架构

Logit

定义

The raw, unnormalised score produced by a model's final layer before the softmax function is applied. Logits are useful for calibration, temperature scaling, and understanding a model's confidence distribution across possible output classes.

相关术语

Softmax

A mathematical function that converts a vector of raw logits into a probability distribution summing to 1. Softmax is applied at the output of classifiers and language models to produce token probabilities used in sampling and decoding.

Temperature (LLM)

A sampling parameter that controls the randomness of an LLM's output. A temperature of 0 produces deterministic, focused responses; higher values introduce creative variability. Selecting the right temperature is part of operationalising LLMs in production workflows.

Cross-Entropy Loss

The most common training objective for classification and language modelling tasks, measuring the difference between predicted probability distributions and true labels. Minimising cross-entropy loss during training drives the model to assign high probability to correct outputs.

了解术语只是第一步，将其落地应用才是第二步。

预约一次探索通话，探讨这些 AI 概念如何转化到您所在的具体行业与业务挑战中。