Generative Python Transformer p.5 - Training and some testing of GPT-2 model
6
Generative Python Transformer p.6 - Testing larger model
Description:
Learn to create a Generative Python Transformer (GPT) model in this comprehensive 3-hour 30-minute tutorial. Explore the entire process from acquiring raw data to testing a larger model. Begin with data acquisition techniques, then move on to cleaning and preprocessing the dataset. Master tokenization methods before diving into training and testing a GPT-2 model. Finally, gain hands-on experience in scaling up to a larger model for improved performance.