docs: make Chinese README the default

README.md

@@ -1,13 +1,19 @@
+<!-- WEHUB_ZH_README -->
+> [!NOTE]
+> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。  
+> [English](./README.en.md) · [原始项目](https://github.com/Light-Heart-Labs/DreamServer) · [上游 README](https://github.com/Light-Heart-Labs/DreamServer/blob/HEAD/README.md)  
+> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
+
 <div align="center">
 
 # ODS
 
 **Osmantic Deployment System**
 
-**Turn your PC, Mac, or Linux box into a private AI server.**
+**将你的 PC、Mac 或 Linux 机器变成私有 AI 服务器。**
 
-AI server and homelab setup is rapidly becoming a solved problem.
-It should feel that way for everyone.
+AI 服务器与 homelab（家庭实验室）搭建正在迅速成为一项已解决的问题。
+每个人都理应如此感受。
 
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)
 [![GitHub Stars](https://img.shields.io/github/stars/Light-Heart-Labs/ODS)](https://github.com/Light-Heart-Labs/ODS/stargazers)
@@ -19,141 +25,120 @@ It should feel that way for everyone.
 
 ---
 
-ODS installs and wires together everything you need to run AI locally, so you do not have to assemble Ollama, Open WebUI, n8n, ComfyUI, and privacy tools by hand:
+ODS 会安装并串联你在本地运行 AI 所需的一切，你无需再手动拼装 Ollama、Open WebUI、n8n、ComfyUI 以及各类隐私工具：
 
-- **Local model inference** — run open models on your own hardware
-- **ChatGPT-style web UI** — talk to your models from any browser
-- **Control dashboard** — manage models, services, setup, GPU status, and extensions from one place
-- **Voice, agents, and workflows** — build automations that can listen, speak, call tools, and get work done
-- **RAG and search** — connect local documents, private search, and retrieval workflows
-- **Image generation** — run local image tools without sending prompts to a hosted API
-- **Privacy and ops** — keep service auth, secrets, observability, and diagnostics in one local stack
+- **本地模型推理（local model inference）** — 在你自己的硬件上运行开源模型
+- **ChatGPT 风格 Web UI** — 从任意浏览器与你的模型对话
+- **控制面板（control dashboard）** — 在一个地方管理模型、服务、配置、GPU 状态与扩展
+- **语音、智能体与工作流** — 构建能听、能说、调用工具并完成任务的自动化
+- **RAG 与搜索** — 连接本地文档、私有搜索与检索工作流
+- **图像生成** — 运行本地图像工具，无需将提示词发送到托管 API
+- **隐私与运维** — 将服务认证、密钥、可观测性与诊断集中在一套本地栈中
 
-No cloud required. No subscriptions required. Your prompts and data stay on your machine unless you choose otherwise. Cloud and hybrid API modes are optional when you want them.
+无需云端。无需订阅。你的提示词和数据留在本机，除非你主动选择其他方式。需要时，云端与混合 API 模式为可选项。
 
-**Release validation:** Operational changes are checked with a release-grade
-fleet and distro lab: zero-prereq bootstrap, fresh installs, product flows,
-full-model capabilities, lifecycle recovery, and the final User Green gate. See
-[Release Validation](ods/docs/RELEASE_VALIDATION.md) for what a green
-run proves.
+**发布验证：** 运维变更会通过发布级 fleet 与发行版实验室（distro lab）校验：零前置依赖引导、全新安装、产品流程、全模型能力、生命周期恢复，以及最终的 User Green（用户绿灯）关卡。请参阅 [Release Validation](ods/docs/RELEASE_VALIDATION.md) 了解一次 green run 所证明的内容。
 
-**Repo layout:** the repository root holds the public README, installers,
-security policy, GitHub workflows, and project coordination docs. The
-`ods/` directory is the product runtime: services, installer phases,
-compose overlays, dashboard, CLI, tests, and operator docs.
+**仓库结构：** 仓库根目录存放公开 README、安装器、安全策略、GitHub workflows 与项目协作文档。`ods/` 目录是产品运行时：服务、安装阶段、compose overlays、dashboard、CLI、测试与运维文档。
 
-**Stable consumption:** `v2.5.2` is the current stable release. `main` moves
-quickly; use it for active development and validation candidates. For forks,
-appliances, labs, or production-like installs, pin a tagged release or audited
-commit and keep your own validation receipt. Stable patch fixes land on
-`release/2.5.x` before being merged forward. See
-[Release Channels](ods/docs/RELEASE_CHANNELS.md),
-[Installer Trust](ods/docs/INSTALLER_TRUST.md), and
-[Forkability](ods/docs/FORKABILITY.md).
+**稳定版使用：** `v2.5.2` 是当前稳定发布版。`main` 迭代较快；用于活跃开发与验证候选。对于 fork、一体机、实验室或类生产安装，请固定（pin）带标签的发布版或经审计的 commit，并保留你自己的验证记录。稳定补丁修复会先落在 `release/2.5.x`，再向前合并。请参阅 [Release Channels](ods/docs/RELEASE_CHANNELS.md)、[Installer Trust](ods/docs/INSTALLER_TRUST.md) 与 [Forkability](ods/docs/FORKABILITY.md)。
 
-## Get Started
+## 快速开始
 
-Linux and macOS:
+Linux 与 macOS：
 
 ```bash
 curl -fsSL https://raw.githubusercontent.com/Light-Heart-Labs/ODS/main/ods/get-ods.sh | bash
 ```
 
-Prefer to inspect before running or pin a release tag? See
-[Installer Trust](ods/docs/INSTALLER_TRUST.md).
+想先检查再运行，或固定某个发布标签？请参阅 [Installer Trust](ods/docs/INSTALLER_TRUST.md)。
 
-Windows users should use the PowerShell installer shown below or follow the [Windows Quickstart](ods/docs/WINDOWS-QUICKSTART.md).
+Windows 用户应使用下方所示的 PowerShell 安装器，或参阅 [Windows Quickstart](ods/docs/WINDOWS-QUICKSTART.md)。
 
-After install, open **http://localhost:3000** and start chatting.
+安装完成后，打开 **http://localhost:3000** 并开始聊天。
 
-> **API endpoint:** Linux Docker installs expose llama-server on **http://localhost:11434** by default (`OLLAMA_PORT`) while containers use `llama-server:8080`. macOS native Metal and Windows native/Lemonade paths use **http://localhost:8080** unless overridden. Open WebUI stays on **http://localhost:3000**.
+> **API 端点：** Linux Docker 安装默认在 **http://localhost:11434** 暴露 llama-server（`OLLAMA_PORT`），而容器使用 `llama-server:8080`。macOS 原生 Metal 与 Windows 原生/Lemonade 路径默认使用 **http://localhost:8080**，除非另行覆盖。Open WebUI 保持在 **http://localhost:3000**.
 
-> **No GPU?** ODS also runs in cloud mode — same full stack, powered by OpenAI/Anthropic/Together APIs instead of local inference:
+> **没有 GPU？** ODS 也可运行于云端模式 — 同一完整栈，由 OpenAI/Anthropic/Together API 驱动，而非本地推理：
 > ```bash
 > ./install.sh --cloud
 > ```
 
-> **Port conflicts?** Every port is configurable via environment variables. See [`.env.example`](ods/.env.example) for the full list, or override at install time:
+> **端口冲突？** 每个端口均可通过环境变量配置。完整列表见 [`.env.example`](ods/.env.example)，或在安装时覆盖：
 > ```bash
 > WEBUI_PORT=9090 ./install.sh
 > ```
 
 ![ODS Dashboard](ods/docs/images/dashboard.png)
 
-**New here?** Read the [Friendly Guide](ods/docs/HOW-ODS-SERVER-WORKS.md) or [listen to the audio version](https://open.spotify.com/episode/40MvqJ41bC8cEgvUyOyE3K) — a complete walkthrough of what ODS is, how it works, and how to make it your own. No technical background needed.
+**初次接触？** 阅读 [Friendly Guide](ods/docs/HOW-ODS-SERVER-WORKS.md)，或 [收听音频版](https://open.spotify.com/episode/40MvqJ41bC8cEgvUyOyE3K) — 完整讲解 ODS 是什么、如何工作，以及如何把它变成你自己的。无需技术背景。
 
 ---
 
-## At A Glance
+## 一览
 
-| Question | Answer |
+| 问题 | 答案 |
 |----------|--------|
-| **What is it?** | A local AI server stack for your own hardware, with a one-command Linux/macOS installer and a PowerShell installer for Windows. |
-| **Who is it for?** | People who want private AI at home, in a lab, or on a workstation without hand-wiring a dozen services. |
-| **What do I get?** | Local inference, Open WebUI chat, a control dashboard, voice, agents, workflows, RAG, search, image generation, privacy tools, observability, and developer tools. |
-| **What does it run on?** | Linux, Windows with WSL2/Docker Desktop, and macOS Apple Silicon. |
-| **Is cloud required?** | No. Local mode is the default; cloud and hybrid API modes are optional. |
+| **它是什么？** | 面向自有硬件的本地 AI 服务器栈，提供 Linux/macOS 一键安装器与 Windows PowerShell 安装器。 |
+| **适合谁？** | 希望在家、实验室或工作站上获得私有 AI，而无需手动串联十几个服务的人。 |
+| **我能得到什么？** | 本地推理、Open WebUI 聊天、控制面板、语音、智能体、工作流、RAG、搜索、图像生成、隐私工具、可观测性与开发者工具。 |
+| **运行在什么上？** | Linux、带 WSL2/Docker Desktop 的 Windows，以及 macOS Apple Silicon。 |
+| **需要云端吗？** | 不需要。本地模式为默认；云端与混合 API 模式为可选。 |
 
-| If you know... | ODS adds... |
+| 如果你了解... | ODS 额外提供... |
 |----------------|----------------------|
-| **Ollama / llama.cpp** | The surrounding server stack: chat, dashboard, voice, RAG, workflows, agents, privacy, and service management. |
-| **Open WebUI** | A full installer and control plane around Open WebUI, plus pre-wired local services. |
-| **AnythingLLM** | Broader local AI appliance behavior beyond RAG: inference, chat, voice, workflows, image generation, and ops. |
-| **n8n self-hosted AI starter kits** | Workflow automation as one part of a larger private AI server. |
+| **Ollama / llama.cpp** | 围绕其外的服务器栈：聊天、面板、语音、RAG、工作流、智能体、隐私与服务管理。 |
+| **Open WebUI** | 围绕 Open WebUI 的完整安装器与控制平面，以及预接线的本地服务。 |
+| **AnythingLLM** | 超越 RAG 的更广本地 AI 一体机能力：推理、聊天、语音、工作流、图像生成与运维。 |
+| **n8n 自托管 AI starter kits** | 作为更大私有 AI 服务器一部分的工作流自动化。 |
 
 ---
 
-> **Current Platform Support**
+> **当前平台支持**
 >
-> | Platform | Status |
+> | 平台 | 状态 |
 > |----------|--------|
-> | **Linux** (NVIDIA + AMD + Intel Arc) | **Supported** — install and run today |
-> | **Windows** (NVIDIA + AMD) | **Supported** — install and run today |
-> | **macOS** (Apple Silicon) | **Supported** — install and run today |
+> | **Linux**（NVIDIA + AMD + Intel Arc） | **已支持** — 今日即可安装运行 |
+> | **Windows**（NVIDIA + AMD） | **已支持** — 今日即可安装运行 |
+> | **macOS**（Apple Silicon） | **已支持** — 今日即可安装运行 |
 >
-> **Tested Linux distros:** Ubuntu 24.04/22.04, Debian 12, Linux Mint 21.3, Fedora 41+, Rocky Linux 9, Arch Linux, Manjaro, CachyOS, and openSUSE Tumbleweed. Other distros using apt, dnf, pacman, or zypper should also work — [open an issue](https://github.com/Light-Heart-Labs/ODS/issues) if yours doesn't.
+> **已测试 Linux 发行版：** Ubuntu 24.04/22.04、Debian 12、Linux Mint 21.3、Fedora 41+、Rocky Linux 9、Arch Linux、Manjaro、CachyOS 与 openSUSE Tumbleweed。使用 apt、dnf、pacman 或 zypper 的其他发行版通常也可用 — 若你的不行，请 [提交 issue](https://github.com/Light-Heart-Labs/ODS/issues)。
 >
-> **Release validation:** Operational changes run through a release-grade gate
-> that covers zero-prereq bootstrap, clean installs, product behavior,
-> full-model capabilities, lifecycle recovery, and User Green. See
-> [Release Validation](ods/docs/RELEASE_VALIDATION.md) and the
-> [Validation Matrix](ods/docs/VALIDATION-MATRIX.md).
+> **发布验证：** 运维变更会经过发布级关卡，覆盖零前置依赖引导、干净安装、产品行为、全模型能力、生命周期恢复与 User Green。请参阅 [Release Validation](ods/docs/RELEASE_VALIDATION.md) 与 [Validation Matrix](ods/docs/VALIDATION-MATRIX.md)。
 >
-> **Windows:** Requires Docker Desktop with WSL2 backend. NVIDIA GPUs use Docker GPU passthrough; AMD Strix Halo runs through the platform-specific accelerated path documented in the Windows installer and support matrix.
+> **Windows：** 需要带 WSL2 后端的 Docker Desktop。NVIDIA GPU 使用 Docker GPU 直通；AMD Strix Halo 通过 Windows 安装器与支持矩阵中记录的平台专用加速路径运行。
 >
-> **macOS:** Requires Apple Silicon (M1+) and Docker Desktop. llama-server runs natively with Metal GPU acceleration; all other services run in Docker.
+> **macOS：** 需要 Apple Silicon（M1+）与 Docker Desktop。llama-server 以 Metal GPU 加速原生运行；其余服务在 Docker 中运行。
 >
-> See the [Support Matrix](ods/docs/SUPPORT-MATRIX.md) for supported
-> platform claims and the [Validation Matrix](ods/docs/VALIDATION-MATRIX.md)
-> for the layered test surface used to test those claims.
+> 平台支持声明见 [Support Matrix](ods/docs/SUPPORT-MATRIX.md)，用于验证这些声明的分层测试面见 [Validation Matrix](ods/docs/VALIDATION-MATRIX.md)。
 
 ---
 
-## Why ODS?
+## 为何选择 ODS？
 
-A handful of companies control the vast majority of global AI traffic — and with it, your data, your costs, and your uptime. Every query you send to a centralized provider is business intelligence you don’t own, running on infrastructure you don’t control, priced on terms you can’t negotiate.
+少数公司掌控着全球绝大多数 AI 流量 — 连同你的数据、成本与可用性。你发给中心化提供商的每一次查询，都是你不拥有的商业情报，运行在你无法掌控的基础设施上，按你无法谈判的条款定价。
 
-If AI is becoming critical infrastructure, it shouldn’t be rented. Self-hosting local AI should be a sovereign human right, not a career choice.
+如果 AI 正在成为关键基础设施，它就不该被租用。自托管本地 AI 应是一项主权人权，而非职业选择。
 
-Because running your own AI shouldn't require a CS degree and a weekend of debugging CUDA drivers. Right now, setting up local AI means stitching together a dozen projects, writing Docker configs from scratch, and praying everything talks to each other. Most people give up and go back to paying OpenAI.
+因为运行自己的 AI 不应需要计算机学位，也不该花一个周末调试 CUDA 驱动。如今搭建本地 AI 意味着拼接十几个项目、从零编写 Docker 配置，并祈祷一切能互相通信。大多数人会放弃，回到付费使用 OpenAI。
 
-We built ODS so you don't have to.
+我们打造 ODS，就是让你不必如此。
 
-- **One command** — detects your GPU, picks the right model, generates credentials, launches everything
-- **Chatting in under 2 minutes** — bootstrap mode gives you a working model instantly while your full model downloads in the background
-- **Full service stack, pre-wired** — chat, agents, voice, workflows, search, RAG, image generation, privacy tools, observability, and developer tools. All talking to each other out of the box
-- **Fully moddable** — every service is an extension. Drop in a folder, run `ods enable`, done
+- **一条命令** — 检测 GPU、选择合适模型、生成凭据、启动一切
+- **不到 2 分钟即可聊天** — 引导模式在完整模型后台下载时，立即给你一个可用模型
+- **完整服务栈，预接线** — 聊天、智能体、语音、工作流、搜索、RAG、图像生成、隐私工具、可观测性与开发者工具，开箱即用、彼此互通
+- **完全可改装** — 每个服务都是扩展。放入一个文件夹，运行 `ods enable`，完成
 
 <div align="center">
 
 ![ODS Installer](ods/docs/images/installer-splash.gif)
 
-*The ODSGATE installer handles everything — GPU detection, model selection, service orchestration.*
+*ODSGATE 安装程序会处理一切——GPU 检测、模型选择与服务编排。*
 
 </div>
 
 <details>
-<summary><b>Manual install (Linux)</b></summary>
+<summary><b>手动安装（Linux）</b></summary>
 
 ```bash
 git clone https://github.com/Light-Heart-Labs/ODS.git
@@ -164,12 +149,12 @@ cd ODS/ods
 </details>
 
 <details>
-<summary><b>Windows (PowerShell)</b></summary>
+<summary><b>Windows（PowerShell）</b></summary>
 
-Requires [Docker Desktop](https://www.docker.com/products/docker-desktop/) with WSL2 backend enabled.
-**Install Docker Desktop first and make sure it is running before you start.**
+需要启用 WSL2 后端的 [Docker Desktop](https://www.docker.com/products/docker-desktop/) with WSL2 backend enabled.
+**请先安装 Docker Desktop，并在开始前确保其正在运行。**
 
-Open a normal **PowerShell** session and run:
+打开一个普通的 **PowerShell** 会话并运行：
 
 ```powershell
 Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass
@@ -178,18 +163,18 @@ cd ODS
 .\install.ps1
 ```
 
-> The `Set-ExecutionPolicy` command allows the installer script to run in the current session. It does not change your system-wide policy.
-> Running as Administrator is not recommended for the installer because user-level paths such as `.opencode`, `data/`, and `.env` can be created with admin-owned permissions.
+> `Set-ExecutionPolicy` 命令允许安装脚本在当前会话中运行。它不会更改你的系统级策略。
+> 不建议以管理员身份运行安装程序，因为 `.opencode`、`data/` 和 `.env` 等用户级路径可能会以管理员拥有的权限创建。
 
-The installer detects your GPU, picks the right model, generates credentials, starts all services, and creates a Desktop shortcut to the Dashboard. Manage with `.\ods\installers\windows\ods.ps1 status`.
+安装程序会检测你的 GPU、选择合适模型、生成凭据、启动所有服务，并创建指向 Dashboard 的桌面快捷方式。使用 `.\ods\installers\windows\ods.ps1 status` 进行管理。
 
 </details>
 
 <details>
-<summary><b>macOS (Apple Silicon)</b></summary>
+<summary><b>macOS（Apple Silicon）</b></summary>
 
-Requires Apple Silicon (M1+) and [Docker Desktop](https://www.docker.com/products/docker-desktop/).
-**Install Docker Desktop first and make sure it is running before you start.**
+需要 Apple Silicon（M1+）和 [Docker Desktop](https://www.docker.com/products/docker-desktop/).
+**请先安装 Docker Desktop，并在开始前确保其正在运行。**
 
 ```bash
 git clone https://github.com/Light-Heart-Labs/ODS.git
@@ -197,130 +182,130 @@ cd ODS/ods
 ./install.sh
 ```
 
-The installer detects your chip, picks the right model for your unified memory, launches llama-server natively with Metal acceleration, and starts all other services in Docker. Manage with `./ods-macos.sh status`.
+安装程序会检测你的芯片、根据统一内存选择合适模型，以 Metal 加速原生启动 llama-server，并在 Docker 中启动所有其他服务。使用 `./ods-macos.sh status` 进行管理。
 
-See the [macOS Quickstart](ods/docs/MACOS-QUICKSTART.md) for details.
+详见 [macOS 快速入门](ods/docs/MACOS-QUICKSTART.md)。
 
 </details>
 
 ---
 
-## What's In The Box
+## 开箱即用
 
-### Chat & Inference
-- **Open WebUI** — full-featured chat interface with conversation history, web search, document upload, and [30+ languages](https://docs.openwebui.com)
-- **llama-server** — high-performance LLM inference with continuous batching, auto-selected for your GPU; Linux Docker host API defaults to `localhost:11434`, native macOS/Windows paths use `localhost:8080`, and container API runs on `8080`
-- **LiteLLM** — API gateway supporting local/cloud/hybrid modes
-- **TEI Embeddings** — text embedding service for RAG and search workflows
+### 聊天与推理
+- **Open WebUI** — 功能完整的聊天界面，支持对话历史、网页搜索、文档上传，以及 [30+ 种语言](https://docs.openwebui.com)
+- **llama-server** — 高性能 LLM 推理，支持连续批处理（continuous batching），会根据你的 GPU 自动选择；Linux Docker 主机 API 默认为 `localhost:11434`，macOS/Windows 原生路径使用 `localhost:8080`，容器 API 运行于 `8080`
+- **LiteLLM** — 支持本地/云端/混合模式的 API 网关
+- **TEI Embeddings** — 用于 RAG 与搜索工作流的文本嵌入服务
 
-### Voice
-- **Whisper** — speech-to-text
-- **Kokoro** — text-to-speech
+### 语音
+- **Whisper** — 语音转文字（speech-to-text）
+- **Kokoro** — 文字转语音（text-to-speech）
 
-### Agents & Automation
-- **Hermes Agent** — default local-first autonomous/browser agent with memory, skills, and a magic-link-gated proxy
-- **OpenClaw** — deprecated legacy autonomous agent, still opt-in during the migration window
-- **n8n** — workflow automation with 400+ integrations (Slack, email, databases, APIs)
-- **APE** — Agent Policy Engine for auditing and governing autonomous tool calls
-- **OpenCode** — browser-based AI coding assistant wired to the local stack
-- **Memory Shepherd** — host/systemd helper for agent memory lifecycle management
+### 智能体与自动化
+- **Hermes Agent** — 默认的本地优先自主/浏览器智能体，具备记忆、技能，以及魔法链接（magic-link）门控代理
+- **OpenClaw** — 已弃用的旧版自主智能体，在迁移窗口期内仍可自愿启用
+- **n8n** — 工作流自动化，集成 400+ 种服务（Slack、邮件、数据库、API）
+- **APE** — 智能体策略引擎（Agent Policy Engine），用于审计与治理自主工具调用
+- **OpenCode** — 基于浏览器的 AI 编程助手，已接入本地技术栈
+- **Memory Shepherd** — 用于智能体记忆生命周期管理的宿主机/systemd 辅助工具
 
-### Knowledge & Search
-- **Qdrant** — vector database for retrieval-augmented generation (RAG)
-- **SearXNG** — self-hosted web search (no tracking)
-- **Perplexica** — deep research engine
-- **Brave Search** — optional paid Brave Search API integration
+### 知识与搜索
+- **Qdrant** — 用于检索增强生成（RAG）的向量数据库
+- **SearXNG** — 自托管网页搜索（无追踪）
+- **Perplexica** — 深度研究引擎
+- **Brave Search** — 可选的付费 Brave Search API 集成
 
-### Creative
-- **ComfyUI** — node-based image generation
+### 创意
+- **ComfyUI** — 基于节点的图像生成
 
-### Privacy & Ops
-- **Privacy Shield** — PII scrubbing proxy for API calls
-- **Dashboard** — real-time GPU metrics, service health, model management
-- **Dashboard API** — service health, setup, status, metrics, and management API behind the dashboard
-- **Token Spy** — token usage monitor for local and proxied LLM traffic
-- **Langfuse** — optional LLM observability and tracing
+### 隐私与运维
+- **Privacy Shield** — 用于 API 调用的 PII 脱敏代理
+- **Dashboard** — 实时 GPU 指标、服务健康状态、模型管理
+- **Dashboard API** — Dashboard 背后的服务健康、设置、状态、指标与管理 API
+- **Token Spy** — 本地与代理 LLM 流量的 token 用量监控
+- **Langfuse** — 可选的 LLM 可观测性与追踪
 
 ---
 
-## Hardware Auto-Detection
+## 硬件自动检测
 
