alphaXiv

Explore

State of the Art

Sign In

Labs

Feedback

Browser Extension

We're hiring
PaperBlogResources

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

BibTex
Copy
@Article{Raposo2024MixtureofDepthsDA,
 author = {David Raposo and Sam Ritter and Blake Richards and T. Lillicrap and Peter Humphreys and Adam Santoro},
 booktitle = {arXiv.org},
 journal = {ArXiv},
 title = {Mixture-of-Depths: Dynamically allocating compute in transformer-based language models},
 volume = {abs/2404.02258},
 year = {2024}
}
GitHub
Mixture-of-depths
145
HTTPS
https://github.com/astramind-ai/Mixture-of-depths
SSH
git@github.com:astramind-ai/Mixture-of-depths.git
CLI
gh repo clone astramind-ai/Mixture-of-depths
Transform this paper into an audio lecture
Get an engaging lecture and Q&A format to quickly understand the paper in minutes, perfect for learning on the go.
Audio lecture
Q&A format