Embeddings, Transfer Learning and More: LLM Tailored to You
summary
Covers how to adapt large language models (GPT-3.5 Turbo, GPT-4 and open-source Hugging Face models) to specific use cases using fine-tuning and transfer learning, implemented in Python with transformers, LangChain and PyTorch. Explains embeddings: converting unstructured data into vectors, indexing them in vector databases and performing vector search to retrieve document information for synthetic content generation, and includes practical, example-driven demonstrations.
AI-written summary · about
chapters (7)
- 0:00Welcome
- 3:52What are LLMs?
- 6:56Personalization techniques
- 9:54What is RAG and how it works
- 13:28Code demo
- 23:39Summary
- 24:12Q&A
related talks
51mLarge Language Models for Real-World Applications - A Gentle Intro
25mEmbeddings, Transformers, RLHF: Three key ideas to understand ChatGPT
44mTransfer learning in NLP
32mAn Introduction to Transfer Learning in NLP and HuggingFace
47mInside GPT – Large Language Models Demystified
01h 00mInside GPT – Large Language Models Demystified
58mAn Introduction to Transfer Learning and Hugging Face
43mBeyond the Hype: A Realistic Look at Large Language Models