2min snip

Super Data Science: ML & AI Podcast with Jon Krohn cover image

801: Merged LLMs Are Smaller And More Capable, with Arcee AI's Mark McQuade and Charles Goddard

Super Data Science: ML & AI Podcast with Jon Krohn

NOTE

Automated Model Merging for Enhanced Results

Automated model merging utilizes a script in the mergekit library called mergekit evolve, which enables users to select input models, define tasks for excellence, and generate a merged model seamlessly. This approach eliminates the need for manual parameter mutation and intuition building by allowing users to specify their requirements and obtain the desired merge outcome. Evolutionary model merging mimics evolutionary algorithms by randomly combining parts of models to create children models, evaluating their performance, and breeding subsequent generations from the best performers, ensuring an effective and flexible merging process.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode