AddCollectionView ← Existing Collections ← 存在集合 Add Document Collection 添加文档集合 Add a folder containing plain text files, PDFs, or Markdown. Configure additional extensions in Settings. 添加一个包含纯文本文件、PDF或Markdown的文件夹。在“设置”中配置其他扩展。 Name 名称 Collection name... 集合名称... Name of the collection to add (Required) 集合名称 (必须) Folder 目录 Folder path... 目录地址... Folder path to documents (Required) 文档的目录地址（必须） Browse 查看 Create Collection 创建集合 AddGPT4AllModelView These models have been specifically configured for use in GPT4All. The first few models on the list are known to work the best, but you should only attempt to use models that will fit in your available memory. 这些模型已专门为GPT4All配置。列表前几个模型的效果最好，但你最好只使用那些满足内存的模型。 Network error: could not retrieve %1 网络错误：无法检索 %1 Busy indicator 繁忙程度 Displayed when the models request is ongoing 当模型请求处于进行中时显示 All 全选 Reasoning 推理 Model file 模型文件 Model file to be downloaded 待下载的模型 Description 描述 File description 文件描述 Cancel 取消 Resume 继续 Download 下载 Stop/restart/start the download 停止/重启/开始下载 Remove 删除 Remove model from filesystem 从系统中删除模型 Install 安装 Install online model 安装在线模型 <a href="#error">Error</a> <a href="#error">错误</a> Describes an error that occurred when downloading 描述下载时发生的错误 WARNING: Not recommended for your hardware. Model requires more memory (%1 GB) than your system has available (%2). 警告：不推荐用于您的硬件。模型需要的内存（%1 GB）超过了您系统的可用内存（%2） Error for incompatible hardware 硬件不兼容的错误 Download progressBar 下载进度 Shows the progress made in the download 显示下载进度 Download speed 下载速度 Download speed in bytes/kilobytes/megabytes per second 下载速度 b/kb/mb 每秒 Calculating... 计算中... Whether the file hash is being calculated 是否正在计算文件哈希 Displayed when the file hash is being calculated 在计算文件哈希时显示 ERROR: $API_KEY is empty. 错误：$API_KEY为空 enter $API_KEY 输入 $API_KEY ERROR: $BASE_URL is empty. 错误：$BASE_URL 为空 enter $BASE_URL 输入 $BASE_URL ERROR: $MODEL_NAME is empty. 错误：$MODEL_NAME 为空 enter $MODEL_NAME 输入 $MODEL_NAME File size 文件大小 RAM required 需要 RAM %1 GB %1 GB ? ？ Parameters 参数 Quant 量化 Type 类型 AddHFModelView Use the search to find and download models from HuggingFace. There is NO GUARANTEE that these will work. Many will require additional configuration before they can be used. 在 Hugging Face 上查找并下载模型。不能保证这些模型可以正常工作。许多模型在使用前需要额外的配置。 Discover and download models by keyword search... 通过关键词查找并下载模型 ... Text field for discovering and filtering downloadable models 用于发现和筛选可下载模型的文本字段 Searching · %1 搜索中 · %1 Initiate model discovery and filtering 启动模型发现和过滤 Triggers discovery and filtering of models 触发模型发现和过滤 Default 默认 Likes 热门 Downloads 下载量 Recent 最近 Sort by: %1 排序: %1 Asc 升序 Desc 降序 Sort dir: %1 排序目录: %1 None 无 Limit: %1 数量: %1 Model file 模型文件 Model file to be downloaded 待下载的模型 Description 描述 File description 文件描述 Cancel 取消 Resume 继续 Download 下载 Stop/restart/start the download 停止/重启/开始下载 Remove 删除 Remove model from filesystem 从系统中删除模型 Install 安装 Install online model 安装在线模型 <a href="#error">Error</a> <a href="#error">错误</a> Describes an error that occurred when downloading 描述下载时发生的错误 WARNING: Not recommended for your hardware. Model requires more memory (%1 GB) than your system has available (%2). 警告：不推荐用于您的硬件。模型需要的内存（%1 GB）超过了您系统的可用内存（%2） Error for incompatible hardware 硬件不兼容的错误 Download progressBar 下载进度 Shows the progress made in the download 显示下载进度 Download speed 下载速度 Download speed in bytes/kilobytes/megabytes per second 下载速度 b/kb/mb 每秒 Calculating... 计算中... Whether the file hash is being calculated 是否正在计算文件哈希 Busy indicator 繁忙程度 Displayed when the file hash is being calculated 在计算文件哈希时显示 ERROR: $API_KEY is empty. 错误：$API_KEY为空 enter $API_KEY 输入 $API_KEY ERROR: $BASE_URL is empty. 错误：$BASE_URL 为空 enter $BASE_URL 输入 $BASE_URL ERROR: $MODEL_NAME is empty. 错误：$MODEL_NAME 为空 enter $MODEL_NAME 输入 $MODEL_NAME File size 文件大小 Quant 量化 Type 类型 AddModelView ← Existing Models ← 已安装的模型 Explore Models 发现模型 GPT4All GPT4All Remote Providers 远程提供商 HuggingFace HuggingFace AddRemoteModelView Various remote model providers that use network resources for inference. 使用网络资源进行推理的各种远程模型提供商。 