15 B Models

topic on 1 show · 1 statements across 1 episodes

1 statements about 15 B Models, every show

LATENT SPACE Assertion Supported

He: Upcycling a 15B model on 1T tokens yielded 4% MMLU gain

“On other scaling experiments, we tried on 15 B models upcycling and applied on one trillion tokens and achieved roughly about five percent improvement in terms of the validation loss and four percent improvement on MMLU.”

Ethan He Oct 29, 2024 ▶ 21:12 [Paper Club] Upcycling Large Language Models into Mixture of Experts

← every entity, every show

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

15 B Models

1 statements about 15 B Models, every show

Turn any episode into a week of clips.