue tracker](https:\u002F\u002Fgithub.com\u002Fexplosion\u002FspaCy).\nPlease note that no model is perfect. Because models are statistical, their\nexpected behaviour **will always include some errors**. However, particular\nerrors can indicate deeper issues with the training feature extraction or\noptimisation code. If you come across patterns in the model's performance that\nseem suspicious, please do file a report.\n","\u003Ca href=\"https:\u002F\u002Fexplosion.ai\">\u003Cimg src=\"https:\u002F\u002Fexplosion.ai\u002Fassets\u002Fimg\u002Flogo.svg\" width=\"125\" height=\"125\" align=\"right\" \u002F>\u003C\u002Fa>\n\n# spaCy 模型\n\n此仓库包含 [spaCy](https:\u002F\u002Fgithub.com\u002Fexplosion\u002FspaCy) NLP 库的模型\n[发布](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases)。有关如何下载、安装和使用这些模型的更多信息，请参阅 [模型文档](https:\u002F\u002Fspacy.io\u002Fusage\u002Fmodels)。\n\n> **⚠️ 重要提示：** 由于模型文件可能非常庞大，且主要由二进制数据组成，我们无法直接将它们作为文件放在 GitHub 仓库中。相反，我们选择将其以 `.whl` 和 `.tar.gz` 文件的形式添加到\n> [发布页面](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases)，这样我们仍然可以维护公开的发布历史。\n\n## 快速入门\n\n要安装特定模型，请使用以下命令并指定模型名称（例如 `en_core_web_sm`）：\n\n```bash\npython -m spacy download [model]\n```\n\n- [spaCy v3.x 模型目录](https:\u002F\u002Fspacy.io\u002Fmodels)\n- [spaCy v3.x 模型比较](https:\u002F\u002Fspacy.io\u002Fusage\u002Ffacts-figures#spacy-models)\n- [spaCy v2.x 模型目录](https:\u002F\u002Fv2.spacy.io\u002Fmodels)\n- [spaCy v2.x 模型比较](https:\u002F\u002Fv2.spacy.io\u002Fusage\u002Ffacts-figures#spacy-models)\n- [单个版本发布说明](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases)\n\n关于 spaCy v1.x 的模型，请参阅下方的 [spaCy v1.x 发布](#spacy-v1x-releases)。\n\n## 模型命名规范\n\n通常，spaCy 要求所有模型包遵循 `[lang]_[name]` 的命名规范。对于我们提供的管道模型，我们将名称分为三个部分：\n\n- **类型**：模型功能：\n  - `core`：通用模型，包含标注、句法分析、词形还原和命名实体识别。\n  - `dep`：仅包含标注、句法分析和词形还原。\n  - `ent`：仅包含命名实体识别。\n  - `sent`：仅包含句子分割。\n- **语料类型**：模型训练所用文本的类型（例如 `web` 表示网络文本，`news` 表示新闻文本）。\n- **大小**：模型规模标识：\n  - `sm`：不包含词向量。\n  - `md`：精简版词向量表，包含约 2 万个唯一向量，覆盖约 50 万个词汇。\n  - `lg`：大型词向量表，包含约 50 万个条目。\n\n例如，`en_core_web_md` 是一个中等规模的英语模型，基于书面网络文本（博客、新闻、评论）训练而成，包含标注器、依存句法分析器、词形还原器、命名实体识别器以及一个包含 2 万个唯一向量的词向量表。\n\n### 模型版本控制\n\n此外，模型版本号同时反映了与 spaCy 的兼容性以及模型本身的版本。模型版本 `a.b.c` 的含义如下：\n\n- `a`：**spaCy 主版本号**。例如，`2` 表示 spaCy v2.x。\n- `b`：**spaCy 次版本号**。例如，`3` 表示 spaCy v2.3.x。\n- `c`：**模型版本号**。不同的模型配置：例如，可能基于不同数据集训练、采用不同参数、经过不同迭代次数、使用不同向量等。\n\n有关详细的兼容性概述，请参阅 [`compatibility.json`](compatibility.json)。这也是 spaCy 内部兼容性检查的来源，当您运行 `download` 命令时会进行该检查。\n\n### 对旧版本的支持\n\n如果您使用的是较旧版本（v1.6.0 或更低），仍可通过 spaCy 下载并安装旧模型，方法是运行 `python -m spacy.en.download all` 或 `python -m spacy.de.download all`。`.tar.gz` 归档文件也已附在 [v1.6.0 发布](https:\u002F\u002Fgithub.com\u002Fexplosion\u002FspaCy\u002Ftree\u002Fv1.6.0)中。如需手动下载并安装模型，只需解压归档文件，将其中的目录放入 `spacy\u002Fdata` 目录，然后通过 `spacy.load('en')` 或 `spacy.load('de')` 加载模型。\n\n## 下载模型\n\n为提高透明度并使您更轻松地将 spaCy 与自定义模型结合使用，所有数据现均以直接下载的方式提供，并按\n[单个版本发布](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases) 进行组织。spaCy 1.7 还支持将模型作为 **Python 包** 安装和加载。现在您可以自由选择存储数据文件的位置，并设置“快捷链接”以便通过模型名称从 spaCy 中加载模型。有关详细信息，请参阅新的 [模型文档](https:\u002F\u002Fspacy.io\u002Fusage\u002Fmodels)。\n\n```bash\n# 根据您的 spaCy 安装下载最匹配的特定模型版本\npython -m spacy download en_core_web_sm\n\n# 从路径或 URL 安装 .whl 或 .tar.gz 归档文件\npip install \u002FUsers\u002Fyou\u002Fen_core_web_sm-3.0.0.tar.gz\npip install \u002FUsers\u002Fyou\u002Fen_core_web_sm-3.0.0-py3-none-any.whl\npip install https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_sm-3.0.0\u002Fen_core_web_sm-3.0.0.tar.gz\npip install https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_sm-3.0.0\u002Fen_core_web_sm-3.0.0-py3-none-any.whl\n```\n\n## 加载和使用模型\n\n要加载模型，可使用 `spacy.load()` 方法，传入模型名称、快捷链接或模型数据目录的路径。\n\n```python\nimport spacy\nnlp = spacy.load(\"en_core_web_sm\")\ndoc = nlp(u\"这是一个句子。\")\n```\n\n您也可以直接通过模型的完整名称导入模型，然后调用其 `load()` 方法而无需传递任何参数。这种方法同样适用于 spaCy 早期版本中的旧模型。\n\n```python\nimport spacy\nimport en_core_web_sm\n\nnlp = en_core_web_sm.load()\ndoc = nlp(u\"这是一个句子。\")\n```\n\n## 手动下载和安装\n\n在某些情况下，您可能更倾向于手动下载数据，例如将其放置在自定义目录中。您可以从 [最新发布](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases) 页面通过浏览器下载模型，或者使用归档文件的 URL 编写自己的下载脚本。归档文件包含一个模型目录，该目录下又包含一个存放模型数据的子目录。\n\n```yaml\n└── en_core_web_md-3.0.0.tar.gz       # 下载的归档文件\n    ├── setup.py                      # 用于 pip 安装的设置文件\n    ├── meta.json                     # 管道元数据副本\n    └── en_core_web_md                # 📦 管道包\n        ├── __init__.py               # 用于 pip 安装的初始化文件\n        └── en_core_web_md-3.0.0      # 管道数据\n            ├── config.cfg            # 管道配置文件\n            ├── meta.json             # 管道元数据\n            └── ...                   # 包含组件数据的目录\n```\n\n**📖 更多信息和示例，请参阅 [模型文档](https:\u002F\u002Fspacy.io\u002Fusage\u002Fmodels)。**\n\n## spaCy v1.x 版本发布\n\n| 日期         | 模型                 | 版本 | 依 | 实 | 向 |    大小 | 许可证  |                                       |                                      |\n| ------------ | --------------------- | ------- | :-: | :-: | :-: | ------: | -------- | ------------------------------------- | ------------------------------------ |\n| `2017-06-06` | `es_core_web_md`      | 1.0.0   |  X  |  X  |  X  |  377 MB | CC BY-SA | [![][i]][i-es_core_web_md-1.0.0]      | [![][dl]][es_core_web_md-1.0.0]      |\n| `2017-04-26` | `fr_depvec_web_lg`    | 1.0.0   |  X  |     |  X  | 1.33 GB | CC BY-NC | [![][i]][i-fr_depvec_web_lg-1.0.0]    | [![][dl]][fr_depvec_web_lg-1.0.0]    |\n| `2017-03-21` | `en_core_web_md`      | 1.2.1   |  X  |  X  |  X  |    1 GB | CC BY-SA | [![][i]][i-en_core_web_md-1.2.1]      | [![][dl]][en_core_web_md-1.2.1]      |\n| `2017-03-21` | `en_depent_web_md`    | 1.2.1   |  X  |  X  |     |  328 MB | CC BY-SA | [![][i]][i-en_depent_web_md-1.2.1]    | [![][dl]][en_depent_web_md-1.2.1]    |\n| `2017-03-17` | `en_core_web_sm`      | 1.2.0   |  X  |  X  |  X  |   50 MB | CC BY-SA | [![][i]][i-en_core_web_sm-1.2.0]      | [![][dl]][en_core_web_sm-1.2.0]      |\n| `2017-03-17` | `en_core_web_md`      | 1.2.0   |  X  |  X  |  X  |    1 GB | CC BY-SA | [![][i]][i-en_core_web_md-1.2.0]      | [![][dl]][en_core_web_md-1.2.0]      |\n| `2017-03-17` | `en_depent_web_md`    | 1.2.0   |  X  |  X  |     |  328 MB | CC BY-SA | [![][i]][i-en_depent_web_md-1.2.0]    | [![][dl]][en_depent_web_md-1.2.0]    |\n| `2016-05-10` | `de_core_news_md`     | 1.0.0   |  X  |  X  |  X  |  645 MB | CC BY-SA | [![][i]][i-de_core_news_md-1.0.0]     | [![][dl]][de_core_news_md-1.0.0]     |\n| `2016-03-08` | `en_vectors_glove_md` | 1.0.0   |     |     |  X  |  727 MB | CC BY-SA | [![][i]][i-en_vectors_glove_md-1.0.0] | [![][dl]][en_vectors_glove_md-1.0.0] |\n\n[es_core_web_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fes_core_web_md-1.0.0\u002Fes_core_web_md-1.0.0.tar.gz\n[fr_depvec_web_lg-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Ffr_depvec_web_lg-1.0.0\u002Ffr_depvec_web_lg-1.0.0.tar.gz\n[en_core_web_md-1.2.1]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_md-1.2.1\u002Fen_core_web_md-1.2.1.tar.gz\n[en_depent_web_md-1.2.1]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_depent_web_md-1.2.1\u002Fen_depent_web_md-1.2.1.tar.gz\n[en_core_web_sm-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_sm-1.2.0\u002Fen_core_web_sm-1.2.0.tar.gz\n[en_core_web_md-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_md-1.2.0\u002Fen_core_web_md-1.2.0.tar.gz\n[en_depent_web_md-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_depent_web_md-1.2.0\u002Fen_depent_web_md-1.2.0.tar.gz\n[de_core_news_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fde_core_news_md-1.0.0\u002Fde_core_news_md-1.0.0.tar.gz\n[en_vectors_glove_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_vectors_glove_md-1.0.0\u002Fen_vectors_glove_md-1.0.0.tar.gz\n[i-es_core_web_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fes_core_web_md-1.0.0\n[i-fr_depvec_web_lg-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Ffr_depvec_web_lg-1.0.0\n[i-en_core_web_md-1.2.1]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_core_web_md-1.2.1\n[i-en_depent_web_md-1.2.1]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_depent_web_md-1.2.1\n[i-en_core_web_sm-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_core_web_sm-1.2.0\n[i-en_core_web_md-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_core_web_md-1.2.0\n[i-en_depent_web_md-1.2.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_depent_web_md-1.2.0\n[i-de_core_news_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fde_core_news_md-1.0.0\n[i-en_vectors_glove_md-1.0.0]: https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fen_vectors_glove_md-1.0.0\n[dl]: http:\u002F\u002Fi.imgur.com\u002FgQvPgr0.png\n[i]: http:\u002F\u002Fi.imgur.com\u002FOpLOcKn.png\n\n### v1.x 版本模型命名规范\n\n- **类型**: 模型功能（例如，`core` 表示通用模型，包含词汇表、句法、实体和词向量；`depent` 表示仅包含词汇表、句法和实体）\n- **文体**: 模型训练所用文本的类型（例如，`web` 表示网络文本，`news` 表示新闻文本）\n- **大小**: 模型规模标识（`sm`、`md` 或 `lg`）\n\n例如，`en_depent_web_md` 是一个中等规模的英语模型，基于书面网络文本（博客、新闻、评论）训练而成，包含词汇表、句法和实体。\n\n## 问题与错误报告\n\n如需报告模型相关问题，请在 [spaCy 问题跟踪器](https:\u002F\u002Fgithub.com\u002Fexplosion\u002FspaCy) 上提交问题。请注意，没有任何模型是完美的。由于这些模型基于统计方法，其预期行为**始终会包含一些错误**。然而，某些特定的错误可能表明训练特征提取或优化代码存在更深层次的问题。如果您发现模型性能中存在可疑的模式，请务必提交报告。","# spaCy 模型快速上手指南\n\n## 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n*   **操作系统**：支持 Linux、macOS 或 Windows。\n*   **Python 版本**：建议 Python 3.6+（具体取决于您安装的 spaCy 版本）。\n*   **前置依赖**：必须先安装 `spacy` 库。\n    ```bash\n    pip install spacy\n    ```\n*   **网络环境**：下载模型需要访问 GitHub Releases。如果直接下载速度慢，建议配置代理或使用支持断点续传的工具下载 `.whl` \u002F `.tar.gz` 文件后本地安装。\n\n## 安装步骤\n\nspaCy 模型以独立的 Python 包形式发布。推荐使用命令行工具自动下载并安装与当前 spaCy 版本最匹配的模型。\n\n### 方法一：自动下载（推荐）\n\n使用 spaCy 内置的下载命令，将 `[model]` 替换为您需要的模型名称（例如 `en_core_web_sm`）：\n\n```bash\npython -m spacy download [model]\n```\n\n**常用模型示例：**\n*   英语小型模型：`python -m spacy download en_core_web_sm`\n*   英语中型模型：`python -m spacy download en_core_web_md`\n*   中文小型模型：`python -m spacy download zh_core_web_sm`\n\n### 方法二：手动安装\n\n如果您需要离线安装或指定特定版本，可以从 [GitHub Releases](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases) 下载 `.whl` 或 `.tar.gz` 文件，然后使用 `pip` 安装：\n\n```bash\n# 从本地路径安装\npip install \u002Fpath\u002Fto\u002Fen_core_web_sm-3.0.0.tar.gz\n\n# 或直接通过 URL 安装\npip install https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_sm-3.0.0\u002Fen_core_web_sm-3.0.0-py3-none-any.whl\n```\n\n## 基本使用\n\n安装完成后，您可以通过以下两种加载模型并开始处理文本。\n\n### 方式 A：通过模型名称加载（推荐）\n\n这是最常用的方式，适用于已安装为 Python 包的模型。\n\n```python\nimport spacy\n\n# 加载模型\nnlp = spacy.load(\"en_core_web_sm\")\n\n# 处理文本\ndoc = nlp(u\"This is a sentence.\")\n\n# 打印分词结果\nfor token in doc:\n    print(token.text, token.pos_)\n```\n\n### 方式 B：直接导入模块加载\n\n您也可以像导入普通 Python 库一样直接导入模型包：\n\n```python\nimport spacy\nimport en_core_web_sm\n\n# 加载模型\nnlp = en_core_web_sm.load()\n\n# 处理文本\ndoc = nlp(u\"This is a sentence.\")\n```\n\n> **提示**：模型命名规则通常为 `[语言]_[类型]_[来源]_[大小]`。