Groq Groq Groq offers a high-performance AI inference engine designed for low-latency and efficient processing. Optimized for real-time applications, Groq’s technology is ideal for users who need fast responses from open large language models and other AI workloads. Get your API key: <a href="https://console.groq.com/keys">https://groq.com/</a> Groq 提供高性能 AI 推理引擎，专为低延迟和高效处理而设计。其技术经过优化，适用于实时应用，非常适合需要快速响应的大型开源语言模型和其他 AI 任务的用户。 获取您的 API 密钥：<a href="https://console.groq.com/keys">https://groq.com/</a> OpenAI OpenAI OpenAI provides access to advanced AI models, including GPT-4 supporting a wide range of applications, from conversational AI to content generation and code completion. Get your API key: <a href="https://platform.openai.com/signup">https://openai.com/</a> OpenAI 提供先进的 AI 模型访问权限，包括支持广泛应用的 GPT-4，涵盖对话 AI、内容生成和代码补全等场景。 获取您的 API 密钥：<a href="https://platform.openai.com/signup">https://openai.com/</a> Mistral Mistral Mistral AI specializes in efficient, open-weight language models optimized for various natural language processing tasks. Their models are designed for flexibility and performance, making them a solid option for applications requiring scalable AI solutions. Get your API key: <a href="https://mistral.ai/">https://mistral.ai/</a> Mistral AI 专注于高效的开源语言模型，针对各种自然语言处理任务进行了优化。其模型具备灵活性和高性能，是需要可扩展 AI 解决方案的应用的理想选择。 获取您的 API 密钥：<a href="https://mistral.ai/">https://mistral.ai/</a> Custom 自定义 The custom provider option allows users to connect their own OpenAI-compatible AI models or third-party inference services. This is useful for organizations with proprietary models or those leveraging niche AI providers not listed here. 自定义提供商选项允许用户连接自己的 OpenAI 兼容 AI 模型或第三方推理服务。这对于拥有专有模型的组织，或使用此处未列出的特定 AI 提供商的用户非常有用。 ApplicationSettings Application 应用 Network dialog 网络对话 opt-in to share feedback/conversations 选择加入以共享反馈/对话 Error dialog 错误对话 Application Settings 应用设置 General 通用设置 Theme 主题 The application color scheme. 应用的主题颜色 Dark 深色 Light 亮色 ERROR: Update system could not find the MaintenanceTool used to check for updates! Did you install this application using the online installer? If so, the MaintenanceTool executable should be located one directory above where this application resides on your filesystem. If you can't start it manually, then I'm afraid you'll have to reinstall. 错误：更新系统无法找到用于检查更新的 MaintenanceTool！ 您是否使用在线安装程序安装了此应用程序？如果是的话，MaintenanceTool 可执行文件应该位于文件系统中此应用程序所在目录的上一级目录。 如果无法手动启动它，那么恐怕您需要重新安装。 LegacyDark LegacyDark Font Size 字体大小 The size of text in the application. 应用中的文本大小。 Small 小 Medium 中 Large 大 Language and Locale 语言和本地化 The language and locale you wish to use. 你想使用的语言 System Locale 系统语言 Device 设备 The compute device used for text generation. 设备用于文本生成 Application default 程序默认 Default Model 默认模型 The preferred model for new chats. Also used as the local server fallback. 新聊天的首选模式。也用作本地服务器回退。 Suggestion Mode 建议模式 Generate suggested follow-up questions at the end of responses. 在答复结束时生成建议的后续问题。 When chatting with LocalDocs 本地文档检索 Whenever possible 只要有可能 Never 从不 Download Path 下载目录 Where to store local models and the LocalDocs database. 本地模型和本地文档数据库存储目录 Browse 查看 Choose where to save model files 模型下载目录 Enable Datalake 开启数据湖 Send chats and feedback to the GPT4All Open-Source Datalake. 发送对话和反馈给GPT4All 的开源数据湖。 Advanced 高级 CPU Threads CPU线程 The number of CPU threads used for inference and embedding. 用于推理和嵌入的CPU线程数 Enable System Tray 启用系统托盘 The application will minimize to the system tray when the window is closed. 当窗口关闭时，应用程序将最小化到系统托盘。 Enable Local API Server 开启本地 API 服务 Expose an OpenAI-Compatible server to localhost. WARNING: Results in increased resource usage. 将OpenAI兼容服务器暴露给本地主机。警告：导致资源使用量增加。 API Server Port API 服务端口 The port to use for the local server. Requires restart. 使用本地服务的端口，需要重启 Check For Updates 检查更新 Manually check for an update to GPT4All. 手动检查更新 Updates 更新 Chat New Chat 新对话 Server Chat 服务器对话 ChatAPIWorker ERROR: Network error occurred while connecting to the API server 错误：连接到 API 服务器时发生网络错误 ChatAPIWorker::handleFinished got HTTP Error %1 %2 ChatAPIWorker::handleFinished 收到 HTTP 错误 %1 %2 ChatCollapsibleItem Analysis encountered error 分析时遇到错误 Thinking 思考中 Analyzing 分析中 Thought for %1 %2 思考耗时 %1 %2 second 秒 seconds 秒 Analyzed 分析完成 ChatDrawer Drawer 抽屉 Main navigation drawer 导航＋ New Chat ＋新对话 Create a new chat 新对话 Select the current chat or edit the chat when in edit mode 选择当前的聊天或在编辑模式下编辑聊天 Edit chat name 修改对话名称 Save chat name 保存对话名称 Delete chat 删除对话 Confirm chat deletion 确认删除对话 Cancel chat deletion 取消删除对话 List of chats 对话列表 List of chats in the drawer dialog 对话框中的聊天列表 ChatItemView GPT4All GPT4All You 您 response stopped ... 响应停止... retrieving localdocs: %1 ... 检索本地文档: %1 ... searching localdocs: %1 ... 搜索本地文档: %1 ... processing ... 处理中... generating response ... 正在生成回复… generating questions ... 正在生成问题… generating toolcall ... 正在生成工具调用… Copy 复制 %n Source(s) %n 资源 LocalDocs 本地文档 Edit this message? 编辑这条消息？ All following messages will be permanently erased. 所有后续消息将被永久删除。 Redo this response? 重新生成这条回复？ Cannot edit chat without a loaded model. 未加载模型时无法编辑聊天。 Cannot edit chat while the model is generating. 生成模型时无法编辑聊天。 Edit 编辑 Cannot redo response without a loaded model. 未加载模型时无法重新生成回复。 Cannot redo response while the model is generating. 生成模型时无法重新生成回复。 Redo 重做 Like response 点赞这条回复 Dislike response 点踩这条回复 Suggested follow-ups 建议的后续步骤 ChatLLM Your message was too long and could not be processed (%1 > %2). Please try again with something shorter. 您的消息过长，无法处理（%1 > %2）。请尝试简短内容。 ChatListModel TODAY 今天 THIS WEEK 本周 THIS MONTH 本月 LAST SIX MONTHS 半年内 THIS YEAR 今年内 LAST YEAR 去年 ChatTextItem Copy 复制 Copy Message 复制消息 Disable markdown 禁用 Markdown Enable markdown 禁用 Markdown ChatView <h3>Warning</h3>%1 <h3>警告</h3>%1 Conversation copied to clipboard. 复制对话到剪切板。 Code copied to clipboard. 复制代码到剪切板。 The entire chat will be erased. 全部聊天记录将被清除。 Chat panel 对话面板 Chat panel with options 对话面板选项 Reload the currently loaded model 重载当前模型 Eject the currently loaded model 弹出当前加载的模型 No model installed. 没有安装模型。 Model loading error. 模型加载错误。 Waiting for model... 等待模型... Switching context... 切换上下文... Choose a model... 选择模型... Not found: %1 没找到: %1 The top item is the current model 当前模型的最佳选项 LocalDocs 本地文档 Add documents 添加文档 add collections of documents to the chat 将文档集合添加到聊天中 Load the default model 载入默认模型 Loads the default model which can be changed in settings 加载默认模型，可以在设置中更改 No Model Installed 没有下载模型 GPT4All requires that you install at least one model to get started GPT4All要求您至少安装一个模型才能开始 Install a Model 下载模型 Shows the add model view 查看添加的模型 Conversation with the model 使用此模型对话 prompt / response pairs from the conversation 对话中的提示/响应对 Legacy prompt template needs to be <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">updated</a> in Settings. 旧版提示模板需要在设置中<a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">更新</a>。 No <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">chat template</a> configured. 未配置<a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">对话模板</a>。 The <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">chat template</a> cannot be blank. <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">对话模板</a>不能为空。 Legacy system prompt needs to be <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">updated</a> in Settings. 旧系统提示需要在设置中<a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">更新</a>。 Copy 复制 Erase and reset chat session 清空并重置聊天会话 Copy chat session to clipboard 复制对话到剪切板 Add media 新增媒體 Adds media to the prompt 將媒體加入提示中 Stop generating 停止生成 Stop the current response generation 停止当前响应 Attach 附 Single File 單一文件 Reloads the model 重载模型 <h3>Encountered an error loading model:</h3> "%1" Model loading failures can happen for a variety of reasons, but the most common causes include a bad file format, an incomplete or corrupted download, the wrong file type, not enough system RAM or an incompatible model type. Here are some suggestions for resolving the problem: <ul><li>Ensure the model file has a compatible format and type<li>Check the model file is complete in the download folder<li>You can find the download folder in the settings dialog<li>If you've sideloaded the model ensure the file is not corrupt by checking md5sum<li>Read more about what models are supported in our <a href="https://docs.gpt4all.io/">documentation</a> for the gui<li>Check out our <a href="https://discord.gg/4M2QFmTt2k">discord channel</a> for help <h3>加载模型时遇到错误：</h3> <%1> 模型加载失败可能由多种原因引起，但最常见的原因包括文件格式错误、下载不完整或损坏、文件类型错误、系统 RAM 不足或模型类型不兼容。以下是一些解决问题的建议： <ul><li>确保模型文件具有兼容的格式和类型<li>检查下载文件夹中的模型文件是否完整<li>您可以在设置对话框中找到下载文件夹<li>如果您已侧载模型，请通过检查 md5sum 确保文件未损坏<li>在我们的 <a href="https://docs.gpt4all.io/">文档</a> 中了解有关 gui 支持哪些模型的更多信息<li>查看我们的 <a href="https://discord.gg/4M2QFmTt2k">discord 频道</a> 以获取帮助 Erase conversation? 清空对话？ Changing the model will erase the current conversation. 更换模型将清除当前对话。 Reload · %1 重载 · %1 Loading · %1 载入中 · %1 Load · %1 (default) → 载入 · %1 (默认) → Send a message... 发送消息... Load a model to continue... 选择模型并继续... Send messages/prompts to the model 发送消息/提示词给模型 Cut 剪切 Paste 粘贴 Select All 全选 Send message 发送消息 Sends the message/prompt contained in textfield to the model 将文本框中包含的消息/提示发送给模型 CodeInterpreter Code Interpreter 代码解释器 compute javascript code using console.log as output 使用 console.log 计算 JavaScript 代码并输出结果 CollectionsDrawer Warning: searching collections while indexing can return incomplete results 提示: 索引时搜索集合可能会返回不完整的结果 %n file(s) %n word(s) Updating 更新中＋ Add Docs ＋添加文档 Select a collection to make it available to the chat model. 选择一个集合，使其可用于聊天模型。 ConfirmationDialog OK 好 Cancel 取消 Download Model "%1" is installed successfully. 模型 "%1" 安装成功 ERROR: $MODEL_NAME is empty. 错误：$MODEL_NAME 为空 ERROR: $API_KEY is empty. 错误：$API_KEY为空 ERROR: $BASE_URL is invalid. 错误：$BASE_URL 非法 ERROR: Model "%1 (%2)" is conflict. 错误: 模型 "%1 (%2)" 有冲突. Model "%1 (%2)" is installed successfully. 模型 "%1 (%2)" 安装成功. Model "%1" is removed. 模型 "%1" 已删除. HomeView Welcome to GPT4All 欢迎 The privacy-first LLM chat application 隐私至上的大模型咨询应用程序 Start chatting 开始聊天 Start Chatting 开始聊天 Chat with any LLM 大语言模型聊天 LocalDocs 本地文档 Chat with your local files 本地文件聊天 Find Models 查找模型 Explore and download models 发现并下载模型 Latest news 新闻 Latest news from GPT4All GPT4All新闻 Release Notes 发布日志 Documentation 文档 Discord Discord X (Twitter) X (Twitter) Github Github nomic.ai nomic.ai Subscribe to Newsletter 订阅信息 LocalDocsSettings LocalDocs 本地文档 LocalDocs Settings 本地文档设置 Indexing 索引中 Allowed File Extensions 添加文档扩展名 Comma-separated list. LocalDocs will only attempt to process files with these extensions. 逗号分隔的列表。LocalDocs 只会尝试处理具有这些扩展名的文件 Embedding Embedding Use Nomic Embed API 使用 Nomic 内部 API Embed documents using the fast Nomic API instead of a private local model. Requires restart. 使用快速的 Nomic API 嵌入文档，而不是使用私有本地模型 Nomic API Key Nomic API Key API key to use for Nomic Embed. Get one from the Atlas <a href="https://atlas.nomic.ai/cli-login">API keys page</a>. Requires restart. Nomic Embed 使用的 API 密钥。请访问官网获取，需要重启。 Embeddings Device Embeddings 设备 The compute device used for embeddings. Requires restart. 技术设备用于embeddings. 需要重启. Application default 程序默认 Display 显示 Show Sources 查看源码 Display the sources used for each response. 显示每个响应所使用的源。 Advanced 高级 Warning: Advanced usage only. 提示: 仅限高级使用。 Values too large may cause localdocs failure, extremely slow responses or failure to respond at all. Roughly speaking, the {N chars x N snippets} are added to the model's context window. More info <a href="https://docs.gpt4all.io/gpt4all_desktop/localdocs.html">here</a>. 值过大可能会导致 localdocs 失败、响应速度极慢或根本无法响应。粗略地说，{N 个字符 x N 个片段} 被添加到模型的上下文窗口中。更多信息请见<a href="https://docs.gpt4all.io/gpt4all_desktop/localdocs.html">此处</a>。 Document snippet size (characters) 文档粘贴大小 (字符) Number of characters per document snippet. Larger numbers increase likelihood of factual responses, but also result in slower generation. 每个文档片段的字符数。较大的数值增加了事实性响应的可能性，但也会导致生成速度变慢。 Max document snippets per prompt 每个提示的最大文档片段数 Max best N matches of retrieved document snippets to add to the context for prompt. Larger numbers increase likelihood of factual responses, but also result in slower generation. 检索到的文档片段最多添加到提示上下文中的前 N 个最佳匹配项。较大的数值增加了事实性响应的可能性，但也会导致生成速度变慢。 LocalDocsView LocalDocs 本地文档 Chat with your local files 和本地文件对话＋ Add Collection ＋添加集合 <h3>错误：无法访问 LocalDocs 数据库或该数据库无效。</h3> 注意：尝试以下任何建议的修复方法后，您将需要重新启动。 <ul><li>确保设置为下载路径的文件夹存在于文件系统中。</li><li>检查下载路径的所有权以及读写权限。</li><li>如果有localdocs_v2.db文件，请检查其所有权和读/写权限。</li></ul> 如果问题仍然存在，并且存在任何“localdocs_v*.db”文件，作为最后的手段，您可以 尝试备份并删除它们。但是，您必须重新创建您的收藏。 <h3>ERROR: The LocalDocs database cannot be accessed or is not valid.</h3> Note: You will need to restart after trying any of the following suggested fixes. <ul><li>Make sure that the folder set as Download Path exists on the file system.</li><li>Check ownership as well as read and write permissions of the Download Path.</li><li>If there is a localdocs_v2.db file, check its ownership and read/write permissions, too.</li></ul> If the problem persists and there are any 'localdocs_v*.db' files present, as a last resort you can try backing them up and removing them. You will have to recreate your collections, however. <h3>错误：无法访问 LocalDocs 数据库或该数据库无效。</h3> 注意：尝试以下任何建议的修复方法后，您将需要重新启动。 <ul><li>确保设置为下载路径的文件夹存在于文件系统中。</li><li>检查下载路径的所有权以及读写权限。</li><li>如果有localdocs_v2.db文件，请检查其所有权和读/写权限。</li></ul> 如果问题仍然存在，并且存在任何“localdocs_v*.db”文件，作为最后的手段，您可以 尝试备份并删除它们。但是，您必须重新创建您的收藏。 No Collections Installed 没有集合 Install a collection of local documents to get started using this feature 安装一组本地文档以开始使用此功能＋ Add Doc Collection ＋添加文档集合 Shows the add model view 查看添加的模型 Indexing progressBar 索引进度 Shows the progress made in the indexing 显示索引进度 ERROR 错误 INDEXING 索引 EMBEDDING EMBEDDING REQUIRES UPDATE 需更新 READY 准备 INSTALLING 安装中 Indexing in progress 构建索引中 Embedding in progress Embedding进度 This collection requires an update after version change 此集合需要在版本更改后进行更新 Automatically reindexes upon changes to the folder 在文件夹变动时自动重新索引 Installation in progress 安装进度 % % %n file(s) %n 文件 %n word(s) %n 词 Remove 删除 Rebuild 重新构建 Reindex this folder from scratch. This is slow and usually not needed. 从头开始重新索引此文件夹。这个过程较慢，通常情况下不需要。 Update 更新 Update the collection to the new version. This is a slow operation. 将集合更新为新版本。这是一个缓慢的操作。 ModelList cannot open "%1": %2 无法打开“%1”：%2 cannot create "%1": %2 无法创建“%1”：%2 %1 (%2) %1 (%2) OpenAI-Compatible API Model <ul><li>API Key: %1</li><li>Base URL: %2</li><li>Model Name: %3</li></ul> 与 OpenAI 兼容的 API 模型 <ul><li>API 密钥：%1</li><li>基本 URL：%2</li><li>模型名称：%3</li></ul> <ul><li>Requires personal OpenAI API key.</li><li>WARNING: Will send your chats to OpenAI!</li><li>Your API key will be stored on disk</li><li>Will only be used to communicate with OpenAI</li><li>You can apply for an API key <a href="https://platform.openai.com/account/api-keys">here.</a></li> <ul><li>需要个人 OpenAI API 密钥。</li><li>警告：将把您的聊天内容发送给 OpenAI！</li><li>您的 API 密钥将存储在磁盘上</li><li>仅用于与 OpenAI 通信</li><li>您可以在此处<a href="https://platform.openai.com/account/api-keys">申请 API 密钥。</a></li> OpenAI's ChatGPT model GPT-3.5 Turbo %1 OpenAI's ChatGPT model GPT-3.5 Turbo %1 OpenAI's ChatGPT model GPT-4 %1 %2 OpenAI's ChatGPT model GPT-4 %1 %2 Mistral Tiny model %1 Mistral Tiny model %1 Mistral Small model %1 Mistral Small model %1 Mistral Medium model %1 Mistral Medium model %1 <ul><li>Requires personal API key and the API base URL.</li><li>WARNING: Will send your chats to the OpenAI-compatible API Server you specified!</li><li>Your API key will be stored on disk</li><li>Will only be used to communicate with the OpenAI-compatible API Server</li> <ul><li>需要个人 API 密钥和 API 基本 URL。</li><li>警告：将把您的聊天内容发送到您指定的与 OpenAI 兼容的 API 服务器！</li><li>您的 API 密钥将存储在磁盘上</li><li>仅用于与与 OpenAI 兼容的 API 服务器通信</li> Connect to OpenAI-compatible API server %1 连接到与 OpenAI 兼容的 API 服务器 %1 * Even if you pay OpenAI for ChatGPT-4 this does not guarantee API key access. Contact OpenAI for more info. * 即使您为ChatGPT-4向OpenAI付款，这也不能保证API密钥访问。联系OpenAI获取更多信息。 <ul><li>Requires personal Mistral API key.</li><li>WARNING: Will send your chats to Mistral!</li><li>Your API key will be stored on disk</li><li>Will only be used to communicate with Mistral</li><li>You can apply for an API key <a href="https://console.mistral.ai/user/api-keys">here</a>.</li> <ul><li>Requires personal Mistral API key.</li><li>WARNING: Will send your chats to Mistral!</li><li>Your API key will be stored on disk</li><li>Will only be used to communicate with Mistral</li><li>You can apply for an API key <a href="https://console.mistral.ai/user/api-keys">here</a>.</li> Created by %1. <ul><li>Published on %2.<li>This model has %3 likes.<li>This model has %4 downloads.<li>More info can be found <a href="https://huggingface.co/%5">here.</a></ul> Created by %1. <ul><li>Published on %2.<li>This model has %3 likes.<li>This model has %4 downloads.