AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min snip
Episode 21: Deploying LLMs in Production: Lessons Learned
Vanishing Gradients
Core Skills for Data Scientists in Working with Large Language Models
Working with Large Language Models (LLMs) requires core skills such as cleaning data, designing good metrics, and thinking rigorously about evaluations, which are innate to data scientists. The focus of LLMs is less on training models and more on tasks like looking at data skeptically, refining metrics, and improving data quality and iteration cycle speed. Becoming an expert in transformers is not essential for deploying LLMs; instead, expertise in curating diverse, high-quality datasets and acquiring intuition about data sets and their transformations is crucial. The emphasis in machine learning has always been on data cleaning and high-quality data, rather than solely training models.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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