例如 `en_core_web_sm` 表示：英语 (`en`) + 通用核心功能 (`core`) + 网络文本训练 (`web`) + 小型无词向量 (`sm`)。更多模型详情可查阅 [spaCy 官方模型目录](https:\u002F\u002Fspacy.io\u002Fmodels)。","某电商数据团队需要每日自动处理数万条全球用户的英文评论，以提取产品缺陷关键词并统计情感倾向。\n\n### 没有 spacy-models 时\n- 开发人员必须从零收集语料库并手动训练命名实体识别（NER）模型，耗时数周且难以保证准确率。\n- 缺乏预训练的词向量支持，导致系统无法识别\"battery life\"与\"battery duration\"等语义相似的表达，分析结果支离破碎。\n- 不同版本的 NLP 组件兼容性混乱，团队需花费大量时间调试依赖冲突，阻碍了自动化流水线的部署。\n- 只能基于简单的关键词匹配进行提取，无法区分句子结构，经常误将用户提到的“竞争对手产品缺点”当作自家产品的反馈。\n\n### 使用 spacy-models 后\n- 通过一行命令 `python -m spacy download en_core_web_md` 即可获取包含分词、句法分析及实体识别的成熟模型，实现当天部署。\n- 利用模型内置的 20k 唯一词向量表，系统能精准理解上下文语义，将不同表述的同一缺陷自动归类，大幅提升统计精度。\n- 模型版本与 spaCy 库严格对应，内部兼容性检查机制消除了环境配置错误，确保了生产环境的长期稳定运行。\n- 借助预训练的句法依赖解析能力，系统能准确锁定主语和宾语关系，有效过滤掉无关的对比信息，只保留针对自家产品的真实反馈。\n\nspacy-models 将原本需要数周研发的 NLP 能力转化为即插即用的标准化组件，让团队能专注于业务逻辑而非底层算法构建。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fexplosion_spacy-models_725159d7.png","explosion","Explosion","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fexplosion_6bc9ac84.png","Software company specializing in developer tools and tailored solutions for AI and Natural Language Processing",null,"contact@explosion.ai","https:\u002F\u002Fexplosion.ai","https:\u002F\u002Fgithub.com\u002Fexplosion",[81],{"name":82,"color":83,"percentage":84},"Python","#3572A5",100,1860,315,"2026-04-17T20:25:09",1,"未说明",{"notes":91,"python":89,"dependencies":92},"模型文件较大，不以源码形式直接存放在仓库中，而是通过 releases 以 .whl 或 .tar.gz 格式提供。可通过 'python -m spacy download [模型名]' 命令安装，或使用 pip 手动安装下载的文件。模型版本命名规则反映了与 spaCy 主版本、次版本的兼容性以及模型自身的迭代版本。旧版本 (v1.6.0 及以下) 用户需使用特定的下载命令或手动解压到 spacy\u002Fdata 目录。",[93],"spacy",[14,35],[93,96,97,98,99,100,101,64],"nlp","natural-language-processing","machine-learning","models","machine-learning-models","statistical-models","2026-03-27T02:49:30.150509","2026-04-19T09:17:44.526127",[],[106,111,116,120,125,130,135,140,145,150,155,160,164,169,174,179,184,189,194,199],{"id":107,"version":108,"summary_zh":109,"released_at":110},334446,"en_core_web_hftrf-3.8.1","针对 `spacy-transformers>=1.4.0` 和 `spacy>=3.8.0` 重新打包的英文 Transformer 管道（roberta-base）。\n\n这是 `en_core_web_trf` 3.6.1 模型，包含以下改动：\n- 将 Transformer 权重从 PyTorch 的 pickle 格式转换为 safetensors 格式\n- 更新了对 spacy 3.8.x 和 spacy-transformers 1.4.x 的依赖版本约束\n- 重命名为 `en_core_web_hftrf`，以避免与官方模型发生冲突\n\n## 安装\n\n```bash\npip install https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fen_core_web_hftrf-3.8.1\u002Fen_core_web_hftrf-3.8.1-py3-none-any.whl\n```\n\n## 使用\n\n```python\nimport spacy\nnlp = spacy.load(\"en_core_web_hftrf\")\ndoc = nlp(\"Apple is looking at buying U.K. startup for $1 billion\")\nprint([(ent.text, ent.label_) for ent in doc.ents])\n# [('Apple', 'ORG'), ('U.K.', 'GPE'), ('$1 billion', 'MONEY')]\n```","2026-03-20T10:24:57",{"id":112,"version":113,"summary_zh":114,"released_at":115},334447,"zh_core_web_lg-3.8.0","[![下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fzh_core_web_lg-3.8.0\u002Fzh_core_web_lg-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fzh_core_web_lg-3.8.0\u002Fzh_core_web_lg-3.8.0.tar.gz) [![下载量 (wheel 格式)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fzh_core_web_lg-3.8.0\u002Fzh_core_web_lg-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fzh_core_web_lg-3.8.0\u002Fzh_core_web_lg-3.8.0-py3-none-any.whl)\n\n> **.tar.gz 校验和:** `f5ba75104f5a07854503461a6bbaf7bb34232e9a8b746953a3a46e1478380c34`\u003Cbr \u002F>**.whl 校验和:** `eb39f5deb382752d3faef4052fb61570b7f45441076082b2a1fdbe50a8848e7c`\n\n### 详情: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fzh#zh_core_web_lg\n\n专为 CPU 优化的中文处理流水线。包含组件：tok2vec、词性标注器、依存句法分析器、句子边界检测器、命名实体识别器以及属性规则匹配器。\n\n| 特性 | 描述 |\n| --- | --- |\n| **名称** | `zh_core_web_lg` |\n| **版本** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **默认流水线** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `ner` |\n| **组件** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `ner` |\n| **向量** | 500,000 个键，500,000 个唯一向量（300 维） |\n| **来源** | [OntoNotes 5](https:\u002F\u002Fcatalog.ldc.upenn.edu\u002FLDC2013T19)（Ralph Weischedel、Martha Palmer、Mitchell Marcus、Eduard Hovy、Sameer Pradhan、Lance Ramshaw、Nianwen Xue、Ann Taylor、Jeff Kaufman、Michelle Franchini、Mohammed El-Bachouti、Robert Belvin、Ann Houston）\u003Cbr \u002F>[CoreNLP Universal Dependencies 转换器](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fstanford-dependencies.html)（斯坦福 NLP 小组）\u003Cbr \u002F>[Explosion fastText 向量（cbow，OSCAR Common Crawl + Wikipedia）](https:\u002F\u002Fspacy.io)（Explosion）|\n| **许可证** | `MIT` |\n| **作者** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **模型大小** | 575 MB |\n\n### 标签体系\n\n\u003Cdetails>\n\n\u003Csummary>查看标签体系（3 个组件共 100 个标签）\u003C\u002Fsummary>\n\n| 组件 | 标签 |\n| --- | --- |\n| **`tagger`** | `AD`、`AS`、`BA`、`CC`、`CD`、`CS`、`DEC`、`DEG`、`DER`、`DEV`、`DT`、`ETC`、`FW`、`IJ`、`INF`、`JJ`、`LB`、`LC`、`M`、`MSP`、`NN`、`NR`、`NT`、`OD`、`ON`、`P`、`PN`、`PU`、`SB`、`SP`、`URL`、`VA`、`VC`、`VE`、`VV`、`X`、`_SP` |\n| **`parser`** | `ROOT`、`acl`、`advcl:loc`、`advmod`、`advmod:dvp`、`advmod:loc`、`advmod:rcomp`、`amod`、`amod:ordmod`、`appos`、`aux:asp`、`aux:ba`、`aux:modal`、`aux:prtmod`、`auxpass`、`case`、`cc`、`ccomp`、`compound:nn`、`compound:vc`、`conj`、`cop`、`dep`、`det`、`discourse`、`dobj`、`etc`、`mark`、`mark:clf`、`name`、`neg`、`nmod`、`nmod:assmod`、`nmod:poss`、`nmod:prep`、`nmod:range`、`nmod:tmod`、`nmod:topic`、`nsubj`、`nsubj:xsubj`、`nsubjpass`、`nummod`、`parataxis:prnmod`、`punct`、`xcomp` |\n| **`ner`** | `CARDINAL`、`DATE`、`EVENT`、`FAC`、`GPE`、`LANGUAGE`、`LAW`、`LOC`、`MONEY`、`NORP`、`ORDINAL`、`ORG`、`PERCENT`、`PERSON`、`PRODUCT`、`QUANTITY`、`TIME`、`WORK_OF_ART` |\n\n\u003C\u002Fdetails>\n\n### 准确率","2024-09-30T09:59:57",{"id":117,"version":118,"summary_zh":119,"released_at":115},334448,"zh_core_web_md-3.8.0","[![下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fzh_core_web_md-3.8.0\u002Fzh_core_web_md-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fzh_core_web_md-3.8.0\u002Fzh_core_web_md-3.8.0.tar.gz) [![下载量（wheel）](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fzh_core_web_md-3.8.0\u002Fzh_core_web_md-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fzh_core_web_md-3.8.0\u002Fzh_core_web_md-3.8.0-py3-none-any.whl)\n\n> **.tar.gz 校验和:** `42cd04e0f406cbddf6aab5b9665c89a23de45456526c43d4875b10fd193573f8`\u003Cbr \u002F>**.whl 校验和:** `bcf300540fbd15b1b0aac358f327f2a31de8992b346162d5600f843514da0e98`\n\n### 详情：https:\u002F\u002Fspacy.io\u002Fmodels\u002Fzh#zh_core_web_md\n\n针对 CPU 优化的中文处理管道。组件包括：tok2vec、词性标注器、依存句法分析器、句子边界检测器、命名实体识别器以及属性规则匹配器。\n\n| 特性 | 描述 |\n| --- | --- |\n| **名称** | `zh_core_web_md` |\n| **版本** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **默认管道** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `ner` |\n| **组件** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `ner` |\n| **向量** | 500,000 个键，20,000 个唯一向量（300 维） |\n| **来源** | [OntoNotes 5](https:\u002F\u002Fcatalog.ldc.upenn.edu\u002FLDC2013T19)（Ralph Weischedel、Martha Palmer、Mitchell Marcus、Eduard Hovy、Sameer Pradhan、Lance Ramshaw、Nianwen Xue、Ann Taylor、Jeff Kaufman、Michelle Franchini、Mohammed El-Bachouti、Robert Belvin、Ann Houston）\u003Cbr \u002F>[CoreNLP Universal Dependencies 转换器](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fstanford-dependencies.html)（斯坦福 NLP 小组）\u003Cbr \u002F>[Explosion fastText 向量（cbow，OSCAR Common Crawl + Wikipedia）](https:\u002F\u002Fspacy.io)（Explosion）|\n| **许可证** | `MIT` |\n| **作者** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **模型大小** | 74 MB |\n\n### 标签体系\n\n\u003Cdetails>\n\n\u003Csummary>查看标签体系（3 个组件共 100 个标签）\u003C\u002Fsummary>\n\n| 组件 | 标签 |\n| --- | --- |\n| **`tagger`** | `AD`, `AS`, `BA`, `CC`, `CD`, `CS`, `DEC`, `DEG`, `DER`, `DEV`, `DT`, `ETC`, `FW`, `IJ`, `INF`, `JJ`, `LB`, `LC`, `M`, `MSP`, `NN`, `NR`, `NT`, `OD`, `ON`, `P`, `PN`, `PU`, `SB`, `SP`, `URL`, `VA`, `VC`, `VE`, `VV`, `X`, `_SP` |\n| **`parser`** | `ROOT`, `acl`, `advcl:loc`, `advmod`, `advmod:dvp`, `advmod:loc`, `advmod:rcomp`, `amod`, `amod:ordmod`, `appos`, `aux:asp`, `aux:ba`, `aux:modal`, `aux:prtmod`, `auxpass`, `case`, `cc`, `ccomp`, `compound:nn`, `compound:vc`, `conj`, `cop`, `dep`, `det`, `discourse`, `dobj`, `etc`, `mark`, `mark:clf`, `name`, `neg`, `nmod`, `nmod:assmod`, `nmod:poss`, `nmod:prep`, `nmod:range`, `nmod:tmod`, `nmod:topic`, `nsubj`, `nsubj:xsubj`, `nsubjpass`, `nummod`, `parataxis:prnmod`, `punct`, `xcomp` |\n| **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `TIME`, `WORK_OF_ART` |\n\n\u003C\u002Fdetails>\n\n### 准确率",{"id":121,"version":122,"summary_zh":123,"released_at":124},334449,"zh_core_web_sm-3.8.0","[![下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fzh_core_web_sm-3.8.0\u002Fzh_core_web_sm-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fzh_core_web_sm-3.8.0\u002Fzh_core_web_sm-3.8.0.tar.gz) [![下载量 (wheel 格式)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fzh_core_web_sm-3.8.0\u002Fzh_core_web_sm-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fzh_core_web_sm-3.8.0\u002Fzh_core_web_sm-3.8.0-py3-none-any.whl)\n\n> **.tar.gz 校验和:** `b099841a3f8c0e591ffff295c4aa30b243c3d7cc21446ff5ca2fac52792c34ea`\u003Cbr \u002F>**.whl 校验和:** `7de3bd267176b9b2a8defb6997c1cd296da16c57b5e712f72ea44a51755421c8`\n\n### 详情：https:\u002F\u002Fspacy.io\u002Fmodels\u002Fzh#zh_core_web_sm\n\n针对 CPU 优化的中文处理流水线。包含组件：tok2vec、词性标注器、依存句法分析器、句子分割器、命名实体识别器、属性规则匹配器。\n\n| 特性 | 描述 |\n| --- | --- |\n| **名称** | `zh_core_web_sm` |\n| **版本** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **默认流水线** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `ner` |\n| **组件** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `ner` |\n| **向量** | 0 个键，0 个唯一向量（0 维） |\n| **来源** | [OntoNotes 5](https:\u002F\u002Fcatalog.ldc.upenn.edu\u002FLDC2013T19)（Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston）\u003Cbr \u002F>[CoreNLP 通用依存句法转换器](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fstanford-dependencies.html)（斯坦福 NLP 小组） |\n| **许可证** | `MIT` |\n| **作者** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **模型大小** | 46 MB |\n\n### 标签体系\n\n\u003Cdetails>\n\n\u003Csummary>查看标签体系（3 个组件共 100 个标签）\u003C\u002Fsummary>\n\n| 组件 | 标签 |\n| --- | --- |\n| **`tagger`** | `AD`, `AS`, `BA`, `CC`, `CD`, `CS`, `DEC`, `DEG`, `DER`, `DEV`, `DT`, `ETC`, `FW`, `IJ`, `INF`, `JJ`, `LB`, `LC`, `M`, `MSP`, `NN`, `NR`, `NT`, `OD`, `ON`, `P`, `PN`, `PU`, `SB`, `SP`, `URL`, `VA`, `VC`, `VE`, `VV`, `X`, `_SP` |\n| **`parser`** | `ROOT`, `acl`, `advcl:loc`, `advmod`, `advmod:dvp`, `advmod:loc`, `advmod:rcomp`, `amod`, `amod:ordmod`, `appos`, `aux:asp`, `aux:ba`, `aux:modal`, `aux:prtmod`, `auxpass`, `case`, `cc`, `ccomp`, `compound:nn`, `compound:vc`, `conj`, `cop`, `dep`, `det`, `discourse`, `dobj`, `etc`, `mark`, `mark:clf`, `name`, `neg`, `nmod`, `nmod:assmod`, `nmod:poss`, `nmod:prep`, `nmod:range`, `nmod:tmod`, `nmod:topic`, `nsubj`, `nsubj:xsubj`, `nsubjpass`, `nummod`, `parataxis:prnmod`, `punct`, `xcomp` |\n| **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `TIME`, `WORK_OF_ART` |\n\n\u003C\u002Fdetails>\n\n### 准确率\n\n| 类型 | 分数 |\n| --- | --- |\n| `TOKEN_ACC` | 95.85 |\n| `TOKEN_P` | 94.58 |\n| `TOKEN_R` | 91.36 |\n| `TOKEN_F","2024-09-30T09:59:56",{"id":126,"version":127,"summary_zh":128,"released_at":129},334450,"xx_sent_ud_sm-3.8.0","[![下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fxx_sent_ud_sm-3.8.0\u002Fxx_sent_ud_sm-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fxx_sent_ud_sm-3.8.0\u002Fxx_sent_ud_sm-3.8.0.tar.gz) [![下载量 (wheel 格式)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fxx_sent_ud_sm-3.8.0\u002Fxx_sent_ud_sm-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fxx_sent_ud_sm-3.8.0\u002Fxx_sent_ud_sm-3.8.0-py3-none-any.whl)\n\n> **.tar.gz 校验和:** `d895d6ce9e1a70139fa9096e2d2809d8d20a306e4e3d5ef0beb3d66d87a09edf`\u003Cbr \u002F>**.whl 校验和:** `1b5fb9321723b395f76458d2a13b7a3673c537eb58c0a9df3778f4e0950180b4`\n\n### 详情: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fxx#xx_sent_ud_sm\n\n适用于 CPU 的多语言管道。