Creating Your Own Copy with a Fine-Tuned LLM
summary
The talk explains how to fine-tune a large language model (LLM) for a specific use case, covering data preparation, instruction creation, the training process itself, and deploying the tuned model to production. It compares using self-hosted models versus OpenAI's API and surveys top frameworks for deployment.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 4:01What is an LLM and types
- 10:49Why fine-tune models
- 16:42Adding new knowledge
- 22:24Data preparation
- 26:17Training process
- 31:15Production deployment
- 36:17Resources
- 38:27Q&A
related talks
30mLearning to wield large language models
29mLocal LLM fine-tuning: a practical example
31mCustomizing LLMs: A Guide to local Fine-Tuning...
21mFrom Data to Precision: Fine-Tuning LLMs for Proprietary Query Languages
49mA Practical Approach to Using LLMs: Peculiarities and Pitfalls
33mFine-Tuning Large Language Models with Declarative ML Orchestration
22mSpecializing Small Language Models with less data
12mKeynote: How LLMs Have Changed the Way Organizations Do AI