-The installer detects your GPU and first assigns a deterministic hardware tier. Linux and macOS then run the versioned catalog selector (`ods/scripts/select-model.py`), while Windows uses the PowerShell catalog selector in `ods/installers/windows/lib/tier-map.ps1`; both read `ods/config/model-library.json` to choose the best installable GGUF for the detected memory envelope. The final choice is written to `.env` as `LLM_MODEL`, `GGUF_FILE`, `MAX_CONTEXT`, and `MODEL_RECOMMENDATION_*`.
+安装程序会检测你的 GPU，并首先分配一个确定性的硬件层级（tier）。Linux 与 macOS 随后运行带版本号的目录选择器（`ods/scripts/select-model.py`），而 Windows 使用 `ods/installers/windows/lib/tier-map.ps1` 中的 PowerShell 目录选择器；两者都会读取 `ods/config/model-library.json`，以根据检测到的内存容量选择最佳可安装 GGUF。最终选择会写入 `.env`，对应 `LLM_MODEL`、`GGUF_FILE`、`MAX_CONTEXT` 和 `MODEL_RECOMMENDATION_*`。
 
-`MODEL_PROFILE=qwen` is the default non-Gemma catalog profile, so the effective pick can be Qwen, Phi, or DeepSeek depending on what fits best. `MODEL_PROFILE=gemma4` forces Gemma 4 where available, and `MODEL_PROFILE=auto` uses Gemma 4 on NVIDIA, Apple Silicon, and Intel Arc tiers. Override tier selection with `./install.sh --tier 3`; override the model family with `MODEL_PROFILE=gemma4 ./install.sh` or `MODEL_PROFILE=auto ./install.sh`.
+`MODEL_PROFILE=qwen` 是默认的非 Gemma 目录配置，因此实际选择可能是 Qwen、Phi 或 DeepSeek，取决于哪种最合适。`MODEL_PROFILE=gemma4` 会在可用时强制使用 Gemma 4，`MODEL_PROFILE=auto` 会在 NVIDIA、Apple Silicon 和 Intel Arc 层级上使用 Gemma 4。可使用 `./install.sh --tier 3` 覆盖层级选择；使用 `MODEL_PROFILE=gemma4 ./install.sh` 或 `MODEL_PROFILE=auto ./install.sh` 覆盖模型系列。
 
-When Hermes is enabled, which is the default agent path, installers keep the first-run bootstrap model at a 64K context floor and promote the full local model context to 128K where the selected model supports it. That avoids Hermes's hard 64K minimum while preserving the under-2-minute first chat experience. The examples below are current catalog-selector outputs for common hardware envelopes; exact installs can differ with detected VRAM/RAM, host architecture, existing downloads, or explicit profile overrides. Throughput still needs a local benchmark after first launch.
+当 Hermes 启用时（这是默认的智能体路径），安装程序会将首次运行的引导模型保持在 64K 上下文下限，并在所选模型支持的情况下将完整本地模型上下文提升至 128K。这样既能满足 Hermes 硬性 64K 最低要求，又能保留首次聊天不到 2 分钟的体验。以下示例是当前目录选择器在常见硬件容量下的输出；实际安装可能因检测到的 VRAM/RAM、主机架构、已有下载或显式配置覆盖而有所不同。首次启动后，吞吐量仍需进行本地基准测试。
 
 ### NVIDIA
 
-| Tier / envelope | Current default catalog pick | Context | Example hardware |
+| 层级 / 容量 | 当前默认目录选择 | 上下文 | 示例硬件 |
 |------|--------------|---------|--------------|
-| 0 / 8 GB CPU fallback | Qwen3.5 2B (Q4_K_M) | 8K | Low-RAM CPU-only |
-| 1 / 8 GB discrete VRAM | Qwen3.5 9B (Q4_K_M) | 32K | RTX 4060, RTX 3060 12GB |
-| 2 / 12 GB discrete VRAM | Phi-4 14B (Q4_K_M) | 16K | RTX 4070-class cards |
-| 3 / 24 GB discrete VRAM | Qwen3.5 27B (Q4_K_M) | 32K | RTX 4090, A6000 |
-| 4 / 48 GB discrete VRAM | DeepSeek R1 Distill Llama 70B (Q4_K_M) | 32K | A6000 Ada, L40S |
-| NV_ULTRA / 90+ GB amd64 discrete VRAM | Qwen3 Coder Next (Q4_K_M) | 128K | Multi-GPU A100/H100 |
-| NV_ULTRA / 90+ GB arm64 unified memory | Qwen3.6 35B-A3B (UD-Q4_K_M) | 128K | DGX Spark / GB10-class hosts |
+| 0 / 8 GB CPU 回退 | Qwen3.5 2B (Q4_K_M) | 8K | 低内存纯 CPU |
+| 1 / 8 GB 独立 VRAM | Qwen3.5 9B (Q4_K_M) | 32K | RTX 4060、RTX 3060 12GB |
+| 2 / 12 GB 独立 VRAM | Phi-4 14B (Q4_K_M) | 16K | RTX 4070 级别显卡 |
+| 3 / 24 GB 独立 VRAM | Qwen3.5 27B (Q4_K_M) | 32K | RTX 4090、A6000 |
+| 4 / 48 GB 独立 VRAM | DeepSeek R1 Distill Llama 70B (Q4_K_M) | 32K | A6000 Ada、L40S |
+| NV_ULTRA / 90+ GB amd64 独立 VRAM | Qwen3 Coder Next (Q4_K_M) | 128K | 多 GPU A100/H100 |
+| NV_ULTRA / 90+ GB arm64 统一内存 | Qwen3.6 35B-A3B (UD-Q4_K_M) | 128K | DGX Spark / GB10 级别主机 |
 
-### AMD Strix Halo (Unified Memory)
+### AMD Strix Halo（统一内存）
 
-| Tier / envelope | Current default catalog pick | Context | Hardware |
+| 层级 / 容量 | 当前默认目录选择 | 上下文 | 硬件 |
 |------|--------------|---------|----------|
-| SH_COMPACT / 64 GB unified RAM | Qwen3.6 35B-A3B (UD-Q4_K_M) | 128K | Ryzen AI MAX+ 395 (64GB) |
-| SH_LARGE / 96 GB unified RAM | DeepSeek R1 Distill Llama 70B (Q4_K_M) | 32K | Ryzen AI MAX+ 395 (96GB) |
