GPT-2 Courses and Certifications

Andrej Karpathy

Reproducing GPT-2 (124M) from Scratch - Implementation and Optimization

Comprehensive tutorial on reproducing GPT-2 (124M) from scratch, covering implementation, optimization, training setup, and results analysis. Includes practical coding and performance tuning tips.

• YouTube
• 4 hours 1 minute
• Self-Paced
• Free Video

AI Engineer

Decoding the Decoder LLM Without Code - Understanding GPT-2 Through Spreadsheets

Discover how GPT-2 works using only Excel spreadsheets - no coding required! Demystify tokenization, embeddings, attention mechanisms, and neural networks through accessible visualizations.

• YouTube
• 17 minutes
• Self-Paced
• Free Video

Wolfram

Analyzing GPT-2's Brain Development

Explore GPT-2's inner workings through token manipulation, node analysis, and temperature adjustments to gain insights into its structure and functioning.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

Generating Python Code with GPT

Build and test a GPT-2 model in Python, from raw-data acquisition and cleaning through preprocessing, tokenization, and training.

• YouTube
• 3 hours 30 minutes
• Self-Paced
• Free Video

GOTO Conferences

Inside GPT - Large Language Models Demystified

Demystifying GPT algorithms: architecture, inner workings, and practical applications. Explore NLP fundamentals, train models, and learn to leverage ChatGPT and GPT4 for innovative solutions.

• YouTube
• 47 minutes
• Self-Paced
• Free Video

AI Engineer

How LLMs Work for Web Developers - GPT in 600 Lines of Vanilla JavaScript

Discover how modern LLMs work by building GPT-2 from scratch in vanilla JavaScript, covering tokenization, embeddings, neural networks, and text generation for web developers.

• YouTube
• 1 hour 42 minutes
• Self-Paced
• Free Video

NDC Conferences

Inside GPT - Large Language Models Demystified

Dive into GPT architecture and ChatGPT internals, from NLP fundamentals to training models, prompt engineering, and RAG patterns for building AI-powered applications.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Harnessing Transformers with Hugging Face

Explore Hugging Face through hands-on work with BERT, GPT-2, and T5, including tokenizers, architecture-specific behavior, classification, question answering, and text generation.

• CodeSignal
• 3 hours
• Self-Paced
• Free Certificate

Samuel Chan

LangChain and HuggingFace Integration - Using GPT-2 Without OpenAI Credits

1 rating

Connect LangChain to Hugging Face’s hosted GPT-2 model through its inference API, without relying on OpenAI credits.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

Samuel Chan

OpenAI's Python QuickStart Tutorial - GPT-3, DALL-E 2, and Whisper

A first look at using OpenAI’s Python library for text completion and Q&A, image generation, and speech transcription.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

echohive

QA Chat with a Website - OpenAI Embeddings Tutorial: Use GPT-3 API and OpenAI ADA-2 Embeddings

Convert website text into OpenAI embeddings for similarity-search-based GPT-3 question answering.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

echohive

Langchain ChatGPT Your Documents Challenge Part 2 with GPT-3 and OpenAI Embeddings and Streamlit UI

Build a document-questioning chatbot with LangChain, GPT-3, OpenAI embeddings, Wikipedia search, and a Streamlit file-upload interface.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Devoxx

What's in My AI? A Comprehensive Analysis of Datasets Used to Train GPT 1, GPT 2, GPT 3, GPT NeoX 20

Comprehensive analysis of datasets used to train major language models, exploring size, content, and documentation practices for GPT-1 to Gopher. Insights into AI development and dataset transparency.

• YouTube
• 53 minutes
• Self-Paced
• Conference Talk

Andrej Karpathy

Deep Dive into Large Language Models: From ChatGPT to Training and Applications

Dive into a comprehensive exploration of Large Language Models, from fundamental concepts to advanced topics like RLHF, with insights from an industry expert on their development and practical applications.

• YouTube
• 3 hours 31 minutes
• Self-Paced
• Free Video

Generating New Recipes using GPT-2

45 ratings at Coursera

Fine-tune GPT-2 with the HuggingFace library on Google Colab to generate original recipes from ingredient lists, preprocessing a recipe dataset and exploring knowledge distillation.

• Coursera
• 2-3 hours
• No Longer Offered
• Paid Course