<li>More info can be found <a href="https://huggingface.co/%5">here.</a></ul> ModelSettings Model 模型 %1 system message? %1系统消息？ Clear 清除 Reset 重置 The system message will be %1. 系统消息将被%1。 removed 删除 reset to the default 重置为初始状态 %1 chat template? %1 对话模板？ The chat template will be %1. 对话模板将被%1。 erased 清除 Model Settings 模型设置 Clone 克隆 Remove 删除 Name 名称 Model File 模型文件 System Message 系统消息 A message to set the context or guide the behavior of the model. Leave blank for none. NOTE: Since GPT4All 3.5, this should not contain control tokens. 用于设定上下文或引导模型行为的消息。若无则留空。注意：自GPT4All 3.5版本开始，此信息中不应包含控制符。 System message is not <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">plain text</a>. 系统消息不是<a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">纯文本</a>. Chat Template 对话模板 This Jinja template turns the chat into input for the model. 该Jinja模板会将聊天内容转换为模型的输入。 No <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">chat template</a> configured. 未配置<a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">对话模板</a>。 The <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">chat template</a> cannot be blank. <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">对话模板</a>不能为空。 <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">Syntax error</a>: %1 <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">语法错误</a>: %1 Chat template is not in <a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">Jinja format</a>. 对话模板不是<a href="https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html">Jinja格式</a>. Chat Name Prompt 聊天名称提示 Prompt used to automatically generate chat names. 用于自动生成聊天名称的提示。 Suggested FollowUp Prompt 建议的后续提示 Prompt used to generate suggested follow-up questions. 用于生成建议的后续问题的提示。 Context Length 上下文长度 Number of input and output tokens the model sees. 模型看到的输入和输出令牌的数量。 Maximum combined prompt/response tokens before information is lost. Using more context than the model was trained on will yield poor results. NOTE: Does not take effect until you reload the model. 信息丢失前的最大组合提示/响应令牌。使用比模型训练时更多的上下文将产生较差的结果。注意：在重新加载模型之前不会生效。 Temperature 温度 Randomness of model output. Higher -> more variation. 模型输出的随机性。更高->更多的变化。 Temperature increases the chances of choosing less likely tokens. NOTE: Higher temperature gives more creative but less predictable outputs. 温度增加了选择不太可能的token的机会。注：温度越高，输出越有创意，但预测性越低。 Top-P Top-P Nucleus Sampling factor. Lower -> more predictable. 核子取样系数。较低->更具可预测性。 Only the most likely tokens up to a total probability of top_p can be chosen. NOTE: Prevents choosing highly unlikely tokens. 只能选择总概率高达top_p的最有可能的令牌。注意：防止选择极不可能的token。 Min-P Min-P Minimum token probability. Higher -> more predictable. 最小令牌概率。更高 -> 更可预测。 Sets the minimum relative probability for a token to be considered. 设置被考虑的标记的最小相对概率。 Top-K Top-K Size of selection pool for tokens. 令牌选择池的大小。 Only the top K most likely tokens will be chosen from. 仅从最可能的前 K 个标记中选择 Max Length 最大长度 Maximum response length, in tokens. 最大响应长度（以令牌为单位） Prompt Batch Size 提示词大小 The batch size used for prompt processing. 用于快速处理的批量大小。 Amount of prompt tokens to process at once. NOTE: Higher values can speed up reading prompts but will use more RAM. 一次要处理的提示令牌数量。注意：较高的值可以加快读取提示，但会使用更多的RAM。 Repeat Penalty 重复惩罚 Repetition penalty factor. Set to 1 to disable. 重复处罚系数。设置为1可禁用。 Repeat Penalty Tokens 重复惩罚数 Number of previous tokens used for penalty. 用于惩罚的先前令牌数量。 GPU Layers GPU 层 Number of model layers to load into VRAM. 要加载到VRAM中的模型层数。 How many model layers to load into VRAM. Decrease this if GPT4All runs out of VRAM while loading this model. Lower values increase CPU load and RAM usage, and make inference slower. NOTE: Does not take effect until you reload the model. 将多少模型层加载到VRAM中。如果GPT4All在加载此模型时耗尽VRAM，请减少此值。较低的值会增加CPU负载和RAM使用率，并使推理速度变慢。注意：在重新加载模型之前不会生效。 ModelsView No Models Installed 无模型 Install a model to get started using GPT4All 安装模型并开始使用＋ Add Model ＋添加模型 Shows the add model view 查看增加到模型 Installed Models 已安装的模型 Locally installed chat models 本地安装的聊天 Model file 模型文件 Model file to be downloaded 待下载的模型 Description 描述 File description 文件描述 Cancel 取消 Resume 继续 Stop/restart/start the download 停止/重启/开始下载 Remove 删除 Remove model from filesystem 从系统中删除模型 Install 安装 Install online model 安装在线模型 <a href="#error">Error</a> <a href="#error">错误</a> WARNING: Not recommended for your hardware. Model requires more memory (%1 GB) than your system has available (%2). 