How and When to Fine-tune Large Language Models

​In this event we'll discuss how and when you should fine-tune LLMs. Including hands-on code demos of how to fine-tune with multiple different datasets! We'll describe in detail:

• ​When you should fine-tune your LLM vs just using RAG.

• ​How to fine-tune for long context tasks, like summarization.

• ​How loss-masking works and when to use it.

• ​How to fine-tune with multi-turn conversation data.

• ​Show performance improvements for all these tasks.