Andrej Karpathy — searchable YouTube transcripts & AI Q&A

How I use LLMs

Andrej Karpathy explains how to use LLMs like ChatGPT, detailing tokenization, conversation formats, and the broader AI ecosystem.

Deep Dive into LLMs like ChatGPT

This video explains the process of building large language models like ChatGPT, focusing on data collection and pre-training.

Let's reproduce GPT-2 (124M)

Reproducing the 124M GPT-2 model using PyTorch and Hugging Face Transformers, covering model architecture, tokenization, and training.

Let's build the GPT Tokenizer

Andrej Karpathy explains the process of tokenization in large language models, covering character-level and chunk-level tokenization, and the importance of tokenization in large language models.

[1hr Talk] Intro to Large Language Models

Andrej Karpathy explains how large language models work, specifically the LLaMA 270b model, and how to run it on a MacBook.