组件：senter。\n\n| 特性 | 描述 |\n| --- | --- |\n| **名称** | `xx_sent_ud_sm` |\n| **版本** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **默认管道** | `senter` |\n| **组件** | `senter` |\n| **向量** | 0 个键，0 个唯一向量（0 维） |\n| **来源** | [Universal Dependencies v2.8 (UD_Afrikaans-AfriBooms, UD_Croatian-SET, UD_Czech-CAC, UD_Czech-CLTT, UD_Danish-DDT, UD_Dutch-Alpino, UD_Dutch-LassySmall, UD_English-EWT, UD_Finnish-FTB, UD_Finnish-TDT, UD_French-GSD, UD_French-Spoken, UD_German-GSD, UD_Indonesian-GSD, UD_Irish-IDT, UD_Italian-TWITTIRO, UD_Korean-GSD, UD_Korean-Kaist, UD_Latvian-LVTB, UD_Lithuanian-ALKSNIS, UD_Lithuanian-HSE, UD_Marathi-UFAL, UD_Norwegian-Bokmaal, UD_Norwegian-Nynorsk, UD_Norwegian-NynorskLIA, UD_Persian-Seraji, UD_Portuguese-Bosque, UD_Portuguese-GSD, UD_Romanian-Nonstandard, UD_Romanian-RRT, UD_Russian-GSD, UD_Russian-Taiga, UD_Serbian-SET, UD_Slovak-SNK, UD_Spanish-GSD, UD_Swedish-Talbanken, UD_Telugu-MTG, UD_Vietnamese-VTB)](https:\u002F\u002Funiversaldependencies.org\u002F) (Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell; 等) |\n| **许可证** | `CC BY-SA 3.0` |\n| **作者** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **模型大小** | 4 MB |\n\n### 标签体系\n\n\n\n### 准确率\n\n| 类型 | 分数 |\n| --- | --- |\n| `TOKEN_ACC` | 98.59 |\n| `TOKEN_P` | 95.31 |\n| `TOKEN_R` | 95.72 |\n| `TOKEN_F` | 95.52 |\n| `SENTS_P` | 90.67 |\n| `SENTS_R` | 81.49 |\n| `SENTS_F` | 85.83 |\n\n### 安装\n\n```bash\npip install spacy\npython -m spacy download xx_sent_ud_sm\n```","2024-09-30T09:59:58",{"id":131,"version":132,"summary_zh":133,"released_at":134},334451,"uk_core_news_lg-3.8.0","[![下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fuk_core_news_lg-3.8.0\u002Fuk_core_news_lg-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fuk_core_news_lg-3.8.0\u002Fuk_core_news_lg-3.8.0.tar.gz) [![下载量 (wheel 格式)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fuk_core_news_lg-3.8.0\u002Fuk_core_news_lg-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fuk_core_news_lg-3.8.0\u002Fuk_core_news_lg-3.8.0-py3-none-any.whl)\n\n> **.tar.gz 校验和:** `491b50d0804262709108b5ae5a5058f70bc945aae54452993cb7e9ae1284a324`\u003Cbr \u002F>**.whl 校验和:** `60b56f8fa5525925cf8e6266a80e907431c3d475f874c75c68b62f3e12620b0b`\n\n### 详情: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fuk#uk_core_news_lg\n\n专为 CPU 优化的乌克兰语处理管道。包含组件：tok2vec、词法分析器、依存句法分析器、句子边界检测器、命名实体识别器、属性规则匹配器、词形还原器。\n\n| 特性 | 描述 |\n| --- | --- |\n| **名称** | `uk_core_news_lg` |\n| **版本** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **默认管道** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **组件** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **向量** | floret (200000, 300) |\n| **来源** | [Ukr-Synth (e5d9eaf3)](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fukr-models\u002FUkr-Synth) (Volodymyr Kurnosov)\u003Cbr \u002F>[Explosion 向量 (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-vectors-builder) (Explosion) |\n| **许可证** | `MIT` |\n| **作者** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **模型大小** | 220 MB |\n\n### 标签体系\n\n\u003Cdetails>\n\n\u003Csummary>查看标签体系（3 个组件共 1211 个标签）\u003C\u002Fsummary>\n\n| 组件 | 标签 |\n| --- | --- |\n| **`morphologizer`** | `POS=CCONJ`, `Degree=Cmp\\|POS=ADV`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Animacy=Inan\\|Case=Nom\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Gen\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Inan\\|Case=Ins\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `POS=PUNCT`, `Case=Gen\\|Number=Plur\\|POS=DET\\|PronType=Dem`, `Animacy=Inan\\|Case=Gen\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `POS=ADV\\|PronType=Rel`, `POS=PART`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin`, `Aspect=Imp\\|POS=VERB\\|VerbForm=Inf`, `Animacy=Inan\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Acc\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Case=Loc\\|POS=ADP`, `Case=Loc\\|Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Animacy=Inan\\|Case=Loc\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|NameType=Giv\\|Number=Sing\\|POS=PROPN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|NameType=Sur\\|Number=Sing\\|POS=PROPN`, `POS=ADV`, `Aspect=Imp\\|Gender=Masc\\|Moo","2024-09-30T10:00:03",{"id":136,"version":137,"summary_zh":138,"released_at":139},334452,"uk_core_news_md-3.8.0","[![下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fuk_core_news_md-3.8.0\u002Fuk_core_news_md-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fuk_core_news_md-3.8.0\u002Fuk_core_news_md-3.8.0.tar.gz) [![下载量 (wheel 格式)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fuk_core_news_md-3.8.0\u002Fuk_core_news_md-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fuk_core_news_md-3.8.0\u002Fuk_core_news_md-3.8.0-py3-none-any.whl)\n\n> **.tar.gz 校验和:** `707b00a61684c9095fe7c56c5509833c152e85d0c60cea4ead5d71f0ed9d7457`\u003Cbr \u002F>**.whl 校验和:** `583c65ab55d6bdbe3b3ebe86978bf4f6a8aab0b6778ea8c4c5ab529722abaafd`\n\n### 详情: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fuk#uk_core_news_md\n\n针对 CPU 优化的乌克兰语处理管道。组件包括：tok2vec、形态分析器、依存句法分析器、句子边界检测器、命名实体识别器、属性规则匹配器和词形还原器。\n\n| 特性 | 描述 |\n| --- | --- |\n| **名称** | `uk_core_news_md` |\n| **版本** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **默认管道** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **组件** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **词向量** | floret (50000, 300) |\n| **来源** | [Ukr-Synth (e5d9eaf3)](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fukr-models\u002FUkr-Synth) (Volodymyr Kurnosov)\u003Cbr \u002F>[Explosion 词向量 (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-vectors-builder) (Explosion) |\n| **许可证** | `MIT` |\n| **作者** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **模型大小** | 65 MB |\n\n### 标签体系\n\n\u003Cdetails>\n\n\u003Csummary>查看标签体系（3 个组件共 1211 个标签）\u003C\u002Fsummary>\n\n| 组件 | 标签 |\n| --- | --- |\n| **`morphologizer`** | `POS=CCONJ`, `Degree=Cmp\\|POS=ADV`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Animacy=Inan\\|Case=Nom\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Gen\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Inan\\|Case=Ins\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `POS=PUNCT`, `Case=Gen\\|Number=Plur\\|POS=DET\\|PronType=Dem`, `Animacy=Inan\\|Case=Gen\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `POS=ADV\\|PronType=Rel`, `POS=PART`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin`, `Aspect=Imp\\|POS=VERB\\|VerbForm=Inf`, `Animacy=Inan\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Acc\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Case=Loc\\|POS=ADP`, `Case=Loc\\|Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Animacy=Inan\\|Case=Loc\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|NameType=Giv\\|Number=Sing\\|POS=PROPN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|NameType=Sur\\|Number=Sing\\|POS=PROPN`, `POS=ADV`, `Aspect=Imp\\|Gender=Masc\\|Mood=","2024-09-30T10:00:02",{"id":141,"version":142,"summary_zh":143,"released_at":144},334453,"uk_core_news_sm-3.8.0","[![下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fuk_core_news_sm-3.8.0\u002Fuk_core_news_sm-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fuk_core_news_sm-3.8.0\u002Fuk_core_news_sm-3.8.0.tar.gz) [![下载量（wheel）](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fuk_core_news_sm-3.8.0\u002Fuk_core_news_sm-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fuk_core_news_sm-3.8.0\u002Fuk_core_news_sm-3.8.0-py3-none-any.whl)\n\n> **.tar.gz 校验和:** `777fdbcd482a6e66ef278e2f739cc2e5f934295f02df4c0ec8b9c060f2b59624`\u003Cbr \u002F>**.whl 校验和:** `d20adb50b42c0dcfdedf4994dabcb96789a64983a9ab560d0c6c38a59e8efb58`\n\n### 详情：https:\u002F\u002Fspacy.io\u002Fmodels\u002Fuk#uk_core_news_sm\n\n针对 CPU 优化的乌克兰语处理管道。组件包括：tok2vec、形态分析器、依存句法分析器、句子边界检测器、命名实体识别器、属性规则匹配器和词形还原器。\n\n| 特性 | 描述 |\n| --- | --- |\n| **名称** | `uk_core_news_sm` |\n| **版本** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **默认管道** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **组件** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **向量** | 0 个键，0 个唯一向量（0 维） |\n| **来源** | [Ukr-Synth (e5d9eaf3)](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fukr-models\u002FUkr-Synth)（Volodymyr Kurnosov） |\n| **许可证** | `MIT` |\n| **作者** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **模型大小** | 14 MB |\n\n### 标签体系\n\n\u003Cdetails>\n\n\u003Csummary>查看标签体系（3 个组件共 1211 个标签）\u003C\u002Fsummary>\n\n| 组件 | 标签 |\n| --- | --- |\n| **`morphologizer`** | `POS=CCONJ`, `Degree=Cmp\\|POS=ADV`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Animacy=Inan\\|Case=Nom\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Gen\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Inan\\|Case=Ins\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `POS=PUNCT`, `Case=Gen\\|Number=Plur\\|POS=DET\\|PronType=Dem`, `Animacy=Inan\\|Case=Gen\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `POS=ADV\\|PronType=Rel`, `POS=PART`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin`, `Aspect=Imp\\|POS=VERB\\|VerbForm=Inf`, `Animacy=Inan\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Acc\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Case=Loc\\|POS=ADP`, `Case=Loc\\|Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Animacy=Inan\\|Case=Loc\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|NameType=Giv\\|Number=Sing\\|POS=PROPN`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|NameType=Sur\\|Number=Sing\\|POS=PROPN`, `POS=ADV`, `Aspect=Imp\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin`, `Animacy=Inan\\|Case=Loc\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Case=Gen","2024-09-30T10:00:01",{"id":146,"version":147,"summary_zh":148,"released_at":149},334454,"xx_ent_wiki_sm-3.8.0","[![下载次数](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fxx_ent_wiki_sm-3.8.0\u002Fxx_ent_wiki_sm-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fxx_ent_wiki_sm-3.8.0\u002Fxx_ent_wiki_sm-3.8.0.tar.gz) [![下载次数 (wheel 文件)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fxx_ent_wiki_sm-3.8.0\u002Fxx_ent_wiki_sm-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fxx_ent_wiki_sm-3.8.0\u002Fxx_ent_wiki_sm-3.8.0-py3-none-any.whl)\n\n> **.tar.gz 校验和:** `a0f0f1be6faa96300abf9d711f7d5a326698333ba8f21f9f9e0e12bf92f6be6b`\u003Cbr \u002F>**.whl 校验和:** `6f3c4b853852ea9e9d2dc76cc950dddb10a7e4c42d813308caefe6c5e8be2f0a`\n\n### 详情: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fxx#xx_ent_wiki_sm\n\n多语言管道，针对 CPU 优化。