Token dropping

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Oct 29, 2024 by Ethan He · across every show →

Everything said about Token dropping, oldest first

Oct 29, 2024 neutral
Insight
He: Token dropping works in MoE pre-training; dropless excels in fine-tuning
“A lot of pre-training experiments show that Token dropping is very efficient, and it doesn't impact performance, but in some of the, like, the downstream fine-tuning, people realize drop-less is better.”
Ethan He Oct 29, 2024 ▶ 10:28 [Paper Club] Upcycling Large Language Models into Mixture of Experts
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes 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.