MOXUY

Mar 24, 2023

英语学习之文档翻译(2)

https://platform.openai.com/docs/introduction/overview/

Original:
Overview
The OpenAI API can be applied to virtually any task that involves understanding or generating natural language, code, or images. We offer a spectrum of models with different levels of power suitable for different tasks, as well as the ability to fine-tune your own custom models. These models can be used for everything from content generation to semantic search and classification.
ME:
概述
OpenAI API几乎可以应用到所有任务中,包括理解和生成自然语言,代码或者图像。我们为不同任务提供适当的模型,也能够调整为你的自定义模型。这些模型可以被用作搜索和归类任何生成文本。

GPT:
概述
OpenAI API可以应用于几乎涉及自然语言理解或生成、代码或图像的任务。我们提供一系列不同功率水平的模型,适用于不同的任务,以及微调自定义模型的能力。这些模型可用于从内容生成到语义搜索和分类等各种任务。

Original:
Key concepts
We recommend completing our quickstart tutorial to get acquainted with key concepts through a hands-on, interactive example.
ME:
关键概念
我们推荐手动完成我们的快速入门练习去了解关键概念,互动实例。

GPT:
关键概念
我们建议您完成快速入门教程,通过实践互动示例来熟悉关键概念。

Original:
Prompts
Designing your prompt is essentially how you “program” the model, usually by providing some instructions or a few examples. This is different from most other NLP services which are designed for a single task, such as sentiment classification or named entity recognition. Instead, the completions and chat completions endpoint can be used for virtually any task including content or code generation, summarization, expansion, conversation, creative writing, style transfer, and more.
ME:
提示词
设计你的提示词实际上就是编程模型,通常提供一些指令或者示例。这不同于大多数NLP科学为了单个任务设计,像是分类观点或识别实体。相反,完成和聊天完成端点可以被用作几乎包括文本、代码生成、总结、延展、创造性写作、风格转换等的任何任务。

GPT:
提示
设计提示方式基本上就是“编程”该模型,通常是通过提供一些说明或几个示例来完成的。这与大多数其他针对单一任务设计的NLP服务(例如情感分类或命名实体识别)不同。相反,完成和聊天完成终端点可用于几乎包括内容或代码生成、摘要、扩展、对话、创意写作、样式转移等任何任务。

Original:
Tokens
Our models understand and process text by breaking it down into tokens. Tokens can be words or just chunks of characters. For example, the word “hamburger” gets broken up into the tokens “ham”, “bur” and “ger”, while a short and common word like “pear” is a single token. Many tokens start with a whitespace, for example “ hello” and “ bye”.
ME:
Tokens
我们的模型通过将文本分解为tokens来理解和处理。tokens可以是单词或者字符快。举个例子,“hamburger”这个词分解为 “ham”, “bur” and “ger” 这几个tokens,一个短的指令词像是”pear“是单个token。大多数tokens开始于空格,比如“ hello”和“ bye”。

GPT:
标记
我们的模型通过将文本分解为标记来理解和处理文本。标记可以是单词或字符块。例如,“汉堡包”这个词被分成标记“汉”、“堡”和“包”,而一个短且常用的词如“梨”则是一个标记。许多标记以空格开头,例如“hello”和“bye”。

Original:
The number of tokens processed in a given API request depends on the length of both your inputs and outputs. As a rough rule of thumb, 1 token is approximately 4 characters or 0.75 words for English text. One limitation to keep in mind is that your text prompt and generated completion combined must be no more than the model’s maximum context length (for most models this is 2048 tokens, or about 1500 words). Check out our tokenizer tool to learn more about how text translates to tokens.
ME:
一个API请求消耗的token数量取决于你输入和输出的长度。一般来说,一个token大约是4个字符或者0.75个英文单词。对于记住你的提示词的限制和生成组合词最多不能超过模型的最大文本长度(对于大多数模型这个限制是2048个tokens,或者大约1500个单词)。看看我们的分词器工具去了解怎么将文本转换为tokens。

GPT:
在给定的API请求中处理的标记数取决于您输入和输出的长度。作为一个粗略的经验法则,一个标记在英文文本中大约是4个字符或0.75个单词。请记住一个限制,即您的文本提示和生成的完成组合必须不超过模型的最大上下文长度(对于大多数模型,这是2048个标记,或约1500个单词)。查看我们的标记工具以了解文本如何转换为标记。

Original:
Models
The API is powered by a set of models with different capabilities and price points. GPT-4 is our latest and most powerful model. GPT-3.5-Turbo is the model that powers ChatGPT and is optimized for conversational formats. To learn more about these models and what else we offer, visit our models documentation.
ME:
模型
这个API靠一个模型集驱动,拥有不同的能力和价格。GPT-4是我们最新且最强的模型。GPT-3.5-Turbo是ChatGPT能力的模型,经过优化以适配对话.要了解更多关于这些我们提供的模型,可以访问我们的模型文档。

GPT:
模型
API由一组具有不同功能和价格点的模型提供支持。 GPT-4是我们最新且最强大的模型。 GPT-3.5-Turbo是为聊天GPT提供动力的模型,经过优化以适应对话格式。要了解有关这些模型及其他内容的详细信息,请访问我们的模型文档。

tags: 英语 翻译
OLDER > < NEWER