GPT

Next Token Prediction

अर्को टोकन अनुमान

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

BERT

बर्ट (BERT)

An influential transformer model that reads text in both directions to understand context.

Conditioning

कन्डिसनिङ

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

Corpus

कोर्पस / पाठ सङ्ग्रह

A large, structured collection of text used to train or study language models.

Ensemble Learning

समूह सिकाइ

Combining multiple models to produce a stronger overall prediction.

Generative Adversarial Network (GAN)

जेनेरेटिभ एडभर्सरियल नेटवर्क

Two networks competing — one generates fake data, the other judges it — to produce realistic outputs.

Generative AI

जेनेरेटिभ एआई / सिर्जनात्मक एआई

AI that creates new content such as text, images, audio, or code.

Subword

उप-शब्द

A fragment of a word used as a token so models can handle rare or new words.