-| SH_LARGE / 124 GB unified RAM | Qwen3.6 35B-A3B (UD-Q4_K_M) | 128K | Ryzen AI MAX+ 395 (128GB class) |
+| SH_COMPACT / 64 GB 统一 RAM | Qwen3.6 35B-A3B (UD-Q4_K_M) | 128K | Ryzen AI MAX+ 395 (64GB) |
+| SH_LARGE / 96 GB 统一 RAM | DeepSeek R1 Distill Llama 70B (Q4_K_M) | 32K | Ryzen AI MAX+ 395 (96GB) |
+| SH_LARGE / 124 GB 统一 RAM | Qwen3.6 35B-A3B (UD-Q4_K_M) | 128K | Ryzen AI MAX+ 395 (128GB 级别) |
 
-The selector routes unified-memory hosts away from Qwen3 Coder Next when that model would otherwise be selected, because current repo policy documents correctness issues on those backends.
+当否则会选中 Qwen3 Coder Next 时，选择器会将统一内存主机路由到其他模型，因为当前仓库策略文档记录了这些后端上的正确性问题。
 
-### Apple Silicon (Unified Memory, Metal)
+### Apple Silicon（统一内存，Metal）
 
-| Tier / envelope | Current default catalog pick | Context | Example hardware |
+| 层级 / 容量 | 当前默认目录选择 | 上下文 | 示例硬件 |
 |------|--------------|---------|-----------------|
-| 0 / 8 GB unified RAM | Phi-4 Mini (Q4_K_M) | 128K | M1/M2 base (8GB) |
-| 1 / 16 GB unified RAM | Qwen3.5 9B (Q4_K_M) | 32K | M4 Mac Mini (16GB) |
-| 2 / 32 GB unified RAM | Phi-4 14B (Q4_K_M) | 16K | M4 Pro Mac Mini, M3 Max MacBook Pro |
-| 3 / 48 GB unified RAM | Qwen3.5 27B (Q4_K_M) | 32K | M4 Pro (48GB), M2 Max (48GB) |
-| 4 / 64+ GB unified RAM | Qwen3.6 35B-A3B (UD-Q4_K_M) | 128K | M2 Ultra Mac Studio, M4 Max (64GB+) |
+| 0 / 8 GB 统一 RAM | Phi-4 Mini (Q4_K_M) | 128K | M1/M2 基础款 (8GB) |
+| 1 / 16 GB 统一 RAM | Qwen3.5 9B (Q4_K_M) | 32K | M4 Mac Mini (16GB) |
+| 2 / 32 GB 统一 RAM | Phi-4 14B (Q4_K_M) | 16K | M4 Pro Mac Mini、M3 Max MacBook Pro |
+| 3 / 48 GB 统一 RAM | Qwen3.5 27B (Q4_K_M) | 32K | M4 Pro (48GB)、M2 Max (48GB) |
+| 4 / 64+ GB 统一 RAM | Qwen3.6 35B-A3B (UD-Q4_K_M) | 128K | M2 Ultra Mac Studio、M4 Max (64GB+) |
 
-### Intel Arc (Linux, SYCL)
+### Intel Arc（Linux，SYCL）
 
-| Tier / envelope | Current default catalog pick | Context | Example hardware |
+| 层级 / 容量 | 当前默认目录选择 | 上下文 | 示例硬件 |
 |------|--------------|---------|------------------|
-| ARC_LITE / 6 GB discrete VRAM | Phi-4 Mini (Q4_K_M) | 128K | Arc A380 |
-| ARC_LITE / 8 GB discrete VRAM | Qwen3.5 9B (Q4_K_M) | 32K | Arc A750 |
-| ARC / 16 GB discrete VRAM | Phi-4 14B (Q4_K_M) | 16K | Arc A770 16GB, newer Arc GPUs |
+| ARC_LITE / 6 GB 独立 VRAM | Phi-4 Mini (Q4_K_M) | 128K | Arc A380 |
+| ARC_LITE / 8 GB 独立 VRAM | Qwen3.5 9B (Q4_K_M) | 32K | Arc A750 |
+| ARC / 16 GB 独立 VRAM | Phi-4 14B (Q4_K_M) | 16K | Arc A770 16GB、较新 Arc GPU |
 
-Gemma 4 profile tiers remain in the installer tier maps: E2B on entry hardware, E4B on midrange hardware, 26B-A4B on pro hardware, and 31B on large/ultra hardware.
+Gemma 4 配置层级仍保留在安装程序的层级映射中：入门级硬件为 E2B，中端硬件为 E4B，专业级硬件为 26B-A4B，大型/旗舰级硬件为 31B。
 
 ---
 
-## Bootstrap Mode
+## 引导模式（Bootstrap Mode）
 
-No waiting for large downloads. ODS uses bootstrap mode by default:
+无需等待大型下载。ODS 默认使用引导模式：
 
-1. Downloads a tiny 1.5B model in under a minute
-2. You start chatting immediately
-3. The full model downloads in the background
-4. Hot-swap to the full model when it's ready — zero downtime
+1. 不到一分钟即可下载一个 1.5B 的小型模型
+2. 可立即开始聊天
+3. 完整模型在后台下载
+4. 就绪后热切换到完整模型——零停机
 
 <div align="center">
 
-![Installer downloading modules](ods/docs/images/installer-download.png)
+![安装程序正在下载模块](ods/docs/images/installer-download.png)
 
-*The installer pulls all services in parallel. Downloads are resume-capable — interrupted downloads pick up where they left off.*
+*安装程序会并行拉取所有服务。下载支持断点续传——中断后可从上次位置继续。*
 
 </div>
 
-The bootstrap model starts with a 64K context window so Hermes can work during the first session. After the background download finishes, ODS swaps to the full model and restores the Hermes/full-model context target.
+引导模型（bootstrap model）初始提供 64K 上下文窗口，以便 Hermes 在首次会话期间可用。后台下载完成后，ODS 会切换到完整模型，并恢复 Hermes/完整模型的上下文目标。
 
-Skip bootstrap: `./install.sh --no-bootstrap`
+跳过引导：`./install.sh --no-bootstrap`
 
 ---
 
-## Switching Models
+## 切换模型
 
-The installer picks a model for your hardware, but you can switch anytime:
+安装程序会根据你的硬件选择模型，但你可随时切换：
 