组件：ner。\n\n| 特性 | 描述 |\n| --- | --- |\n| **名称** | `xx_ent_wiki_sm` |\n| **版本** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **默认管道** | `ner` |\n| **组件** | `ner` |\n| **向量** | 0 个键，0 个唯一向量（0 维） |\n| **来源** | [WikiNER](https:\u002F\u002Ffigshare.com\u002Farticles\u002FLearning_multilingual_named_entity_recognition_from_Wikipedia\u002F5462500)（乔尔·诺斯曼、尼基·林格兰、威尔·拉德福德、塔拉·墨菲、詹姆斯·R·柯兰） |\n| **许可证** | `MIT` |\n| **作者** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **模型大小** | 10 MB |\n\n### 标签体系\n\n\u003Cdetails>\n\n\u003Csummary>查看标签体系（1 个组件，共 4 个标签）\u003C\u002Fsummary>\n\n| 组件 | 标签 |\n| --- | --- |\n| **`ner`** | `LOC`, `MISC`, `ORG`, `PER` |\n\n\u003C\u002Fdetails>\n\n### 准确率\n\n| 类型 | 分数 |\n| --- | --- |\n| `ENTS_P` | 83.57 |\n| `ENTS_R` | 82.71 |\n| `ENTS_F` | 83.14 |\n\n### 安装\n\n```bash\npip install spacy\npython -m spacy download xx_ent_wiki_sm\n```","2024-09-30T09:59:59",{"id":151,"version":152,"summary_zh":153,"released_at":154},334455,"sv_core_news_lg-3.8.0","[![下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsv_core_news_lg-3.8.0\u002Fsv_core_news_lg-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsv_core_news_lg-3.8.0\u002Fsv_core_news_lg-3.8.0.tar.gz) [![下载量 (wheel 文件)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsv_core_news_lg-3.8.0\u002Fsv_core_news_lg-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsv_core_news_lg-3.8.0\u002Fsv_core_news_lg-3.8.0-py3-none-any.whl)\n\n> **.tar.gz 校验和:** `82a4b3d96e643f9d5c559536a7d6e500a35504aaf84d31b42cc415bbd3f4e788`\u003Cbr \u002F>**.whl 校验和:** `1f1db1cb811dc21e7eaab023bb0ea4afe66038d0e6f0837b537f736503bcede3`\n\n### 详情: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fsv#sv_core_news_lg\n\n针对 CPU 优化的瑞典语处理流程。组件包括：tok2vec、词性标注器、形态分析器、依存句法分析器、词形还原器（可训练的词形还原器）、句子边界检测器、命名实体识别器。\n\n| 特性 | 描述 |\n| --- | --- |\n| **名称** | `sv_core_news_lg` |\n| **版本** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **默认管道** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |\n| **组件** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |\n| **向量** | floret (200000, 300) |\n| **来源** | [UD 瑞典语 Talbanken v2.8](https:\u002F\u002Fgithub.com\u002FUniversalDependencies\u002FUD_Swedish-Talbanken) (Nivre, Joakim; Smith, Aaron)\u003Cbr \u002F>[斯德哥尔摩-于默奥语料库 (SUC) v3.0](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FKBLab\u002Fsucx3_ner) (Språkbanken)\u003Cbr \u002F>[Explosion 向量（OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl）](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-vectors-builder) (Explosion) |\n| **许可证** | `CC BY-SA 4.0` |\n| **作者** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **模型大小** | 218 MB |\n\n### 标签体系\n\n\u003Cdetails>\n\n\u003Csummary>查看标签体系（4 个组件共 381 个标签）\u003C\u002Fsummary>\n\n| 组件 | 标签 |\n| --- | --- |\n| **`tagger`** | `AB`, `AB\\|AN`, `AB\\|KOM`, `AB\\|POS`, `AB\\|SMS`, `AB\\|SUV`, `DT\\|NEU\\|SIN\\|DEF`, `DT\\|NEU\\|SIN\\|IND`, `DT\\|NEU\\|SIN\\|IND\u002FDEF`, `DT\\|UTR\u002FNEU\\|PLU\\|DEF`, `DT\\|UTR\u002FNEU\\|PLU\\|IND`, `DT\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF`, `DT\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND`, `DT\\|UTR\u002FNEU\\|SIN\\|DEF`, `DT\\|UTR\u002FNEU\\|SIN\\|IND`, `DT\\|UTR\\|SIN\\|DEF`, `DT\\|UTR\\|SIN\\|IND`, `DT\\|UTR\\|SIN\\|IND\u002FDEF`, `HA`, `HD\\|NEU\\|SIN\\|IND`, `HD\\|UTR\u002FNEU\\|PLU\\|IND`, `HD\\|UTR\\|SIN\\|IND`, `HP\\|-\\|-\\|-`, `HP\\|NEU\\|SIN\\|IND`, `HP\\|UTR\u002FNEU\\|PLU\\|IND`, `HP\\|UTR\\|SIN\\|IND`, `HS\\|DEF`, `IE`, `IN`, `JJ`, `JJ\\|AN`, `JJ\\|KOM\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|MAS\\|SIN\\|DEF\\|GEN`, `JJ\\|POS\\|MAS\\|SIN\\|DEF\\|NOM`, `JJ\\|POS\\|NEU\\|SIN\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|NEU\\|SIN\\|IND\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|GEN`, `JJ\\|POS\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|PLU\\|IND\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|SIN\\|DEF\\|NOM`, `JJ\\|POS\\|UTR\\|-\\|-\\|SMS`, `JJ\\|POS\\|UTR\\|SIN\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|UTR\\|S","2024-09-30T10:00:05",{"id":156,"version":157,"summary_zh":158,"released_at":159},334456,"sv_core_news_md-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsv_core_news_md-3.8.0\u002Fsv_core_news_md-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsv_core_news_md-3.8.0\u002Fsv_core_news_md-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsv_core_news_md-3.8.0\u002Fsv_core_news_md-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsv_core_news_md-3.8.0\u002Fsv_core_news_md-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `57e20b2c301bfd18805ae95da728f69c6e510b77ebb5fc07826e970abf9c30cd`\u003Cbr \u002F>**Checksum .whl:** `f5e719fcf728bd5552daf70f278aba08113ce939714a070dd97f02a2aa2903bc`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fsv#sv_core_news_md\n\nSwedish pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `sv_core_news_md` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |\n| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |\n| **Vectors** | floret (50000, 300) |\n| **Sources** | [UD Swedish Talbanken v2.8](https:\u002F\u002Fgithub.com\u002FUniversalDependencies\u002FUD_Swedish-Talbanken) (Nivre, Joakim; Smith, Aaron)\u003Cbr \u002F>[Stockholm-Umeå Corpus (SUC) v3.0](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FKBLab\u002Fsucx3_ner) (Språkbanken)\u003Cbr \u002F>[Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-vectors-builder) (Explosion) |\n| **License** | `CC BY-SA 4.0` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 63 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (381 labels for 4 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`tagger`** | `AB`, `AB\\|AN`, `AB\\|KOM`, `AB\\|POS`, `AB\\|SMS`, `AB\\|SUV`, `DT\\|NEU\\|SIN\\|DEF`, `DT\\|NEU\\|SIN\\|IND`, `DT\\|NEU\\|SIN\\|IND\u002FDEF`, `DT\\|UTR\u002FNEU\\|PLU\\|DEF`, `DT\\|UTR\u002FNEU\\|PLU\\|IND`, `DT\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF`, `DT\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND`, `DT\\|UTR\u002FNEU\\|SIN\\|DEF`, `DT\\|UTR\u002FNEU\\|SIN\\|IND`, `DT\\|UTR\\|SIN\\|DEF`, `DT\\|UTR\\|SIN\\|IND`, `DT\\|UTR\\|SIN\\|IND\u002FDEF`, `HA`, `HD\\|NEU\\|SIN\\|IND`, `HD\\|UTR\u002FNEU\\|PLU\\|IND`, `HD\\|UTR\\|SIN\\|IND`, `HP\\|-\\|-\\|-`, `HP\\|NEU\\|SIN\\|IND`, `HP\\|UTR\u002FNEU\\|PLU\\|IND`, `HP\\|UTR\\|SIN\\|IND`, `HS\\|DEF`, `IE`, `IN`, `JJ`, `JJ\\|AN`, `JJ\\|KOM\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|MAS\\|SIN\\|DEF\\|GEN`, `JJ\\|POS\\|MAS\\|SIN\\|DEF\\|NOM`, `JJ\\|POS\\|NEU\\|SIN\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|NEU\\|SIN\\|IND\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|GEN`, `JJ\\|POS\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|PLU\\|IND\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|SIN\\|DEF\\|NOM`, `JJ\\|POS\\|UTR\\|-\\|-\\|SMS`, `JJ\\|POS\\|UTR\\|SIN\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|UTR\\|SIN\\|IND\\|GEN`, `JJ\\|POS\\|UTR\\|SIN\\|IND\\|NOM`, `JJ\\|SUV\\|MAS\\|SIN\\|DEF\\|NOM`, `JJ\\|SUV\\|UTR\u002FNEU\\|PLU\\|DEF\\|NOM`, `JJ\\|SUV\\|UTR\u002FNEU\\|SIN\u002FPLU\\|DEF\\|NOM`, `JJ\\|SUV\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\\|NOM`, `KN`, `MAD`, `MID`, `NN`, `NN\\|-\\|-\\|-\\|-`, `NN\\|AN`, `NN\\|NEU\\|-\\|-\\|SMS`, `NN\\|NEU\\|PLU\\|DEF\\|GEN`, `NN\\|NEU\\|PLU\\|DEF\\|NOM`, `NN\\|NEU\\|PLU\\|IND\\|GEN`, `NN\\|NEU\\|PLU\\|IND\\|NOM`, `NN\\|NEU\\|SIN\\|DEF\\|GEN`, `NN\\|NEU\\|SIN\\|DEF\\|NOM`, `NN\\|NEU\\|SIN\\|IND`, `NN\\|NEU\\|SIN\\|IND\\|GEN`, `NN\\|NEU\\|SIN\\|IND\\|NOM`, `NN\\|SMS`, `NN\\|UTR\\|-\\|-\\|-`, `NN\\|UTR\\|-\\|-\\|SMS`, `NN\\|UTR\\|PLU\\|DEF\\|GEN`, `NN\\|UTR\\|PLU\\|DEF\\|NOM`, `NN\\|UTR\\|PLU\\|IND\\|GEN`, `NN\\|UTR\\|PLU\\|IND\\|NOM`, `NN\\|UTR\\|SIN\\|DEF\\|GEN`, `NN\\|UTR\\|SIN\\|DEF\\|NOM`, `NN\\|UTR\\|SIN\\|IND\\|GEN`, `NN\\|UTR\\|SIN\\|IND\\|NOM`, `PAD`, `PC\\|PRF\\|NEU\\|SIN\\|IND\\|NOM`, `PC\\|PRF\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|GEN`, `PC\\|PRF\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|NOM`, `PC\\|PRF\\|UTR\u002FNEU\\|SIN\\|DEF\\|NOM`, `PC\\|PRF\\|UTR\\|SIN\\|IND\\|NOM`, `PC\\|PRS\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\u002FDEF\\|NOM`, `PL`, `PM`, `PM\\|GEN`, `PM\\|NOM`, `PM\\|SMS`, `PN\\|MAS\\|SIN\\|DEF\\|SUB\u002FOBJ`, `PN\\|NEU\\|SIN\\|DEF`, `PN\\|NEU\\|SIN\\|DEF\\|SUB\u002FOBJ`, `PN\\|NEU\\|SIN\\|IND\\|SUB\u002FOBJ`, `PN\\|UTR\u002FNEU\\|PLU\\|DEF\\|OBJ`, `PN\\|UTR\u002FNEU\\|PLU\\|DEF\\|SUB`, `PN\\|UTR\u002FNEU\\|PLU\\|DEF\\|SUB\u002FOBJ`, `PN\\|UTR\u002FNEU\\|PLU\\|IND\\|SUB\u002FOBJ`, `PN\\|UTR\u002FNEU\\|SIN\u002FPLU\\|DEF\\|OBJ`, `PN\\|UTR\\|PLU\\|DEF\\|OBJ`, `PN\\|UTR\\|PLU\\|DEF\\|SUB`, `PN\\|UTR\\|SIN\\|DEF\\|NOM`, `PN\\|UTR\\|SIN\\|DEF\\|OBJ`, `PN\\|UTR\\|SIN\\|DEF\\|SUB`, `PN\\|UTR\\|SIN\\|DEF\\|SUB\u002FOBJ`, `PN\\|UTR\\|SIN\\|IND\\|NOM`, `PN\\|UTR\\|SIN\\|IND\\|SUB`, `PN\\|UTR\\|SIN\\|IND\\|SUB\u002FOBJ`, `PP`, `PS\\|NEU\\|SIN\\|DEF`, `PS\\|UTR\u002FNEU\\|PLU\\|DEF`, `PS\\|UTR\u002FNEU\\|SIN\u002FPLU\\|DEF`, `PS\\|UTR\\|SIN\\|DEF`, `RG\\|NEU\\|SIN\\|IND\\|NOM`, `RG\\|NOM`, `RG\\|SMS`, `RG\\|UTR\\|SIN\\|IND\\|NOM`, `RO\\|MAS\\|SIN\\|IND\u002FDEF\\|NOM`, `RO\\|NOM`, `SN`, `UO`, `VB\\|AN`, `VB\\|IMP\\|AKT`, `VB\\|IMP\\|SFO`, `VB\\|INF\\|AKT`, `VB\\|INF\\|SFO`, `VB\\|KON\\|PRS\\|AKT`, `VB\\|KON\\|PRT\\|AKT`, `VB\\|PRS\\|AKT`, `VB\\|PRS\\|SFO`, `VB\\|PRT\\|AKT`, `VB\\|PRT\\|SFO`, `VB\\|SUP\\|AKT`, `VB\\|SUP\\|SFO`, `_SP` |\n| **`morphol","2024-09-30T10:00:04",{"id":161,"version":162,"summary_zh":163,"released_at":134},334457,"sv_core_news_sm-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsv_core_news_sm-3.8.0\u002Fsv_core_news_sm-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsv_core_news_sm-3.8.0\u002Fsv_core_news_sm-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsv_core_news_sm-3.8.0\u002Fsv_core_news_sm-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsv_core_news_sm-3.8.0\u002Fsv_core_news_sm-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `027c2f594b23d4f6f51080c462cc22fa986091fd32bea102b04ee3639f313dec`\u003Cbr \u002F>**Checksum .whl:** `be4929fb30523dca0b6672f999cdbf4d64f165419f1eed0014ca3a36599b8b4d`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fsv#sv_core_news_sm\n\nSwedish pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `sv_core_news_sm` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |\n| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |\n| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |\n| **Sources** | [UD Swedish Talbanken v2.8](https:\u002F\u002Fgithub.com\u002FUniversalDependencies\u002FUD_Swedish-Talbanken) (Nivre, Joakim; Smith, Aaron)\u003Cbr \u002F>[Stockholm-Umeå Corpus (SUC) v3.0](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FKBLab\u002Fsucx3_ner) (Språkbanken) |\n| **License** | `CC BY-SA 4.0` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 12 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (381 labels for 4 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`tagger`** | `AB`, `AB\\|AN`, `AB\\|KOM`, `AB\\|POS`, `AB\\|SMS`, `AB\\|SUV`, `DT\\|NEU\\|SIN\\|DEF`, `DT\\|NEU\\|SIN\\|IND`, `DT\\|NEU\\|SIN\\|IND\u002FDEF`, `DT\\|UTR\u002FNEU\\|PLU\\|DEF`, `DT\\|UTR\u002FNEU\\|PLU\\|IND`, `DT\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF`, `DT\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND`, `DT\\|UTR\u002FNEU\\|SIN\\|DEF`, `DT\\|UTR\u002FNEU\\|SIN\\|IND`, `DT\\|UTR\\|SIN\\|DEF`, `DT\\|UTR\\|SIN\\|IND`, `DT\\|UTR\\|SIN\\|IND\u002FDEF`, `HA`, `HD\\|NEU\\|SIN\\|IND`, `HD\\|UTR\u002FNEU\\|PLU\\|IND`, `HD\\|UTR\\|SIN\\|IND`, `HP\\|-\\|-\\|-`, `HP\\|NEU\\|SIN\\|IND`, `HP\\|UTR\u002FNEU\\|PLU\\|IND`, `HP\\|UTR\\|SIN\\|IND`, `HS\\|DEF`, `IE`, `IN`, `JJ`, `JJ\\|AN`, `JJ\\|KOM\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|MAS\\|SIN\\|DEF\\|GEN`, `JJ\\|POS\\|MAS\\|SIN\\|DEF\\|NOM`, `JJ\\|POS\\|NEU\\|SIN\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|NEU\\|SIN\\|IND\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|GEN`, `JJ\\|POS\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|PLU\\|IND\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|UTR\u002FNEU\\|SIN\\|DEF\\|NOM`, `JJ\\|POS\\|UTR\\|-\\|-\\|SMS`, `JJ\\|POS\\|UTR\\|SIN\\|IND\u002FDEF\\|NOM`, `JJ\\|POS\\|UTR\\|SIN\\|IND\\|GEN`, `JJ\\|POS\\|UTR\\|SIN\\|IND\\|NOM`, `JJ\\|SUV\\|MAS\\|SIN\\|DEF\\|NOM`, `JJ\\|SUV\\|UTR\u002FNEU\\|PLU\\|DEF\\|NOM`, `JJ\\|SUV\\|UTR\u002FNEU\\|SIN\u002FPLU\\|DEF\\|NOM`, `JJ\\|SUV\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\\|NOM`, `KN`, `MAD`, `MID`, `NN`, `NN\\|-\\|-\\|-\\|-`, `NN\\|AN`, `NN\\|NEU\\|-\\|-\\|SMS`, `NN\\|NEU\\|PLU\\|DEF\\|GEN`, `NN\\|NEU\\|PLU\\|DEF\\|NOM`, `NN\\|NEU\\|PLU\\|IND\\|GEN`, `NN\\|NEU\\|PLU\\|IND\\|NOM`, `NN\\|NEU\\|SIN\\|DEF\\|GEN`, `NN\\|NEU\\|SIN\\|DEF\\|NOM`, `NN\\|NEU\\|SIN\\|IND`, `NN\\|NEU\\|SIN\\|IND\\|GEN`, `NN\\|NEU\\|SIN\\|IND\\|NOM`, `NN\\|SMS`, `NN\\|UTR\\|-\\|-\\|-`, `NN\\|UTR\\|-\\|-\\|SMS`, `NN\\|UTR\\|PLU\\|DEF\\|GEN`, `NN\\|UTR\\|PLU\\|DEF\\|NOM`, `NN\\|UTR\\|PLU\\|IND\\|GEN`, `NN\\|UTR\\|PLU\\|IND\\|NOM`, `NN\\|UTR\\|SIN\\|DEF\\|GEN`, `NN\\|UTR\\|SIN\\|DEF\\|NOM`, `NN\\|UTR\\|SIN\\|IND\\|GEN`, `NN\\|UTR\\|SIN\\|IND\\|NOM`, `PAD`, `PC\\|PRF\\|NEU\\|SIN\\|IND\\|NOM`, `PC\\|PRF\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|GEN`, `PC\\|PRF\\|UTR\u002FNEU\\|PLU\\|IND\u002FDEF\\|NOM`, `PC\\|PRF\\|UTR\u002FNEU\\|SIN\\|DEF\\|NOM`, `PC\\|PRF\\|UTR\\|SIN\\|IND\\|NOM`, `PC\\|PRS\\|UTR\u002FNEU\\|SIN\u002FPLU\\|IND\u002FDEF\\|NOM`, `PL`, `PM`, `PM\\|GEN`, `PM\\|NOM`, `PM\\|SMS`, `PN\\|MAS\\|SIN\\|DEF\\|SUB\u002FOBJ`, `PN\\|NEU\\|SIN\\|DEF`, `PN\\|NEU\\|SIN\\|DEF\\|SUB\u002FOBJ`, `PN\\|NEU\\|SIN\\|IND\\|SUB\u002FOBJ`, `PN\\|UTR\u002FNEU\\|PLU\\|DEF\\|OBJ`, `PN\\|UTR\u002FNEU\\|PLU\\|DEF\\|SUB`, `PN\\|UTR\u002FNEU\\|PLU\\|DEF\\|SUB\u002FOBJ`, `PN\\|UTR\u002FNEU\\|PLU\\|IND\\|SUB\u002FOBJ`, `PN\\|UTR\u002FNEU\\|SIN\u002FPLU\\|DEF\\|OBJ`, `PN\\|UTR\\|PLU\\|DEF\\|OBJ`, `PN\\|UTR\\|PLU\\|DEF\\|SUB`, `PN\\|UTR\\|SIN\\|DEF\\|NOM`, `PN\\|UTR\\|SIN\\|DEF\\|OBJ`, `PN\\|UTR\\|SIN\\|DEF\\|SUB`, `PN\\|UTR\\|SIN\\|DEF\\|SUB\u002FOBJ`, `PN\\|UTR\\|SIN\\|IND\\|NOM`, `PN\\|UTR\\|SIN\\|IND\\|SUB`, `PN\\|UTR\\|SIN\\|IND\\|SUB\u002FOBJ`, `PP`, `PS\\|NEU\\|SIN\\|DEF`, `PS\\|UTR\u002FNEU\\|PLU\\|DEF`, `PS\\|UTR\u002FNEU\\|SIN\u002FPLU\\|DEF`, `PS\\|UTR\\|SIN\\|DEF`, `RG\\|NEU\\|SIN\\|IND\\|NOM`, `RG\\|NOM`, `RG\\|SMS`, `RG\\|UTR\\|SIN\\|IND\\|NOM`, `RO\\|MAS\\|SIN\\|IND\u002FDEF\\|NOM`, `RO\\|NOM`, `SN`, `UO`, `VB\\|AN`, `VB\\|IMP\\|AKT`, `VB\\|IMP\\|SFO`, `VB\\|INF\\|AKT`, `VB\\|INF\\|SFO`, `VB\\|KON\\|PRS\\|AKT`, `VB\\|KON\\|PRT\\|AKT`, `VB\\|PRS\\|AKT`, `VB\\|PRS\\|SFO`, `VB\\|PRT\\|AKT`, `VB\\|PRT\\|SFO`, `VB\\|SUP\\|AKT`, `VB\\|SUP\\|SFO`, `_SP` |\n| **`morphologizer`** | `Case=Nom\\|Definite=Ind\\|Degree=Pos\\|Gender=Com\\|Number=Sing\\|POS=ADJ`, `Case=Nom\\|Definite=Ind\\|Gender=Com\\|Number",{"id":165,"version":166,"summary_zh":167,"released_at":168},334458,"sl_core_news_lg-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsl_core_news_lg-3.8.0\u002Fsl_core_news_lg-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsl_core_news_lg-3.8.0\u002Fsl_core_news_lg-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsl_core_news_lg-3.8.0\u002Fsl_core_news_lg-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsl_core_news_lg-3.8.0\u002Fsl_core_news_lg-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `6434a08a84c49ef281834a9a10f5743c2919726290dd4cdd83dd070bd6df0c06`\u003Cbr \u002F>**Checksum .whl:** `1358fa16bcb2c1309451f748096a801688f6a2b2a251bed94a1bd170df86179f`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fsl#sl_core_news_lg\n\nSlovenian pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), attribute_ruler, senter, ner.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `sl_core_news_lg` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |\n| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |\n| **Vectors** | floret (200000, 300) |\n| **Sources** | [UD Slovenian SSJ v2.11](https:\u002F\u002Fgithub.com\u002FUniversalDependencies\u002FUD_Slovenian-SSJ) (Dobrovoljc, Kaja; Erjavec, Tomaž; Krek, Simon)\u003Cbr \u002F>[Training corpus SUK 1.0](https:\u002F\u002Fwww.clarin.si\u002Frepository\u002Fxmlui\u002Fhandle\u002F11356\u002F1747) (Arhar Holdt, Špela; Krek, Simon; Dobrovoljc, Kaja; Erjavec, Tomaž; Gantar, Polona; Čibej, Jaka; Pori, Eva; Terčon, Luka; Munda, Tina; Žitnik, Slavko; Robida, Nejc; Blagus, Neli; Može, Sara; Ledinek, Nina; Holz, Nanika; Zupan, Katja; Kuzman, Taja; Kavčič, Teja; Škrjanec, Iza; Marko, Dafne; Jezeršek, Lucija; Zajc, Anja)\u003Cbr \u002F>[Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-vectors-builder) (Explosion) |\n| **License** | `CC BY-SA 4.0` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 221 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (2401 labels for 4 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`tagger`** | `Agcfdn`, `Agcfpa`, `Agcfpd`, `Agcfpg`, `Agcfpi`, `Agcfpl`, `Agcfpn`, `Agcfsa`, `Agcfsd`, `Agcfsg`, `Agcfsi`, `Agcfsl`, `Agcfsn`, `Agcmda`, `Agcmdn`, `Agcmpa`, `Agcmpd`, `Agcmpg`, `Agcmpi`, `Agcmpl`, `Agcmpn`, `Agcmsay`, `Agcmsd`, `Agcmsg`, `Agcmsi`, `Agcmsl`, `Agcmsny`, `Agcndn`, `Agcnpa`, `Agcnpd`, `Agcnpg`, `Agcnpi`, `Agcnpl`, `Agcnpn`, `Agcnsa`, `Agcnsd`, `Agcnsg`, `Agcnsi`, `Agcnsl`, `Agcnsn`, `Agpfda`, `Agpfdg`, `Agpfdi`, `Agpfdl`, `Agpfdn`, `Agpfpa`, `Agpfpd`, `Agpfpg`, `Agpfpi`, `Agpfpl`, `Agpfpn`, `Agpfsa`, `Agpfsd`, `Agpfsg`, `Agpfsi`, `Agpfsl`, `Agpfsn`, `Agpmda`, `Agpmdd`, `Agpmdg`, `Agpmdi`, `Agpmdl`, `Agpmdn`, `Agpmpa`, `Agpmpd`, `Agpmpg`, `Agpmpi`, `Agpmpl`, `Agpmpn`, `Agpmsa`, `Agpmsan`, `Agpmsay`, `Agpmsd`, `Agpmsg`, `Agpmsi`, `Agpmsl`, `Agpmsnn`, `Agpmsny`, `Agpnda`, `Agpndg`, `Agpndi`, `Agpndn`, `Agpnpa`, `Agpnpd`, `Agpnpg`, `Agpnpi`, `Agpnpl`, `Agpnpn`, `Agpnsa`, `Agpnsd`, `Agpnsg`, `Agpnsi`, `Agpnsl`, `Agpnsn`, `Agsfda`, `Agsfpa`, `Agsfpg`, `Agsfpi`, `Agsfpl`, `Agsfpn`, `Agsfsa`, `Agsfsd`, `Agsfsg`, `Agsfsi`, `Agsfsl`, `Agsfsn`, `Agsmdn`, `Agsmpa`, `Agsmpd`, `Agsmpg`, `Agsmpi`, `Agsmpl`, `Agsmpn`, `Agsmsa`, `Agsmsay`, `Agsmsg`, `Agsmsi`, `Agsmsl`, `Agsmsny`, `Agsnpa`, `Agsnpg`, `Agsnpn`, `Agsnsa`, `Agsnsg`, `Agsnsi`, `Agsnsl`, `Agsnsn`, `Appfda`, `Appfdg`, `Appfdi`, `Appfdn`, `Appfpa`, `Appfpd`, `Appfpg`, `Appfpi`, `Appfpl`, `Appfpn`, `Appfsa`, `Appfsd`, `Appfsg`, `Appfsi`, `Appfsl`, `Appfsn`, `Appmda`, `Appmdg`, `Appmdl`, `Appmdn`, `Appmpa`, `Appmpd`, `Appmpg`, `Appmpi`, `Appmpl`, `Appmpn`, `Appmsa`, `Appmsan`, `Appmsay`, `Appmsd`, `Appmsg`, `Appmsi`, `Appmsl`, `Appmsnn`, `Appmsny`, `Appndg`, `Appndn`, `Appnpa`, `Appnpg`, `Appnpi`, `Appnpl`, `Appnpn`, `Appnsa`, `Appnsd`, `Appnsg`, `Appnsi`, `Appnsl`, `Appnsn`, `Aspfdi`, `Aspfdn`, `Aspfpa`, `Aspfpg`, `Aspfpl`, `Aspfpn`, `Aspfsa`, `Aspfsd`, `Aspfsg`, `Aspfsi`, `Aspfsl`, `Aspfsn`, `Aspmdl`, `Aspmdn`, `Aspmpa`, `Aspmpd`, `Aspmpg`, `Aspmpl`, `Aspmpn`, `Aspmsa`, `Aspmsan`, `Aspmsd`, `Aspmsg`, `Aspmsi`, `Aspmsl`, `Aspmsnn`, `Aspnpa`, `Aspnpg`, `Aspnpi`, `Aspnpl`, `Aspnpn`, `Aspnsa`, `Aspnsg`, `Aspnsi`, `Aspnsl`, `Aspnsn`, `Cc`, `Cs`, `I`, `Mdc`, `Mdo`, `Mlc-pa`, `Mlc-pd`, `Mlc-pg`, `Mlc-pi`, `Mlc-pl`, `Mlc-pn`, `Mlcfda`, `Mlcfdg`, `Mlcfdi`, `Mlcfdl`, `Mlcfdn`, `Mlcfpa`, `Mlcfpd`, `Mlcfpg`, `Mlcfpi`, `Mlcfpl`, `Mlcfpn`, `Mlcmda`, `Mlcmdg`, `Mlcmdi`, `Mlcmdl`, `Mlcmdn`, `Mlcmpa`, `Mlcmpd`, `Mlcmpg`, `Mlcmpi`, `Mlcmpl`, `Mlcmpn`, `Mlcnda`, `Mlcndg`, `Mlcndi`, `Mlcndl`, `Mlcndn`, `Mlcnpa`, `Mlcnpg`, `Mlcnpi`, `Mlcnpl`, `Mlcnpn`, `Mlofpa`, `Mlofpd`, `Mlofpg`, `Mlofpi`, `Mlofpl`, `Mlofpn`, `Mlofsa`, `Mlofsd`, `Mlofsg`, `Mlofsi`, `Mlofsl`, `Ml","2024-09-30T10:00:09",{"id":170,"version":171,"summary_zh":172,"released_at":173},334459,"sl_core_news_md-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsl_core_news_md-3.8.0\u002Fsl_core_news_md-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsl_core_news_md-3.8.0\u002Fsl_core_news_md-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsl_core_news_md-3.8.0\u002Fsl_core_news_md-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsl_core_news_md-3.8.0\u002Fsl_core_news_md-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `fdab709a9fddbb2f2a1a8d5e8de79114052297de498cfdac79ae33d8ef6a4ed7`\u003Cbr \u002F>**Checksum .whl:** `5f1000c8bdc00044f69c25f6be0747778e6377ee13c236821caeb5ed8f9c932e`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fsl#sl_core_news_md\n\nSlovenian pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), attribute_ruler, senter, ner.