AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
1min snip
Making AI Work: Fine-Tuning, Inference, Memory | Sharon Zhou, CEO, Lamini
The MAD Podcast with Matt Turck
Memory Tuning for Model Accuracy
Memory tuning is crucial for ensuring that a model's predictions align accurately with specific facts, reducing the risk of even slightly incorrect outputs. This technique optimizes the model's memory to minimize errors and computational costs, especially in the context of open-source models like Laura, Q-Lora, and others. By fine-tuning a mixture of expert adapters on top of the model, memory tuning enhances the accuracy of predictions by minimizing losses and ensuring that the model selects the most appropriate expert for each scenario.
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