← Back to Universe

LLM

aibeginner

Large Language Models (LLMs) are a new class of generative machine learning models. They work by taking in a prompt (what you want the model to do) and then generating text. Though language models have been around for decades, today's are pretrained on massive, internet-scale datasets, so they are, well, large.

Read the full post ↗

How do Large Language Models work?

Breaking down what ChatGPT and others are doing under the hood

Read in the Knowledge Base →

Mentioned in

Inference

Inference is a fancy term that just means using an ML model that has already been trained.

RAG

Retrieval Augmented Generation (RAG) is a way to make LLMs like GPT-4 more accurate and personalized to your specific data

How do Large Language Models work?

Breaking down what ChatGPT and others are doing under the hood

It was never about LLM performance

Beware the benchmark.

Related terms

Inference

Context Window

Training