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `sl_core_news_md` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |\n| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |\n| **Vectors** | floret (50000, 300) |\n| **Sources** | [UD Slovenian SSJ v2.11](https:\u002F\u002Fgithub.com\u002FUniversalDependencies\u002FUD_Slovenian-SSJ) (Dobrovoljc, Kaja; Erjavec, Tomaž; Krek, Simon)\u003Cbr \u002F>[Training corpus SUK 1.0](https:\u002F\u002Fwww.clarin.si\u002Frepository\u002Fxmlui\u002Fhandle\u002F11356\u002F1747) (Arhar Holdt, Špela; Krek, Simon; Dobrovoljc, Kaja; Erjavec, Tomaž; Gantar, Polona; Čibej, Jaka; Pori, Eva; Terčon, Luka; Munda, Tina; Žitnik, Slavko; Robida, Nejc; Blagus, Neli; Može, Sara; Ledinek, Nina; Holz, Nanika; Zupan, Katja; Kuzman, Taja; Kavčič, Teja; Škrjanec, Iza; Marko, Dafne; Jezeršek, Lucija; Zajc, Anja)\u003Cbr \u002F>[Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-vectors-builder) (Explosion) |\n| **License** | `CC BY-SA 4.0` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 64 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (2401 labels for 4 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`tagger`** | `Agcfdn`, `Agcfpa`, `Agcfpd`, `Agcfpg`, `Agcfpi`, `Agcfpl`, `Agcfpn`, `Agcfsa`, `Agcfsd`, `Agcfsg`, `Agcfsi`, `Agcfsl`, `Agcfsn`, `Agcmda`, `Agcmdn`, `Agcmpa`, `Agcmpd`, `Agcmpg`, `Agcmpi`, `Agcmpl`, `Agcmpn`, `Agcmsay`, `Agcmsd`, `Agcmsg`, `Agcmsi`, `Agcmsl`, `Agcmsny`, `Agcndn`, `Agcnpa`, `Agcnpd`, `Agcnpg`, `Agcnpi`, `Agcnpl`, `Agcnpn`, `Agcnsa`, `Agcnsd`, `Agcnsg`, `Agcnsi`, `Agcnsl`, `Agcnsn`, `Agpfda`, `Agpfdg`, `Agpfdi`, `Agpfdl`, `Agpfdn`, `Agpfpa`, `Agpfpd`, `Agpfpg`, `Agpfpi`, `Agpfpl`, `Agpfpn`, `Agpfsa`, `Agpfsd`, `Agpfsg`, `Agpfsi`, `Agpfsl`, `Agpfsn`, `Agpmda`, `Agpmdd`, `Agpmdg`, `Agpmdi`, `Agpmdl`, `Agpmdn`, `Agpmpa`, `Agpmpd`, `Agpmpg`, `Agpmpi`, `Agpmpl`, `Agpmpn`, `Agpmsa`, `Agpmsan`, `Agpmsay`, `Agpmsd`, `Agpmsg`, `Agpmsi`, `Agpmsl`, `Agpmsnn`, `Agpmsny`, `Agpnda`, `Agpndg`, `Agpndi`, `Agpndn`, `Agpnpa`, `Agpnpd`, `Agpnpg`, `Agpnpi`, `Agpnpl`, `Agpnpn`, `Agpnsa`, `Agpnsd`, `Agpnsg`, `Agpnsi`, `Agpnsl`, `Agpnsn`, `Agsfda`, `Agsfpa`, `Agsfpg`, `Agsfpi`, `Agsfpl`, `Agsfpn`, `Agsfsa`, `Agsfsd`, `Agsfsg`, `Agsfsi`, `Agsfsl`, `Agsfsn`, `Agsmdn`, `Agsmpa`, `Agsmpd`, `Agsmpg`, `Agsmpi`, `Agsmpl`, `Agsmpn`, `Agsmsa`, `Agsmsay`, `Agsmsg`, `Agsmsi`, `Agsmsl`, `Agsmsny`, `Agsnpa`, `Agsnpg`, `Agsnpn`, `Agsnsa`, `Agsnsg`, `Agsnsi`, `Agsnsl`, `Agsnsn`, `Appfda`, `Appfdg`, `Appfdi`, `Appfdn`, `Appfpa`, `Appfpd`, `Appfpg`, `Appfpi`, `Appfpl`, `Appfpn`, `Appfsa`, `Appfsd`, `Appfsg`, `Appfsi`, `Appfsl`, `Appfsn`, `Appmda`, `Appmdg`, `Appmdl`, `Appmdn`, `Appmpa`, `Appmpd`, `Appmpg`, `Appmpi`, `Appmpl`, `Appmpn`, `Appmsa`, `Appmsan`, `Appmsay`, `Appmsd`, `Appmsg`, `Appmsi`, `Appmsl`, `Appmsnn`, `Appmsny`, `Appndg`, `Appndn`, `Appnpa`, `Appnpg`, `Appnpi`, `Appnpl`, `Appnpn`, `Appnsa`, `Appnsd`, `Appnsg`, `Appnsi`, `Appnsl`, `Appnsn`, `Aspfdi`, `Aspfdn`, `Aspfpa`, `Aspfpg`, `Aspfpl`, `Aspfpn`, `Aspfsa`, `Aspfsd`, `Aspfsg`, `Aspfsi`, `Aspfsl`, `Aspfsn`, `Aspmdl`, `Aspmdn`, `Aspmpa`, `Aspmpd`, `Aspmpg`, `Aspmpl`, `Aspmpn`, `Aspmsa`, `Aspmsan`, `Aspmsd`, `Aspmsg`, `Aspmsi`, `Aspmsl`, `Aspmsnn`, `Aspnpa`, `Aspnpg`, `Aspnpi`, `Aspnpl`, `Aspnpn`, `Aspnsa`, `Aspnsg`, `Aspnsi`, `Aspnsl`, `Aspnsn`, `Cc`, `Cs`, `I`, `Mdc`, `Mdo`, `Mlc-pa`, `Mlc-pd`, `Mlc-pg`, `Mlc-pi`, `Mlc-pl`, `Mlc-pn`, `Mlcfda`, `Mlcfdg`, `Mlcfdi`, `Mlcfdl`, `Mlcfdn`, `Mlcfpa`, `Mlcfpd`, `Mlcfpg`, `Mlcfpi`, `Mlcfpl`, `Mlcfpn`, `Mlcmda`, `Mlcmdg`, `Mlcmdi`, `Mlcmdl`, `Mlcmdn`, `Mlcmpa`, `Mlcmpd`, `Mlcmpg`, `Mlcmpi`, `Mlcmpl`, `Mlcmpn`, `Mlcnda`, `Mlcndg`, `Mlcndi`, `Mlcndl`, `Mlcndn`, `Mlcnpa`, `Mlcnpg`, `Mlcnpi`, `Mlcnpl`, `Mlcnpn`, `Mlofpa`, `Mlofpd`, `Mlofpg`, `Mlofpi`, `Mlofpl`, `Mlofpn`, `Mlofsa`, `Mlofsd`, `Mlofsg`, `Mlofsi`, `Mlofsl`, `Mlof","2024-09-30T10:00:08",{"id":175,"version":176,"summary_zh":177,"released_at":178},334460,"sl_core_news_sm-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsl_core_news_sm-3.8.0\u002Fsl_core_news_sm-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsl_core_news_sm-3.8.0\u002Fsl_core_news_sm-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fsl_core_news_sm-3.8.0\u002Fsl_core_news_sm-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fsl_core_news_sm-3.8.0\u002Fsl_core_news_sm-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `bc17dfb5a83391ccdc0278c2cdc914790e5433a43befc40ade47133561067f1e`\u003Cbr \u002F>**Checksum .whl:** `d6d11f38c917d59b0fe52a15da09963bdc8011d2be288f75371e734065b6911c`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fsl#sl_core_news_sm\n\nSlovenian pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), attribute_ruler, senter, ner.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `sl_core_news_sm` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |\n| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |\n| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |\n| **Sources** | [UD Slovenian SSJ v2.11](https:\u002F\u002Fgithub.com\u002FUniversalDependencies\u002FUD_Slovenian-SSJ) (Dobrovoljc, Kaja; Erjavec, Tomaž; Krek, Simon)\u003Cbr \u002F>[Training corpus SUK 1.0](https:\u002F\u002Fwww.clarin.si\u002Frepository\u002Fxmlui\u002Fhandle\u002F11356\u002F1747) (Arhar Holdt, Špela; Krek, Simon; Dobrovoljc, Kaja; Erjavec, Tomaž; Gantar, Polona; Čibej, Jaka; Pori, Eva; Terčon, Luka; Munda, Tina; Žitnik, Slavko; Robida, Nejc; Blagus, Neli; Može, Sara; Ledinek, Nina; Holz, Nanika; Zupan, Katja; Kuzman, Taja; Kavčič, Teja; Škrjanec, Iza; Marko, Dafne; Jezeršek, Lucija; Zajc, Anja) |\n| **License** | `CC BY-SA 4.0` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 13 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (2401 labels for 4 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`tagger`** | `Agcfdn`, `Agcfpa`, `Agcfpd`, `Agcfpg`, `Agcfpi`, `Agcfpl`, `Agcfpn`, `Agcfsa`, `Agcfsd`, `Agcfsg`, `Agcfsi`, `Agcfsl`, `Agcfsn`, `Agcmda`, `Agcmdn`, `Agcmpa`, `Agcmpd`, `Agcmpg`, `Agcmpi`, `Agcmpl`, `Agcmpn`, `Agcmsay`, `Agcmsd`, `Agcmsg`, `Agcmsi`, `Agcmsl`, `Agcmsny`, `Agcndn`, `Agcnpa`, `Agcnpd`, `Agcnpg`, `Agcnpi`, `Agcnpl`, `Agcnpn`, `Agcnsa`, `Agcnsd`, `Agcnsg`, `Agcnsi`, `Agcnsl`, `Agcnsn`, `Agpfda`, `Agpfdg`, `Agpfdi`, `Agpfdl`, `Agpfdn`, `Agpfpa`, `Agpfpd`, `Agpfpg`, `Agpfpi`, `Agpfpl`, `Agpfpn`, `Agpfsa`, `Agpfsd`, `Agpfsg`, `Agpfsi`, `Agpfsl`, `Agpfsn`, `Agpmda`, `Agpmdd`, `Agpmdg`, `Agpmdi`, `Agpmdl`, `Agpmdn`, `Agpmpa`, `Agpmpd`, `Agpmpg`, `Agpmpi`, `Agpmpl`, `Agpmpn`, `Agpmsa`, `Agpmsan`, `Agpmsay`, `Agpmsd`, `Agpmsg`, `Agpmsi`, `Agpmsl`, `Agpmsnn`, `Agpmsny`, `Agpnda`, `Agpndg`, `Agpndi`, `Agpndn`, `Agpnpa`, `Agpnpd`, `Agpnpg`, `Agpnpi`, `Agpnpl`, `Agpnpn`, `Agpnsa`, `Agpnsd`, `Agpnsg`, `Agpnsi`, `Agpnsl`, `Agpnsn`, `Agsfda`, `Agsfpa`, `Agsfpg`, `Agsfpi`, `Agsfpl`, `Agsfpn`, `Agsfsa`, `Agsfsd`, `Agsfsg`, `Agsfsi`, `Agsfsl`, `Agsfsn`, `Agsmdn`, `Agsmpa`, `Agsmpd`, `Agsmpg`, `Agsmpi`, `Agsmpl`, `Agsmpn`, `Agsmsa`, `Agsmsay`, `Agsmsg`, `Agsmsi`, `Agsmsl`, `Agsmsny`, `Agsnpa`, `Agsnpg`, `Agsnpn`, `Agsnsa`, `Agsnsg`, `Agsnsi`, `Agsnsl`, `Agsnsn`, `Appfda`, `Appfdg`, `Appfdi`, `Appfdn`, `Appfpa`, `Appfpd`, `Appfpg`, `Appfpi`, `Appfpl`, `Appfpn`, `Appfsa`, `Appfsd`, `Appfsg`, `Appfsi`, `Appfsl`, `Appfsn`, `Appmda`, `Appmdg`, `Appmdl`, `Appmdn`, `Appmpa`, `Appmpd`, `Appmpg`, `Appmpi`, `Appmpl`, `Appmpn`, `Appmsa`, `Appmsan`, `Appmsay`, `Appmsd`, `Appmsg`, `Appmsi`, `Appmsl`, `Appmsnn`, `Appmsny`, `Appndg`, `Appndn`, `Appnpa`, `Appnpg`, `Appnpi`, `Appnpl`, `Appnpn`, `Appnsa`, `Appnsd`, `Appnsg`, `Appnsi`, `Appnsl`, `Appnsn`, `Aspfdi`, `Aspfdn`, `Aspfpa`, `Aspfpg`, `Aspfpl`, `Aspfpn`, `Aspfsa`, `Aspfsd`, `Aspfsg`, `Aspfsi`, `Aspfsl`, `Aspfsn`, `Aspmdl`, `Aspmdn`, `Aspmpa`, `Aspmpd`, `Aspmpg`, `Aspmpl`, `Aspmpn`, `Aspmsa`, `Aspmsan`, `Aspmsd`, `Aspmsg`, `Aspmsi`, `Aspmsl`, `Aspmsnn`, `Aspnpa`, `Aspnpg`, `Aspnpi`, `Aspnpl`, `Aspnpn`, `Aspnsa`, `Aspnsg`, `Aspnsi`, `Aspnsl`, `Aspnsn`, `Cc`, `Cs`, `I`, `Mdc`, `Mdo`, `Mlc-pa`, `Mlc-pd`, `Mlc-pg`, `Mlc-pi`, `Mlc-pl`, `Mlc-pn`, `Mlcfda`, `Mlcfdg`, `Mlcfdi`, `Mlcfdl`, `Mlcfdn`, `Mlcfpa`, `Mlcfpd`, `Mlcfpg`, `Mlcfpi`, `Mlcfpl`, `Mlcfpn`, `Mlcmda`, `Mlcmdg`, `Mlcmdi`, `Mlcmdl`, `Mlcmdn`, `Mlcmpa`, `Mlcmpd`, `Mlcmpg`, `Mlcmpi`, `Mlcmpl`, `Mlcmpn`, `Mlcnda`, `Mlcndg`, `Mlcndi`, `Mlcndl`, `Mlcndn`, `Mlcnpa`, `Mlcnpg`, `Mlcnpi`, `Mlcnpl`, `Mlcnpn`, `Mlofpa`, `Mlofpd`, `Mlofpg`, `Mlofpi`, `Mlofpl`, `Mlofpn`, `Mlofsa`, `Mlofsd`, `Mlofsg`, `Mlofsi`, `Mlofsl`, `Mlofsn`, `Mlompa`, `Mlompg`, `Mlompi`, `Mlompl`, `Mlompn`, `Mlomsa`, `Mlomsd`, `Mlomsg`, `Mlomsi`, `Mlomsl`, `Mlomsn`, `Mlonda`, `M","2024-09-30T10:00:07",{"id":180,"version":181,"summary_zh":182,"released_at":183},334461,"ru_core_news_lg-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fru_core_news_lg-3.8.0\u002Fru_core_news_lg-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fru_core_news_lg-3.8.0\u002Fru_core_news_lg-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fru_core_news_lg-3.8.0\u002Fru_core_news_lg-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fru_core_news_lg-3.8.0\u002Fru_core_news_lg-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `9c441fc7e3318cd32a7138e42d5b266f2d0c2709c159a93d0fb267aa41098ac5`\u003Cbr \u002F>**Checksum .whl:** `90bd584be86772b647e1b15cdc62e09d3a7182284ee23da95e19c2bf71aa0189`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fru#ru_core_news_lg\n\nRussian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `ru_core_news_lg` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **Vectors** | 500002 keys, 500002 unique vectors (300 dimensions) |\n| **Sources** | [Nerus](https:\u002F\u002Fgithub.com\u002Fnatasha\u002Fnerus) (Alexander Kukushkin)\u003Cbr \u002F>[Navec](https:\u002F\u002Fgithub.com\u002Fnatasha\u002Fnavec) (Alexander Kukushkin) |\n| **License** | `MIT` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 489 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (900 labels for 3 