What You Will Learn
- LLM pre-training overview
Content Covered
Introduction to concepts behind LLM pre-training.
Resources
- Code for LLM Inference
- Tokenization using BPE, Unigram and WordPiece
- LLM Notebooks by Anish
- Pre-Training and Fine-Tuning (Colab Link)
- BERT MLM Task Details (Colab Link)
- In-Context Learning (Colab Link)
- Gen AI Hyperparameters (Colab Link)
- LLM Model Details (Colab Link)
- BERT
- GPT-3 Overview
- Annotated Transformer link
- Annotated Transformer Video List link
- Positional Encoding Blog (Kazemnejad) link
- Positional Encoding Blog (TowardsDataScience Part I) link
- Positional Encoding Blog (TowardsDataScience Part II) link
- WordPiece Tokenization by HuggingFace