Glossary entry
Perplexity
पर्प्लेक्सिटी
Definition (English)
A measure of how well a language model predicts text; lower means better prediction.
अर्थ (नेपालीमा)
भाषा मोडेलले पाठ कति राम्ररी अनुमान गर्छ भन्ने नाप; कम भए राम्रो।
Related terms
Other terms related to Perplexity.
-
Language Model
भाषा मोडेल
A model that predicts likely sequences of words to understand or generate text.
-
Corpus
कोर्पस / पाठ सङ्ग्रह
A large, structured collection of text used to train or study language models.
-
Function Calling (Tool Use)
फंक्सन कलिङ / उपकरण प्रयोग
Letting a language model invoke external tools or APIs to act, not just generate text.
-
Large Language Model (LLM)
ठूलो भाषा मोडेल
A very large neural network trained on massive text to understand and generate language.
-
Machine Translation
मेसिन अनुवाद
Automatically translating text or speech from one language to another.
-
Next Token Prediction
अर्को टोकन अनुमान
The core training task of LLMs: predicting the next piece of text given prior context.
-
Prediction
भविष्यवाणी / अनुमान
The output a model produces for a given input, such as a label, number, or generated text.
-
Prompt
प्रम्प्ट
The input text or instruction a user gives to a language model.