这是一个创建于 815 天前的主题，其中的信息可能已经有所发展或是发生改变。
下图是设置 API 参数值的界面，左边是暂时翻译，中间是值，右边调整。参数的官方原文在这里，求更容易理解的说法。
model / 模型和最大代币数：
这个参数就是 OpenAI 的模型，不过中间数值是该模型的最大 Token 。
temperature / 创造性：
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
top-p / 准确性：
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
max-tokens-completion / 单次回复可以消耗的最大代币数：
The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. Example Python code for counting tokens.
presence-penalty / 话题分散性：
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
frequency-penalty / 强调观点：
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
 | 1 airyland 2023-07-18 21:06:53 +08:00  1 一般会把 temperature 译为思维发散性。 |
 | 2 shinyzhu 2023-07-19 08:03:11 +08:00 能调 API 的都直接给原文。 |
 | 3 lovestudykid 2023-07-19 11:33:34 +08:00 直译最好 |
 | 4 fakeJas0n 2023-07-19 13:39:10 +08:00 |
Select Language