A comprehensive guide on reproducing and training the GPT-2 124M model using PyTorch, comparing its performance to OpenAI's pre-trained models. Taught by Andrej Kaparthy, a founding member of OpenAI and a ex-senior director of AI at Tesla.

A walkthrough on building the GPT tokenizer. This focuses on tokenization in large language models, discussing its complexities, necessary understanding, and its impact on model performance. Taught by Andrej Kaparthy, a founding member of OpenAI and a ex-senior director of AI at Tesla.