Embeddings, Transfer Learning, and Custom LLMs: Tailoring Language Models to Your Needs

Explore key techniques in artificial intelligence and large language models (LLMs) in this 27-minute PyCon US conference talk. Dive into fine-tuning and transfer learning applied to well-known models like GPT-3.5 Turbo/GPT4 and open-source models available on Hugging Face. Learn how to adapt these models to specific use cases in application development. Discover vector search techniques for querying information from vector databases to locate data within documents and generate synthetic content. Understand embeddings, how to transform unstructured information into vectors, and index them in vector databases for efficient access. Gain practical knowledge using Python libraries such as transformers, langChain, and PyTorch through introductory context and hands-on demonstrations. Access accompanying presentation slides for additional reference.