Temperature

Learning Rate

लर्निङ रेट / सिकाइ दर

A setting that controls how big each step is when a model updates its parameters.

Autoregressive

अटोरिग्रेसिभ

Generating output one token at a time, each based on all the tokens produced before it.

Beam Search

बिम सर्च

A decoding method that keeps several candidate sequences to find a high-quality output.

Bias (parameter)

बायस (प्यारामिटर)

An extra learnable value added to a neuron's output to shift it as needed.

Class Imbalance

वर्ग असन्तुलन

When some categories have far more examples than others, biasing a model.

Conditioning

कन्डिसनिङ

Guiding a generative model's output using extra inputs like text, images, or labels.

Cross-Validation

क्रस-भ्यालिडेसन

A technique that splits data into multiple parts to test a model more reliably.

Customer Segmentation

ग्राहक विभाजन

Grouping customers by shared traits to target products and messaging more effectively.