 ```bash
 ods model current              # What's running now?
@@ -328,35 +313,35 @@ ods model list                 # Show all available tiers
 ods model swap T3              # Switch to a different tier
 ```
 
-If the new model isn't downloaded yet, pre-fetch it first:
+若新模型尚未下载，请先预取：
 
 ```bash
 ./scripts/pre-download.sh --tier 3    # Download before switching
 ods model swap T3                    # Then swap (restarts llama-server)
 ```
 
-Already have a GGUF you want to use? Drop the single `.gguf` file in
-`data/models/`, then open Dashboard -> Models and load the local entry. For
-older installs or headless maintenance, update `GGUF_FILE` and `LLM_MODEL` in
-`.env`, then restart with the CLI:
+已有想使用的 GGUF？将单个 `.gguf` 文件放入
+`data/models/`，然后打开 Dashboard -> Models 并加载本地条目。对于
+较旧安装或无头（headless）维护，在
+`.env` 中更新 `GGUF_FILE` 和 `LLM_MODEL`，然后通过 CLI 重启：
 
 ```bash
 ods restart llm
 ```
 
-Or restart the container directly from the installed `ods` directory:
+或直接从已安装的 `ods` 目录重启容器：
 
 ```bash
 docker compose restart llama-server
 ```
 
-Rollback is automatic — if a new model fails to load, ODS reverts to your previous model.
+回滚是自动的——若新模型加载失败，ODS 会恢复到你之前的模型。
 
 ---
 
-## Extensibility
+## 可扩展性
 
-ODS is designed to be modded. Every service is an extension — a folder with a `manifest.yaml` and a `compose.yaml`. The dashboard, CLI, health checks, and compose stack all discover extensions automatically.
+ODS 专为可改装而设计。每个服务都是一个扩展——包含 `manifest.yaml` 和 `compose.yaml` 的文件夹。Dashboard、CLI、健康检查以及 compose 栈都会自动发现扩展。
 
 ```
 extensions/services/
@@ -371,15 +356,15 @@ ods disable my-service    # Disable it
 ods list                  # See everything
 ```
 
-The installer itself is modular — 19 library modules, a shared service registry, and 13 ordered phases. Want to add a hardware tier, swap a default model, or skip a phase? Start with the installer architecture map so you update the Linux, macOS, Windows, upgrade, and host-agent writers together.
+安装程序本身也是模块化的——19 个库模块、共享服务注册表，以及 13 个有序阶段。想新增硬件层级、更换默认模型或跳过某个阶段？先从安装程序架构图入手，以便同步更新 Linux、macOS、Windows、升级与 host-agent 编写器。
 
-[Full extension guide](ods/docs/EXTENSIONS.md) | [Installer architecture](ods/docs/INSTALLER-ARCHITECTURE.md)
+[完整扩展指南](ods/docs/EXTENSIONS.md) | [安装程序架构](ods/docs/INSTALLER-ARCHITECTURE.md)
 
 ---
 
 ## ods-cli
 
-The `ods` CLI manages your entire stack:
+`ods` CLI 管理你的整个栈：
 
 ```bash
 ods status                # Health checks + GPU status
@@ -403,71 +388,71 @@ ods preset load gaming    # Restore it
 
 ---
 
-## How It Compares
+## 对比
 
-Other tools get you part of the way. ODS gets you the whole way.
+其他工具只能帮你走一部分路。ODS 能带你走完全程。
 
 | | ODS | Ollama + Open WebUI | LocalAI |
 |---|:---:|:---:|:---:|
-| **Scope** | Full AI stack — inference to agents to workflows | LLM + chat | LLM only |
-| One-command install | Everything, auto-configured | LLM + chat only | LLM only |
-| Hardware auto-detect + model selection | NVIDIA + AMD Strix Halo + Apple Silicon + Intel Arc + CPU/cloud fallback | No | No |
-| AMD APU unified memory support | Platform-specific accelerated backend, selected by installer | Partial (Vulkan) | No |
-| Autonomous AI agents | Hermes Agent default; OpenClaw legacy opt-in | No | No |
-| Workflow automation | n8n (400+ integrations) | No | No |
-| Voice (STT + TTS) | Whisper + Kokoro | No | No |
-| Image generation | ComfyUI | No | No |
-| RAG pipeline | Qdrant + embeddings | No | No |
-| Extension system | Manifest-based, hot-pluggable | No | No |
-| Multi-GPU | Yes (NVIDIA) | Partial | Partial |
+| **范围** | 完整 AI 栈——从推理到智能体再到工作流 | LLM + 聊天 | 仅 LLM |
+| 一键安装 | 全部组件，自动配置 | 仅 LLM + 聊天 | 仅 LLM |
+| 硬件自动检测 + 模型选择 | NVIDIA + AMD Strix Halo + Apple Silicon + Intel Arc + CPU/云回退 | 否 | 否 |
+| AMD APU 统一内存支持 | 平台专用加速后端，由安装程序选择 | 部分（Vulkan） | 否 |
+| 自主 AI 智能体 | 默认 Hermes Agent；OpenClaw 遗留可选 | 否 | 否 |
+| 工作流自动化 | n8n（400+ 集成） | 否 | 否 |
+| 语音（STT + TTS） | Whisper + Kokoro | 否 | 否 |
+| 图像生成 | ComfyUI | 否 | 否 |
+| RAG 流水线 | Qdrant + embeddings | 否 | 否 |
+| 扩展系统 | 基于 manifest，支持热插拔 | 否 | 否 |
+| 多 GPU | 是（NVIDIA） | 部分 | 部分 |
 
