Creating instruction tuned models

Practical AI: Machine Learning, Data Science

At the recent ODSC East conference, Daniel got a chance to sit down with Erin Mikail Staples to discuss the process of gathering human feedback and creating an instruction tuned Large Language Models (LLM). They also chatted about the importance of open data and practical tooling for data annotation and fine-tuning. Do you want to create your own custom generative AI models? This is the episode for you!

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:

• Erin Mikail Staples – Mastodon, Twitter
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• Label Studio
• Slides from Erin’s recent PyData talk on RLHF

Something missing or broken? PRs welcome!

अध्यायों

1. Welcome to Practical AI (00:00:00)

2. Erin Mikail Staples (00:00:43)

3. Open source attendees (00:02:09)

4. The key to RLHF (00:03:54)

5. Tooling for RLHF (00:05:35)

6. Humanities in data science (00:07:33)

7. Label Studio's workflow (00:11:22)

8. The open data ecosystem (00:15:41)

9. Do data labeling (00:21:04)

10. Exciting changes coming (00:22:33)

11. DevRel(ish) and other resources (00:24:15)

12. Goodbyes (00:25:13)

13. Outro (00:25:45)