This SuperDataScience episode hosted by our Chief Data Scientist, Jon Krohn, introduces my two-hour “Generative A.I with LLMs” training, which is packed with hands-on Python demos in Colab notebooks. It details open-source LLM (Hugging Face; PyTorch Lightning) and commercial (OpenAI API) options.
The training is available in its entirety on YouTube and all of the code is in GitHub. He’s disabled all YouTube monetization on this video (indeed, I’ve disabled it on all of my instructional content on YouTube) so that you can fully enjoy it, commercial-free!
Topic Summary
Module 1: Introduction to Large Language Models (LLMs)
– A Brief History of Natural Language Processing (NLP)
– Transformers
– Subword Tokenization
– Autoregressive vs Autoencoding Models
– ELMo, BERT and T5
– The GPT (Generative Pre-trained Transformer) Family
– LLM Application Areas
Module 2: The Breadth of LLM Capabilities
– LLM Playgrounds
– Staggering GPT-Family progress
– Key Updates with GPT-4
– Calling OpenAI APIs, including GPT-4
Module 3: Training and Deploying LLMs
– Hardware Options (e.g., CPU, GPU, TPU, IPU, AWS chips)
– The Hugging Face Transformers Library
– Best Practices for Efficient LLM Training
– Parameter-efficient fine-tuning (PEFT) with low-rank adaptation (LoRA)
– Open-Source Pre-Trained LLMs
– LLM Training with PyTorch Lightning
– Multi-GPU Training
– LLM Deployment Considerations
– Monitoring LLMs in Production
Module 4: Getting Commercial Value from LLMs
– Supporting ML with LLMs
– Tasks that can be Automated
– Tasks that can be Augmented
– Best Practices for Successful A.I. Teams and Projects
– What’s Next for A.I.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
