Data Science Lecture 5

What does LLMs stand for and what do they do?

Large Language Models are neutral networks trained to predict and generate text.

How do they learn patterns?

They learn form vast amounts of text data, books, articals, websites.

How are LLMS different from other traditional text mining methods?

Traditional text miniming methods count words or find patterns, LLMs understand context and relationships between words.

What are the main task of LLMs

They complete sentences, answer questions, translate languages, and write code.

How do LLMs work?

They are trained to predict the next word given all previous words in a sentence. They see millions of examples and learn patterns.

Where are LLMs powerfull enought for?

They are powerfull enough for translation, summarization and conversation.

What is tokenization?

The process where computers convert text into words and each word are given a unique ID.