Episode Details

What is the model lifecycle like for experimenting with and then deploying generative AI models? Although there are some similarities, this lifecycle differs somewhat from previous data science practices in that models are typically not trained from scratch (or even fine-tuned). Chris and Daniel give a high level overview in this effort and discuss model optimization and serving.

Leave us a comment

Changelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

• Neo4j – NODES 2023 is coming in October!
• 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.

Featuring:

• Chris Benson – Twitter, GitHub, LinkedIn, Website
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• BigDL
• Article: Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
• Previous episode: Running large models on CPUs
• Baseten’s Truss
• Seldon
• Hugging Face’s TGI
• Intel Gaudi 2
• Intel TDX

Something missing or broken? PRs welcome!

Timestamps:

(00:07) - Welcome to Practical AI
(00:43) - Daniel at GopherCon & IIC
(03:31) - Local inference & TDX
(08:23) - Cloudflare Workers AI
(09:43) - Implementing new models
(16:14) - Sponsor: Neo4j
(17:11) - Navigating HuggingFace
(20:21) - Model Sizes
(24:34) - Running the model
(30:20) - Model optimization
(34:17) - Cloud vs local
(39:26) - Cloud standardization
(43:00) - Open source go-to tools
(46:21) - Keep trying!
(48:18) - Outro