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`morphologizer`** | `Case=Nom\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Aspect=Perf\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Inan\\|Case=Acc\\|POS=NUM`, `Animacy=Inan\\|Case=Gen\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Case=Gen\\|Degree=Pos\\|Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Animacy=Inan\\|Case=Gen\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `POS=ADP`, `Case=Gen\\|Gender=Fem\\|Number=Sing\\|POS=DET`, `Animacy=Inan\\|Case=Gen\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `POS=PUNCT`, `Degree=Pos\\|POS=ADV`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Mid`, `Animacy=Inan\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Animacy=Anim\\|Case=Gen\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Aspect=Perf\\|Case=Gen\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Case=Loc\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Inan\\|Case=Loc\\|Gender=Neut\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Loc\\|Gender=Neut\\|Number=Sing\\|POS=PRON`, `Aspect=Imp\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=Third\\|Tense=Pres\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Inan\\|Case=Nom\\|Gender=Neut\\|Number=Sing\\|POS=NOUN`, `Foreign=Yes\\|POS=PROPN`, `Case=Loc\\|Gender=Fem\\|Number=Sing\\|POS=NUM`, `Aspect=Imp\\|Gender=Neut\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Anim\\|Case=Gen\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Inan\\|Case=Loc\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `POS=NUM`, `Animacy=Inan\\|Case=Gen\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=PRON\\|Person=Third`, `Aspect=Imp\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=AUX\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Anim\\|Case=Ins\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Inan\\|Case=Dat\\|Gender=Neut\\|Number=Sing\\|POS=NOUN`, `POS=DET`, `Animacy=Inan\\|Case=Nom\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `Aspect=Perf\\|Gender=Fem\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Case=Dat\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Inan\\|Case=Dat\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Aspect=Perf\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `POS=SCONJ`, `Animacy=Inan\\|Case=Ins\\|Gender=Neut\\|Number=Sing\\|POS=NOUN`, `Case=Acc\\|Gender=Neut\\|Number=Sing\\|POS=PRON\\|Person=Third`, `Case=Acc\\|POS=NUM`, `Case=Ins\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Inan\\|Case=Ins\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `POS=CCONJ`, `Case=Nom\\|POS=NUM`, `Animacy=Inan\\|Case=Dat\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Aspect=Perf\\|Gender=Masc\\|Number=Sing\\|POS=VERB\\|StyleVariant=Short\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Case=Nom\\|Degree=Pos\\|Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Case=Ins\\|Degree=Pos\\|Gender=Neut\\|Number=Sing\\|POS=ADJ`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=Third\\|Tense=Pres\\|VerbForm=Fin\\|Voice=Act`, `Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=DET`, `Aspect=Imp\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Case=Acc\\|Degree=Pos\\|Gender=Fem\\|Number=Sing\\|POS=ADJ`, `Animacy=Inan\\|Case=Acc\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `Case","2024-09-30T10:00:12",{"id":185,"version":186,"summary_zh":187,"released_at":188},334462,"ru_core_news_md-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fru_core_news_md-3.8.0\u002Fru_core_news_md-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fru_core_news_md-3.8.0\u002Fru_core_news_md-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fru_core_news_md-3.8.0\u002Fru_core_news_md-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fru_core_news_md-3.8.0\u002Fru_core_news_md-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `094917aad64c174e0cf3f244567922b70f0533b5a2dee0416822abdc27bb6e08`\u003Cbr \u002F>**Checksum .whl:** `43f456d40e4b70726874e01ce01fce32f50089ba98a2660292e9a6c63a06ebe9`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fru#ru_core_news_md\n\nRussian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `ru_core_news_md` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **Vectors** | 500002 keys, 20000 unique vectors (300 dimensions) |\n| **Sources** | [Nerus](https:\u002F\u002Fgithub.com\u002Fnatasha\u002Fnerus) (Alexander Kukushkin)\u003Cbr \u002F>[Navec](https:\u002F\u002Fgithub.com\u002Fnatasha\u002Fnavec) (Alexander Kukushkin) |\n| **License** | `MIT` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 39 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (900 labels for 3 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`morphologizer`** | `Case=Nom\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Aspect=Perf\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Inan\\|Case=Acc\\|POS=NUM`, `Animacy=Inan\\|Case=Gen\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Case=Gen\\|Degree=Pos\\|Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Animacy=Inan\\|Case=Gen\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `POS=ADP`, `Case=Gen\\|Gender=Fem\\|Number=Sing\\|POS=DET`, `Animacy=Inan\\|Case=Gen\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `POS=PUNCT`, `Degree=Pos\\|POS=ADV`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Mid`, `Animacy=Inan\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Animacy=Anim\\|Case=Gen\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Aspect=Perf\\|Case=Gen\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Case=Loc\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Inan\\|Case=Loc\\|Gender=Neut\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Loc\\|Gender=Neut\\|Number=Sing\\|POS=PRON`, `Aspect=Imp\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=Third\\|Tense=Pres\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Inan\\|Case=Nom\\|Gender=Neut\\|Number=Sing\\|POS=NOUN`, `Foreign=Yes\\|POS=PROPN`, `Case=Loc\\|Gender=Fem\\|Number=Sing\\|POS=NUM`, `Aspect=Imp\\|Gender=Neut\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Anim\\|Case=Gen\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Inan\\|Case=Loc\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `POS=NUM`, `Animacy=Inan\\|Case=Gen\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=PRON\\|Person=Third`, `Aspect=Imp\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=AUX\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Anim\\|Case=Ins\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Inan\\|Case=Dat\\|Gender=Neut\\|Number=Sing\\|POS=NOUN`, `POS=DET`, `Animacy=Inan\\|Case=Nom\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `Aspect=Perf\\|Gender=Fem\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Case=Dat\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Inan\\|Case=Dat\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Aspect=Perf\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `POS=SCONJ`, `Animacy=Inan\\|Case=Ins\\|Gender=Neut\\|Number=Sing\\|POS=NOUN`, `Case=Acc\\|Gender=Neut\\|Number=Sing\\|POS=PRON\\|Person=Third`, `Case=Acc\\|POS=NUM`, `Case=Ins\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Inan\\|Case=Ins\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `POS=CCONJ`, `Case=Nom\\|POS=NUM`, `Animacy=Inan\\|Case=Dat\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Aspect=Perf\\|Gender=Masc\\|Number=Sing\\|POS=VERB\\|StyleVariant=Short\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Case=Nom\\|Degree=Pos\\|Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Case=Ins\\|Degree=Pos\\|Gender=Neut\\|Number=Sing\\|POS=ADJ`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=Third\\|Tense=Pres\\|VerbForm=Fin\\|Voice=Act`, `Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=DET`, `Aspect=Imp\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Case=Acc\\|Degree=Pos\\|Gender=Fem\\|Number=Sing\\|POS=ADJ`, `Animacy=Inan\\|Case=Acc\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `Case=N","2024-09-30T10:00:11",{"id":190,"version":191,"summary_zh":192,"released_at":193},334463,"ru_core_news_sm-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fru_core_news_sm-3.8.0\u002Fru_core_news_sm-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fru_core_news_sm-3.8.0\u002Fru_core_news_sm-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fru_core_news_sm-3.8.0\u002Fru_core_news_sm-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fru_core_news_sm-3.8.0\u002Fru_core_news_sm-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `a64ca2b8953f33a9b713b60eab38bd4efeb2432133f040d5218809c8b0111310`\u003Cbr \u002F>**Checksum .whl:** `69978d47b43e2c4f329bebdb155e8e9d3861bba1a58ba25551419dae7d7e07fc`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fru#ru_core_news_sm\n\nRussian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `ru_core_news_sm` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |\n| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |\n| **Sources** | [Nerus](https:\u002F\u002Fgithub.com\u002Fnatasha\u002Fnerus) (Alexander Kukushkin) |\n| **License** | `MIT` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 14 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (900 labels for 3 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`morphologizer`** | `Case=Nom\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Anim\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Aspect=Perf\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Inan\\|Case=Acc\\|POS=NUM`, `Animacy=Inan\\|Case=Gen\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Case=Gen\\|Degree=Pos\\|Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Animacy=Inan\\|Case=Gen\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `POS=ADP`, `Case=Gen\\|Gender=Fem\\|Number=Sing\\|POS=DET`, `Animacy=Inan\\|Case=Gen\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `POS=PUNCT`, `Degree=Pos\\|POS=ADV`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Mid`, `Animacy=Inan\\|Case=Nom\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Animacy=Anim\\|Case=Gen\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Aspect=Perf\\|Case=Gen\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Case=Loc\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Inan\\|Case=Loc\\|Gender=Neut\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Loc\\|Gender=Neut\\|Number=Sing\\|POS=PRON`, `Aspect=Imp\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=Third\\|Tense=Pres\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Inan\\|Case=Nom\\|Gender=Neut\\|Number=Sing\\|POS=NOUN`, `Foreign=Yes\\|POS=PROPN`, `Case=Loc\\|Gender=Fem\\|Number=Sing\\|POS=NUM`, `Aspect=Imp\\|Gender=Neut\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Anim\\|Case=Gen\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Inan\\|Case=Loc\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `POS=NUM`, `Animacy=Inan\\|Case=Gen\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=PRON\\|Person=Third`, `Aspect=Imp\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=AUX\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Animacy=Anim\\|Case=Ins\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Animacy=Inan\\|Case=Dat\\|Gender=Neut\\|Number=Sing\\|POS=NOUN`, `POS=DET`, `Animacy=Inan\\|Case=Nom\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `Aspect=Perf\\|Gender=Fem\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Case=Dat\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Inan\\|Case=Dat\\|Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Animacy=Inan\\|Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Aspect=Perf\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `POS=SCONJ`, `Animacy=Inan\\|Case=Ins\\|Gender=Neut\\|Number=Sing\\|POS=NOUN`, `Case=Acc\\|Gender=Neut\\|Number=Sing\\|POS=PRON\\|Person=Third`, `Case=Acc\\|POS=NUM`, `Case=Ins\\|Degree=Pos\\|Number=Plur\\|POS=ADJ`, `Animacy=Inan\\|Case=Ins\\|Gender=Masc\\|Number=Plur\\|POS=NOUN`, `POS=CCONJ`, `Case=Nom\\|POS=NUM`, `Animacy=Inan\\|Case=Dat\\|Gender=Masc\\|Number=Sing\\|POS=NOUN`, `Aspect=Perf\\|Gender=Masc\\|Number=Sing\\|POS=VERB\\|StyleVariant=Short\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Case=Nom\\|Degree=Pos\\|Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Case=Ins\\|Degree=Pos\\|Gender=Neut\\|Number=Sing\\|POS=ADJ`, `Aspect=Imp\\|Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=Third\\|Tense=Pres\\|VerbForm=Fin\\|Voice=Act`, `Case=Nom\\|Gender=Masc\\|Number=Sing\\|POS=DET`, `Aspect=Imp\\|Gender=Masc\\|Mood=Ind\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Fin\\|Voice=Act`, `Case=Acc\\|Degree=Pos\\|Gender=Fem\\|Number=Sing\\|POS=ADJ`, `Animacy=Inan\\|Case=Acc\\|Gender=Fem\\|Number=Sing\\|POS=NOUN`, `Case=Nom\\|Gender=Fem\\|Number=Sing\\|POS=PRON`, `Aspect=Imp\\|Mood=Ind\\|Number=Sing\\|POS=","2024-09-30T10:00:10",{"id":195,"version":196,"summary_zh":197,"released_at":198},334464,"ro_core_news_lg-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fro_core_news_lg-3.8.0\u002Fro_core_news_lg-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fro_core_news_lg-3.8.0\u002Fro_core_news_lg-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fro_core_news_lg-3.8.0\u002Fro_core_news_lg-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fro_core_news_lg-3.8.0\u002Fro_core_news_lg-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `39d3f85c9007fe797f1454bb11f26002775da8275644dad45e5a968b9aa7adf9`\u003Cbr \u002F>**Checksum .whl:** `f8c71487a60125af5a84cdf487fc1670ec9cd1e28cfd9f7ef9561be0e25d2c8e`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fro#ro_core_news_lg\n\nRomanian pipeline optimized for CPU. Components: tok2vec, tagger, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `ro_core_news_lg` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |\n| **Components** | `tok2vec`, `tagger`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |\n| **Vectors** | 500000 keys, 500000 unique vectors (300 dimensions) |\n| **Sources** | [UD Romanian RRT v2.8](https:\u002F\u002Fgithub.com\u002FUniversalDependencies\u002FUD_Romanian-RRT) (Barbu Mititelu, Verginica; Irimia, Elena; Perez, Cenel-Augusto; Ion, Radu; Simionescu, Radu; Popel, Martin)\u003Cbr \u002F>[RONEC - the Romanian Named Entity Corpus (ca9ce460)](https:\u002F\u002Fgithub.com\u002Fdumitrescustefan\u002Fronec) (Dumitrescu, Stefan Daniel; Avram, Andrei-Marius; Morogan, Luciana; Toma; Stefan)\u003Cbr \u002F>[Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)](https:\u002F\u002Fspacy.io) (Explosion) |\n| **License** | `CC BY-SA 4.0` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 542 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (540 labels for 3 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`tagger`** | `ARROW`, `Af`, `Afcfp-n`, `Afcfson`, `Afcfsrn`, `Afcmpoy`, `Afcms-n`, `Afp`, `Afp-p-n`, `Afp-poy`, `Afp-srn`, `Afpf--n`, `Afpfp-n`, `Afpfp-ny`, `Afpfpoy`, `Afpfpry`, `Afpfson`, `Afpfsoy`, `Afpfsrn`, `Afpfsry`, `Afpm--n`, `Afpmp-n`, `Afpmpoy`, `Afpmpry`, `Afpms-n`, `Afpmsoy`, `Afpmsry`, `Afsfp-n`, `Afsfsrn`, `BULLET`, `COLON`, `COMMA`, `Ccssp`, `Ccsspy`, `Crssp`, `Csssp`, `Cssspy`, `DASH`, `DBLQ`, `Dd3-po---e`, `Dd3-po---o`, `Dd3fpo`, `Dd3fpr`, `Dd3fpr---e`, `Dd3fpr---o`, `Dd3fpr--y`, `Dd3fso`, `Dd3fso---e`, `Dd3fsr`, `Dd3fsr---e`, `Dd3fsr---o`, `Dd3fsr--yo`, `Dd3mpo`, `Dd3mpr`, `Dd3mpr---e`, `Dd3mpr---o`, `Dd3mso---e`, `Dd3msr`, `Dd3msr---e`, `Dd3msr---o`, `Dh1ms`, `Dh3fp`, `Dh3fso`, `Dh3fsr`, `Dh3mp`, `Dh3ms`, `Di3`, `Di3-----y`, `Di3--r---e`, `Di3-po`, `Di3-po---e`, `Di3-sr`, `Di3-sr---e`, `Di3-sr--y`, `Di3fp`, `Di3fpr`, `Di3fpr---e`, `Di3fso`, `Di3fso---e`, `Di3fsr`, `Di3fsr---e`, `Di3mp`, `Di3mpr`, `Di3mpr---e`, `Di3ms`, `Di3ms----e`, `Di3mso---e`, `Di3msr`, `Di3msr---e`, `Ds1fp-p`, `Ds1fp-s`, `Ds1fsop`, `Ds1fsos`, `Ds1fsrp`, `Ds1fsrs`, `Ds1fsrs-y`, `Ds1mp-p`, `Ds1mp-s`, `Ds1ms-p`, `Ds1ms-s`, `Ds1msrs-y`, `Ds2---s`, `Ds2fp-p`, `Ds2fp-s`, `Ds2fsrp`, `Ds2fsrs`, `Ds2mp-p`, `Ds2mp-s`, `Ds2ms-p`, `Ds2ms-s`, `Ds3---p`, `Ds3---s`, `Ds3---sy`, `Ds3fp-s`, `Ds3fsos`, `Ds3fsrs`, `Ds3mp-s`, `Ds3ms-s`, `Dw3--r---e`, `Dw3-po---e`, `Dw3fpr`, `Dw3fso---e`, `Dw3fsr`, `Dw3mpr`, `Dw3mso---e`, `Dw3msr`, `Dz3fsr---e`, `Dz3mso---e`, `Dz3msr---e`, `EQUAL`, `EXCL`, `EXCLHELLIP`, `GE`, `GT`, `HELLIP`, `I`, `LCURL`, `LPAR`, `LSQR`, `LT`, `M`, `Mc-p-d`, `Mc-p-l`, `Mc-s-b`, `Mc-s-d`, `Mc-s-l`, `Mcfp-l`, `Mcfp-ln`, `Mcfprln`, `Mcfprly`, `Mcfsoln`, `Mcfsrl`, `Mcfsrln`, `Mcfsrly`, `Mcmp-l`, `Mcms-ln`, `Mcmsrl`, `Mcmsrln`, `Mcmsrly`, `Mffprln`, `Mffsrln`, `Mlfpo`, `Mlfpr`, `Mlmpr`, `Mo---l`, `Mo---ln`, `Mo-s-r`, `Mofp-ln`, `Mofpoly`, `Mofprly`, `Mofs-l`, `Mofsoln`, `Mofsoly`, `Mofsrln`, `Mofsrly`, `Mompoly`, `Momprly`, `Moms-l`, `Moms-ln`, `Momsoly`, `Momsrly`, `Nc`, `Nc---n`, `Ncf--n`, `Ncfp-n`, `Ncfpoy`, `Ncfpry`, `Ncfs-n`, `Ncfson`, `Ncfsoy`, `Ncfsrn`, `Ncfsry`, `Ncfsryy`, `Ncfsvy`, `Ncm--n`, `Ncmp-n`, `Ncmpoy`, `Ncmpry`, `Ncms-n`, `Ncms-ny`, `Ncms-y`, `Ncmsoy`, `Ncmsrn`, `Ncmsry`, `Ncmsryy`, `Ncmsvn`, `Ncmsvy`, `Np`, `Npfson`, `Npfsoy`, `Npfsrn`, `Npfsry`, `Npmpoy`, `Npmpry`, `Npms-n`, `Npmsoy`, `Npmsry`, `PERCENT`, `PERIOD`, `PLUS`, `PLUSMINUS`, `Pd3-po`, `Pd3fpr`, `Pd3fso`, `Pd3fsr`, `Pd3mpo`, `Pd3mpr`, `Pd3mpr--y`, `Pd3mso`, `Pd3msr`, `Pi3--r`, `Pi3-po`, `Pi3-so`, `Pi3-sr`, `Pi3fpr`, `Pi3fso`, `Pi3fsr`, `Pi3mpr`, `Pi3mso`, `Pi3msr`, `Pi3msr--y`, `Pp1-pa--------w`, `Pp1-pa--y-----w`, `Pp1-pd--------s`, `Pp1-pd--------w`, `Pp1-pd--y-----w`, `Pp1-pr--------s`, `Pp1-sa--------s`, `Pp1-sa--------w`, `Pp1-sa--y-----w`, `Pp1-sd--------s`, `Pp1-sd--------w`, `Pp1-sd--y-----w`, `Pp1-sn--------s`, `Pp2-----------s`, `Pp2-pa--------w`, `Pp2-pa--y-----w`, `Pp2-","2024-09-30T10:00:15",{"id":200,"version":201,"summary_zh":202,"released_at":203},334465,"ro_core_news_md-3.8.0","[![Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fro_core_news_md-3.8.0\u002Fro_core_news_md-3.8.0.tar.gz?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fro_core_news_md-3.8.0\u002Fro_core_news_md-3.8.0.tar.gz) [![Downloads (wheel)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fexplosion\u002Fspacy-models\u002Fro_core_news_md-3.8.0\u002Fro_core_news_md-3.8.0-py3-none-any.whl?label=downloads&style=flat-square)](https:\u002F\u002Fgithub.com\u002Fexplosion\u002Fspacy-models\u002Freleases\u002Fdownload\u002Fro_core_news_md-3.8.0\u002Fro_core_news_md-3.8.0-py3-none-any.whl)\n\n> **Checksum .tar.gz:** `2d4f69d4acfab594548fa9fe776cb3c885082f833b1dd40729b907b664b066c1`\u003Cbr \u002F>**Checksum .whl:** `e8606efe3732c84a629c7a586d9d6ec2fb197d787513b3033903d56496dc9db1`\n\n### Details: https:\u002F\u002Fspacy.io\u002Fmodels\u002Fro#ro_core_news_md\n\nRomanian pipeline optimized for CPU. Components: tok2vec, tagger, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.\n\n| Feature | Description |\n| --- | --- |\n| **Name** | `ro_core_news_md` |\n| **Version** | `3.8.0` |\n| **spaCy** | `>=3.8.0,\u003C3.9.0` |\n| **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |\n| **Components** | `tok2vec`, `tagger`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |\n| **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |\n| **Sources** | [UD Romanian RRT v2.8](https:\u002F\u002Fgithub.com\u002FUniversalDependencies\u002FUD_Romanian-RRT) (Barbu Mititelu, Verginica; Irimia, Elena; Perez, Cenel-Augusto; Ion, Radu; Simionescu, Radu; Popel, Martin)\u003Cbr \u002F>[RONEC - the Romanian Named Entity Corpus (ca9ce460)](https:\u002F\u002Fgithub.com\u002Fdumitrescustefan\u002Fronec) (Dumitrescu, Stefan Daniel; Avram, Andrei-Marius; Morogan, Luciana; Toma; Stefan)\u003Cbr \u002F>[Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)](https:\u002F\u002Fspacy.io) (Explosion) |\n| **License** | `CC BY-SA 4.0` |\n| **Author** | [Explosion](https:\u002F\u002Fexplosion.ai) |\n| **Model size** | 40 MB |\n\n### Label Scheme\n\n\u003Cdetails>\n\n\u003Csummary>View label scheme (540 labels for 3 components)\u003C\u002Fsummary>\n\n| Component | Labels |\n| --- | --- |\n| **`tagger`** | `ARROW`, `Af`, `Afcfp-n`, `Afcfson`, `Afcfsrn`, `Afcmpoy`, `Afcms-n`, `Afp`, `Afp-p-n`, `Afp-poy`, `Afp-srn`, `Afpf--n`, `Afpfp-n`, `Afpfp-ny`, `Afpfpoy`, `Afpfpry`, `Afpfson`, `Afpfsoy`, `Afpfsrn`, `Afpfsry`, `Afpm--n`, `Afpmp-n`, `Afpmpoy`, `Afpmpry`, `Afpms-n`, `Afpmsoy`, `Afpmsry`, `Afsfp-n`, `Afsfsrn`, `BULLET`, `COLON`, `COMMA`, `Ccssp`, `Ccsspy`, `Crssp`, `Csssp`, `Cssspy`, `DASH`, `DBLQ`, `Dd3-po---e`, `Dd3-po---o`, `Dd3fpo`, `Dd3fpr`, `Dd3fpr---e`, `Dd3fpr---o`, `Dd3fpr--y`, `Dd3fso`, `Dd3fso---e`, `Dd3fsr`, `Dd3fsr---e`, `Dd3fsr---o`, `Dd3fsr--yo`, `Dd3mpo`, `Dd3mpr`, `Dd3mpr---e`, `Dd3mpr---o`, `Dd3mso---e`, `Dd3msr`, `Dd3msr---e`, `Dd3msr---o`, `Dh1ms`, `Dh3fp`, `Dh3fso`, `Dh3fsr`, `Dh3mp`, `Dh3ms`, `Di3`, `Di3-----y`, `Di3--r---e`, `Di3-po`, `Di3-po---e`, `Di3-sr`, `Di3-sr---e`, `Di3-sr--y`, `Di3fp`, `Di3fpr`, `Di3fpr---e`, `Di3fso`, `Di3fso---e`, `Di3fsr`, `Di3fsr---e`, `Di3mp`, `Di3mpr`, `Di3mpr---e`, `Di3ms`, `Di3ms----e`, `Di3mso---e`, `Di3msr`, `Di3msr---e`, `Ds1fp-p`, `Ds1fp-s`, `Ds1fsop`, `Ds1fsos`, `Ds1fsrp`, `Ds1fsrs`, `Ds1fsrs-y`, `Ds1mp-p`, `Ds1mp-s`, `Ds1ms-p`, `Ds1ms-s`, `Ds1msrs-y`, `Ds2---s`, `Ds2fp-p`, `Ds2fp-s`, `Ds2fsrp`, `Ds2fsrs`, `Ds2mp-p`, `Ds2mp-s`, `Ds2ms-p`, `Ds2ms-s`, `Ds3---p`, `Ds3---s`, `Ds3---sy`, `Ds3fp-s`, `Ds3fsos`, `Ds3fsrs`, `Ds3mp-s`, `Ds3ms-s`, `Dw3--r---e`, `Dw3-po---e`, `Dw3fpr`, `Dw3fso---e`, `Dw3fsr`, `Dw3mpr`, `Dw3mso---e`, `Dw3msr`, `Dz3fsr---e`, `Dz3mso---e`, `Dz3msr---e`, `EQUAL`, `EXCL`, `EXCLHELLIP`, `GE`, `GT`, `HELLIP`, `I`, `LCURL`, `LPAR`, `LSQR`, `LT`, `M`, `Mc-p-d`, `Mc-p-l`, `Mc-s-b`, `Mc-s-d`, `Mc-s-l`, `Mcfp-l`, `Mcfp-ln`, `Mcfprln`, `Mcfprly`, `Mcfsoln`, `Mcfsrl`, `Mcfsrln`, `Mcfsrly`, `Mcmp-l`, `Mcms-ln`, `Mcmsrl`, `Mcmsrln`, `Mcmsrly`, `Mffprln`, `Mffsrln`, `Mlfpo`, `Mlfpr`, `Mlmpr`, `Mo---l`, `Mo---ln`, `Mo-s-r`, `Mofp-ln`, `Mofpoly`, `Mofprly`, `Mofs-l`, `Mofsoln`, `Mofsoly`, `Mofsrln`, `Mofsrly`, `Mompoly`, `Momprly`, `Moms-l`, `Moms-ln`, `Momsoly`, `Momsrly`, `Nc`, `Nc---n`, `Ncf--n`, `Ncfp-n`, `Ncfpoy`, `Ncfpry`, `Ncfs-n`, `Ncfson`, `Ncfsoy`, `Ncfsrn`, `Ncfsry`, `Ncfsryy`, `Ncfsvy`, `Ncm--n`, `Ncmp-n`, `Ncmpoy`, `Ncmpry`, `Ncms-n`, `Ncms-ny`, `Ncms-y`, `Ncmsoy`, `Ncmsrn`, `Ncmsry`, `Ncmsryy`, `Ncmsvn`, `Ncmsvy`, `Np`, `Npfson`, `Npfsoy`, `Npfsrn`, `Npfsry`, `Npmpoy`, `Npmpry`, `Npms-n`, `Npmsoy`, `Npmsry`, `PERCENT`, `PERIOD`, `PLUS`, `PLUSMINUS`, `Pd3-po`, `Pd3fpr`, `Pd3fso`, `Pd3fsr`, `Pd3mpo`, `Pd3mpr`, `Pd3mpr--y`, `Pd3mso`, `Pd3msr`, `Pi3--r`, `Pi3-po`, `Pi3-so`, `Pi3-sr`, `Pi3fpr`, `Pi3fso`, `Pi3fsr`, `Pi3mpr`, `Pi3mso`, `Pi3msr`, `Pi3msr--y`, `Pp1-pa--------w`, `Pp1-pa--y-----w`, `Pp1-pd--------s`, `Pp1-pd--------w`, `Pp1-pd--y-----w`, `Pp1-pr--------s`, `Pp1-sa--------s`, `Pp1-sa--------w`, `Pp1-sa--y-----w`, `Pp1-sd--------s`, `Pp1-sd--------w`, `Pp1-sd--y-----w`, `Pp1-sn--------s`, `Pp2-----------s`, `Pp2-pa--------w`, `Pp2-pa--y-----w`, `Pp2-pd","2024-09-30T10:00:14"]