Prediction

Negative Prompt

नेगेटिभ प्रम्प्ट

Text telling an image model what to avoid including in the generated output.

Next Token Prediction

अर्को टोकन अनुमान

The core training task of LLMs: predicting the next piece of text given prior context.

Output Layer

आउटपुट तह

The final layer of a network that produces the prediction or result.

Conditioning

कन्डिसनिङ

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

Confidence Score

विश्वास अंक

A number expressing how certain a model is about a particular prediction.

Dimensionality Reduction

आयाम न्यूनीकरण

Reducing the number of input features while keeping important information.

Encoder-Decoder

इन्कोडर-डिकोडर

An architecture that compresses input into a representation then expands it into output.

Feedforward Network

फिडफरवार्ड नेटवर्क

A neural network where data flows in one direction from input to output.