警告：不推荐用于您的硬件。模型需要的内存（%1 GB）超过了您系统的可用内存（%2） ERROR: $API_KEY is empty. 错误：$API_KEY 为空 ERROR: $BASE_URL is empty. 错误：$BASE_URL 为空 enter $BASE_URL 输入 $BASE_URL ERROR: $MODEL_NAME is empty. 错误：$MODEL_NAME为空 enter $MODEL_NAME 输入：$MODEL_NAME %1 GB %1 GB ? ？ Describes an error that occurred when downloading 描述下载时发生的错误 Error for incompatible hardware 硬件不兼容的错误 Download progressBar 下载进度 Shows the progress made in the download 显示下载进度 Download speed 下载速度 Download speed in bytes/kilobytes/megabytes per second 下载速度 b/kb/mb /s Calculating... 计算中... Whether the file hash is being calculated 是否正在计算文件哈希 Busy indicator 繁忙程度 Displayed when the file hash is being calculated 在计算文件哈希时显示 enter $API_KEY 输入 $API_KEY File size 文件大小 RAM required 需要 RAM Parameters 参数 Quant 量化 Type 类型 MyFancyLink Fancy link 精选链接 A stylized link 样式化链接 MyFileDialog Please choose a file 請選擇一個文件 MyFolderDialog Please choose a directory 請選擇目錄 MySettingsLabel Clear 清除 Reset 重置 MySettingsTab Restore defaults? 恢复初始化？ This page of settings will be reset to the defaults. 该页面的设置项将重置为默认值。 Restore Defaults 恢复初始化 Restores settings dialog to a default state 将设置对话框恢复为默认状态 NetworkDialog Contribute data to the GPT4All Opensource Datalake. 向GPT4All开源数据湖贡献数据 By enabling this feature, you will be able to participate in the democratic process of training a large language model by contributing data for future model improvements. When a GPT4All model responds to you and you have opted-in, your conversation will be sent to the GPT4All Open Source Datalake. Additionally, you can like/dislike its response. If you dislike a response, you can suggest an alternative response. This data will be collected and aggregated in the GPT4All Datalake. NOTE: By turning on this feature, you will be sending your data to the GPT4All Open Source Datalake. You should have no expectation of chat privacy when this feature is enabled. You should; however, have an expectation of an optional attribution if you wish. Your chat data will be openly available for anyone to download and will be used by Nomic AI to improve future GPT4All models. Nomic AI will retain all attribution information attached to your data and you will be credited as a contributor to any GPT4All model release that uses your data! 通过启用此功能，您将能够通过为未来的模型改进贡献数据来参与训练大型语言模型的民主过程。当 GPT4All 模型回复您并且您已选择加入时，您的对话将被发送到 GPT4All 开源数据湖。此外，您可以喜欢/不喜欢它的回复。如果您不喜欢某个回复，您可以建议其他回复。这些数据将在 GPT4All 数据湖中收集和汇总。注意：通过启用此功能，您将把数据发送到 GPT4All 开源数据湖。启用此功能后，您不应该期望聊天隐私。但是，如果您愿意，您应该期望可选的归因。您的聊天数据将公开供任何人下载，并将被 Nomic AI 用于改进未来的 GPT4All 模型。Nomic AI 将保留与您的数据相关的所有归因信息，并且您将被视为使用您的数据的任何 GPT4All 模型发布的贡献者！ Terms for opt-in 选择加入的条款 Describes what will happen when you opt-in 描述选择加入时会发生的情况 Please provide a name for attribution (optional) 填写名称属性 (可选) Attribution (optional) 属性 (可选) Provide attribution 提供属性 Enable 启用 Enable opt-in 启用选择加入 Cancel 取消 Cancel opt-in 取消加入 NewVersionDialog New version is available 新版本可选 Update 更新 Update to new version 更新到新版本 PopupDialog Reveals a shortlived help balloon 显示一个短暂的帮助气球 Busy indicator 繁忙程度 Displayed when the popup is showing busy 在弹出窗口显示忙碌时显示 RemoteModelCard API Key API 密钥 ERROR: $API_KEY is empty. 错误：$API_KEY 为空 enter $API_KEY 输入 $API_KEY Whether the file hash is being calculated 是否正在计算文件哈希 Base Url 基础 URL ERROR: $BASE_URL is empty. 错误：$BASE_URL 为空 enter $BASE_URL 输入 $BASE_URL Model Name 模型名称 ERROR: $MODEL_NAME is empty. 错误：$MODEL_NAME为空 enter $MODEL_NAME 输入：$MODEL_NAME Models 模型 Install 安装 Install remote model 安装远程模型 SettingsView Settings 设置 Contains various application settings 包含各种应用程序设置 Application 应用 Model 模型 LocalDocs 本地文档 StartupDialog Welcome! 欢迎！ ### Release Notes %1 ### Contributors %2 ### 发布日志 %1 ### 贡献者 %2 Release notes 发布日志 Release notes for this version 本版本发布日志 ### Opt-ins for anonymous usage analytics and datalake By enabling these features, you will be able to participate in the democratic process of training a large language model by contributing data for future model improvements. When a GPT4All model responds to you and you have opted-in, your conversation will be sent to the GPT4All Open Source Datalake. Additionally, you can like/dislike its response. If you dislike a response, you can suggest an alternative response. This data will be collected and aggregated in the GPT4All Datalake. NOTE: By turning on this feature, you will be sending your data to the GPT4All Open Source Datalake. You should have no expectation of chat privacy when this feature is enabled. You should; however, have an expectation of an optional attribution if you wish. Your chat data will be openly available for anyone to download and will be used by Nomic AI to improve future GPT4All models. Nomic AI will retain all attribution information attached to your data and you will be credited as a contributor to any GPT4All model release that uses your data! ### 选择加入匿名使用分析和数据湖通过启用这些功能，您将能够通过为未来的模型改进贡献数据来参与训练大型语言模型的民主过程。当 GPT4All 模型回复您并且您已选择加入时，您的对话将被发送到 GPT4All 开源数据湖。此外，您可以喜欢/不喜欢它的回复。如果您不喜欢某个回复，您可以建议其他回复。这些数据将在 GPT4All 数据湖中收集和汇总。注意：通过启用此功能，您将把您的数据发送到 GPT4All 开源数据湖。启用此功能后，您不应该期望聊天隐私。但是，如果您愿意，您应该期望可选的归因。您的聊天数据将公开供任何人下载，并将由 Nomic AI 用于改进未来的 GPT4All 模型。 Nomic AI 将保留与您的数据相关的所有归因信息，并且您将被视为使用您的数据的任何 GPT4All 模型发布的贡献者！ Terms for opt-in 选择加入选项 Describes what will happen when you opt-in 描述选择加入时会发生的情况 Opt-in to anonymous usage analytics used to improve GPT4All 选择加入匿名使用分析，以帮助改进GPT4All Opt-in for anonymous usage statistics 允许选择加入匿名使用统计数据 Yes 是 Allow opt-in for anonymous usage statistics 允许选择加入匿名使用统计数据 No 否 Opt-out for anonymous usage statistics 退出匿名使用统计数据 Allow opt-out for anonymous usage statistics 允许选择退出匿名使用统计数据 Opt-in to anonymous sharing of chats to the GPT4All Datalake 选择匿名共享聊天记录到GPT4All数据池 Opt-in for network 选择加入网络 Allow opt-in for network 允许选择加入网络 Allow opt-in anonymous sharing of chats to the GPT4All Datalake 允许选择加入匿名共享聊天至 GPT4All 数据湖 Opt-out for network 选择退出网络 Allow opt-out anonymous sharing of chats to the GPT4All Datalake 允许选择退出将聊天匿名共享至 GPT4All 数据池 ThumbsDownDialog Please edit the text below to provide a better response. (optional) 请编辑下方文本以提供更好的回复。（可选） Please provide a better response... 提供更好回答... Submit 提交 Submits the user's response 提交用户响应 Cancel 取消 Closes the response dialog 关闭的对话 main GPT4All v%1 GPT4All v%1 Restore 恢复 Quit 退出 <h3>Encountered an error starting up:</h3> "Incompatible hardware detected." Unfortunately, your CPU does not meet the minimal requirements to run this program. In particular, it does not support AVX intrinsics which this program requires to successfully run a modern large language model. The only solution at this time is to upgrade your hardware to a more modern CPU. See here for more information: <a href="https://en.wikipedia.org/wiki/Advanced_Vector_Extensions">https://en.wikipedia.org/wiki/Advanced_Vector_Extensions</a> <h3>启动时遇到错误：</h3> “检测到不兼容的硬件。” 很遗憾，您的 CPU 不满足运行此程序的最低要求。特别是，它不支持此程序成功运行现代大型语言模型所需的 AVX 内在函数。目前唯一的解决方案是将您的硬件升级到更现代的 CPU。 有关更多信息，请参阅此处：<a href="https://en.wikipedia.org/wiki/Advanced_Vector_Extensions>>https://en.wikipedia.org/wiki/Advanced_Vector_Extensions</a> <h3>Encountered an error starting up:</h3> "Inability to access settings file." Unfortunately, something is preventing the program from accessing the settings file. This could be caused by incorrect permissions in the local app config directory where the settings file is located. Check out our <a href="https://discord.gg/4M2QFmTt2k">discord channel</a> for help. <h3>启动时遇到错误：</h3> “无法访问设置文件。” 不幸的是，某些东西阻止程序访问设置文件。这可能是由于设置文件所在的本地应用程序配置目录中的权限不正确造成的。请查看我们的<a href="https://discord.gg/4M2QFmTt2k">discord 频道</a> 以获取帮助。 Connection to datalake failed. 链接数据湖失败 Saving chats. 保存对话 Network dialog 网络对话 opt-in to share feedback/conversations 选择加入以共享反馈/对话 Home view 主页 Home view of application 主页 Home 主页 Chat view 对话视图 Chat view to interact with models 聊天视图可与模型互动 Chats 对话 Models 模型 Models view for installed models 已安装模型的页面 LocalDocs 本地文档 LocalDocs view to configure and use local docs LocalDocs视图可配置和使用本地文档 Settings 设置 Settings view for application configuration 设置页面 The datalake is enabled 数据湖已开启 Using a network model 使用联网模型 Server mode is enabled 服务器模式已开 Installed models 安装模型 View of installed models 查看已安装模型