 ---
 
-## Documentation
+## 文档
 
 | | |
 |---|---|
-| [Quickstart](ods/QUICKSTART.md) | Step-by-step install guide with troubleshooting |
-| [Docs Index](ods/docs/README.md) | Maintained map for operators, contributors, and reviewers |
-| [Build On ODS](ods/docs/BUILD-ON-ODS-SERVER.md) | Forking, custom editions, extension templates, and downstream validation |
-| [Forkability](ods/docs/FORKABILITY.md) | How to fork, audit, customize, and independently operate ODS |
-| [Maintainer Runbook](ods/docs/MAINTAINER_RUNBOOK.md) | Release, rollback, validation, and operator continuity guidance for maintainers and forks |
-| [High-Risk Change Map](ods/docs/HIGH_RISK_CHANGE_MAP.md) | Which changes require focused checks, fleet validation, or release-grade gates |
-| [Headless Setup](ods/docs/HEADLESS-SETUP.md) | QR onboarding, first-boot setup, AP mode, mDNS, and local agent access |
-| [Support Matrix](ods/docs/SUPPORT-MATRIX.md) | Current platform and GPU support status |
-| [Release Validation](ods/docs/RELEASE_VALIDATION.md) | User Green gates and the release-grade fleet/distro validation policy |
-| [Validation Matrix](ods/docs/VALIDATION-MATRIX.md) | Sanitized CI, distro lab, and real-hardware fleet release-readiness evidence |
-| [Validation Reproducibility](ods/docs/VALIDATION_REPRODUCIBILITY.md) | How forks and operators can reproduce the validation story on their own hardware |
-| [Offline And Mirroring](ods/docs/OFFLINE_AND_MIRRORING.md) | Pinning, mirroring, and preserving release artifacts for independent operation |
-| [Installer Trust](ods/docs/INSTALLER_TRUST.md) | Inspect-first install paths, ref pinning, and current provenance limits |
-| [Model Management](ods/docs/MODEL-MANAGEMENT.md) | Dashboard model downloads, switching, and manual GGUF workflows |
-| [Hardware Guide](ods/docs/HARDWARE-GUIDE.md) | What to buy, tier recommendations |
-| [FAQ](ods/FAQ.md) | Common questions and configuration |
-| [Extensions](ods/docs/EXTENSIONS.md) | How to add custom services |
-| [Installer Architecture](ods/docs/INSTALLER-ARCHITECTURE.md) | Modular installer deep dive |
-| [Installer Phase Contracts](ods/docs/INSTALLER_PHASE_CONTRACTS.md) | Phase ownership, idempotency, failure modes, and validation expectations |
-| [Compose Resolver Contracts](ods/docs/COMPOSE_RESOLVER_CONTRACTS.md) | Rules for compose layers, extensions, backends, ports, and mode overlays |
-| [Changelog](ods/CHANGELOG.md) | Version history and release notes |
-| [Contributing](CONTRIBUTING.md) | How to contribute |
+| [快速入门](ods/QUICKSTART.md) | 分步安装指南，含故障排除 |
+| [文档索引](ods/docs/README.md) | 面向运维人员、贡献者与审阅者的维护地图 |
+| [基于 ODS 构建](ods/docs/BUILD-ON-ODS-SERVER.md) | Fork、定制版本、扩展模板与下游验证 |
+| [可 Fork 性](ods/docs/FORKABILITY.md) | 如何 fork、审计、定制并独立运营 ODS |
+| [维护者运行手册](ods/docs/MAINTAINER_RUNBOOK.md) | 面向维护者与 fork 的发布、回滚、验证及运维连续性指南 |
+| [高风险变更地图](ods/docs/HIGH_RISK_CHANGE_MAP.md) | 哪些变更需要重点检查、机群验证或发布级门禁 |
+| [无头设置](ods/docs/HEADLESS-SETUP.md) | QR 引导、首次启动设置、AP 模式、mDNS 及本地智能体访问 |
+| [支持矩阵](ods/docs/SUPPORT-MATRIX.md) | 当前平台与 GPU 支持状态 |
+| [发布验证](ods/docs/RELEASE_VALIDATION.md) | User Green 门禁及发布级机群/发行版验证策略 |
+| [验证矩阵](ods/docs/VALIDATION-MATRIX.md) | 脱敏 CI、发行版实验室与真实硬件机群的发布就绪证据 |
+| [验证可复现性](ods/docs/VALIDATION_REPRODUCIBILITY.md) | fork 与运维人员如何在自己的硬件上复现验证流程 |
+| [离线与镜像](ods/docs/OFFLINE_AND_MIRRORING.md) | 固定版本、镜像并保留发布制品以支持独立运营 |
+| [安装程序信任](ods/docs/INSTALLER_TRUST.md) | 先检查后安装路径、ref 固定及当前来源追溯限制 |
+| [模型管理](ods/docs/MODEL-MANAGEMENT.md) | Dashboard 模型下载、切换及手动 GGUF 工作流 |
+| [硬件指南](ods/docs/HARDWARE-GUIDE.md) | 选购建议与层级推荐 |
+| [常见问题](ods/FAQ.md) | 常见问题与配置 |
+| [扩展](ods/docs/EXTENSIONS.md) | 如何添加自定义服务 |
+| [安装程序架构](ods/docs/INSTALLER-ARCHITECTURE.md) | 模块化安装程序深度解析 |
+| [安装程序阶段契约](ods/docs/INSTALLER_PHASE_CONTRACTS.md) | 阶段归属、幂等性、失败模式与验证预期 |
+| [Compose 解析器契约](ods/docs/COMPOSE_RESOLVER_CONTRACTS.md) | compose 层、扩展、后端、端口与模式叠加规则 |
+| [变更日志](ods/CHANGELOG.md) | 版本历史与发布说明 |
+| [贡献指南](CONTRIBUTING.md) | 如何参与贡献 |
 
 ---
 
-## Contributors And Recognition
+## 贡献者与认可
 
-ODS is built by a growing group of contributors across installers, GPU support, dashboard, security, extensions, docs, and release validation. The README keeps the product overview focused; the long-form credits, upstream acknowledgements, and contributor history live in [CONTRIBUTORS.md](CONTRIBUTORS.md).
+ODS 由不断壮大的贡献者团队在安装程序、GPU 支持、Dashboard、安全、扩展、文档与发布验证等领域共同构建。README 聚焦产品概览；详细致谢、上游鸣谢与贡献者历史见 [CONTRIBUTORS.md](CONTRIBUTORS.md)。
 
-ODS has been recognized by the local AI and developer community, including AMD Featured Developer recognition, selection as a May 2026 AMD Lemonade Developer Challenge winner, and a feature at [(Co)nnect: Philly's AI Ecosystem Summit](https://luma.com/xdwih64h) at Pennovation Works.
+ODS 已获得本地 AI 与开发者社区认可，包括 AMD Featured Developer 认可、入选 2026 年 5 月 AMD Lemonade Developer Challenge 获奖者，并在 [(Co)nnect: Philly's AI Ecosystem Summit](https://luma.com/xdwih64h) at Pennovation Works 上亮相。
 
 ---
 
-## License
+## 许可证
 
-Apache 2.0 — Use it, modify it, ship it. See [LICENSE](LICENSE).
+Apache 2.0 — 随意使用、修改、发布。详见 [LICENSE](LICENSE)。
 
 ---
 
 <div align="center">
 
-*Built by [Light Heart Labs](https://github.com/Light-Heart-Labs) and the growing resistance that refuses to rent what should be owned.*
+*由 [Light Heart Labs](https://github.com/Light-Heart-Labs) 与不断壮大的、拒绝租用本应拥有之物的抵抗力量共同打造。*
 
 </div>