The speaker addresses the misconceptions surrounding fine-tuning language models (LLMs), emphasizing that fine-tuning on personal emails doesn't enable the model to write like the user. They highlight the effectiveness of retrieval augmented generation (RAG) for generating responses and discuss scenarios where fine-tuning is useful. The speaker also cautions against the belief that fine-tuning is always necessary and reminds listeners of the data collection and cleaning challenges.
In this episode we welcome back our good friend Demetrios from the MLOps Community to discuss fine-tuning vs. retrieval augmented generation. Along the way, we also chat about OpenAI Enterprise, results from the MLOps Community LLM survey, and the orchestration and evaluation of generative AI workloads.
Leave us a comment
Changelog++ members save 1 minute on this episode because they made the ads disappear. Join today!
Sponsors:
- Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com
- Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.
- Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster!
Featuring:
Show Notes:
Something missing or broken? PRs welcome!