This is the 5th video in a series on using large language models (LLMs) in practice. Here, I discuss how to fine-tune an existing LLM for a particular use case and walk through a concrete example with Python code.
Learn how to implement RAG (Retrieval Augmented Generation) from scratch, straight from a LangChain software engineer. This Python course teaches you how to use RAG to combine your own custom data with the power of Large Language Models (LLMs). 💻 Code: https://github.com/langchain-ai/rag-from-scratch ⭐️ Course Contents ⭐️⌨️ (0:00:00) Overview⌨️ (0:05:53) Indexing⌨️ (0:10:40) Retrieval⌨️ (0:15:52) Generation⌨️ (0:22:14)…
What are the neurons, why are there layers, and what is the math underlying it? Typo correction: At 14 minutes 45 seconds, the last index on the bias vector is n, when it’s supposed to in fact be a k. Thanks for the sharp eyes that caught that! There are two neat things about this…
Demystifying attention, the key mechanism inside transformers and LLMs.
https://www.youtube.com/watch?v=9-Jl0dxWQs8 AI Alignment forum post from the Deepmind researchers referenced at the video’s start:https://www.alignmentforum.org/posts/… Anthropic posts about superposition referenced near the end:https://transformer-circuits.pub/2022…https://transformer-circuits.pub/2023… Some added resources for those interested in learning more about mechanistic interpretability, offered by Neel Nanda Mechanistic interpretability paper reading listhttps://www.alignmentforum.org/posts/… Getting started in mechanistic interpretabilityhttps://www.neelnanda.io/mechanistic-… An interactive demo of sparse autoencoders (made…
In this video we will talk about backpropagation – an algorithm powering the entire field of machine learning and try to derive it from first principles. OUTLINE:00:00 Introduction01:28 Historical background02:50 Curve Fitting problem06:26 Random vs guided adjustments09:43 Derivatives14:34 Gradient Descent16:23 Higher dimensions21:36 Chain Rule Intuition27:01 Computational Graph and Autodiff36:24 Summary38:16 Shortform39:20 Outro Jürgen Schmidhuber’s blog…
This is the last of a series of 3 videos where we demystify Transformer models and explain them with visuals and friendly examples. 00:00 Introduction01:50 What is a transformer?04:35 Generating one word at a time08:59 Sentiment Analysis13:05 Neural Networks18:18 Tokenization19:12 Embeddings25:06 Positional encoding27:54 Attention32:29 Softmax35:48 Architecture of a Transformer39:00 Fine-tuning42:20 Conclusion
