跳到主要内容
Learn Motion
探索课程产品能力价格

下载 Learn Motion

用手机扫描二维码,下载 App。

App Store

扫码从 App Store 下载 Learn Motion打开商店页面

Google Play

扫码从 Google Play 下载 Learn Motion打开商店页面
登录
Learn Motion

How ChatGPT Writes One Token at a Time

1From Your Words to Tokens2Predicting the Next Token3Choosing a Token and Looping4Why the Answer Reads as Coherent Text
Choosing a Token and Looping

Reshaping the Odds

2 / 4
That appended token changes the input, but before the next pick, the distribution itself can be reshaped. Temperature does this by rescaling the scores before they become probabilities.
0:00 / 0:00

Before selection, the distribution can be reshaped. Temperature rescales the logits before softmax: a low temperature sharpens the distribution so the top candidate dominates, while a high temperature flattens it so many tokens become nearly equally likely. Top-k filtering keeps only the k highest-probability tokens and discards the rest. Top-p filtering keeps the smallest set of tokens whose cumulative probability reaches p, cutting off the long tail. Both filters restrict which tokens are eligible before the actual selection step.

上一页2 / 4下一页

Learn Motion

生成课程,认真学会。

运营方:Wuhan Daoyin Technology Co., Ltd.

联系我们: [email protected]
隐私政策用户服务协议

© 2026 Learn Motion