All Topics
All Topics
Technology
Technology
AI
AI
Business
Business
Entertainment
Entertainment
News
News
Programming
Programming
Security
Security
Science
Science
Design
Design
Environment
Environment
Finance
Finance
Crypto
Crypto
Politics
Politics
Sports
Sports
Education
Education
Gaming
Gaming
Art
Art
Music
Music
Health
Health
Books
Books
Food
Food
Travel
Travel
Personal
Personal
Bluesky
Twitter

A ~10K parameter router can beat every individual open model on MMLU by learning which model should answer which question. Not by being smarter than the models. By allocating work better.

3h agoCode

Source

Twitter / XA ~10K parameter router can beat every individual open model on MMLU by learning which model should answer which question. Not by being smarter than the models. By allocating work better.github.com
Snippet from the RSS feed
A ~10K parameter router can beat every individual open model on MMLU by learning which model should answer which question. Not by being smarter than the models. By allocating work better.

You might also wanna read

Comments

Sign in to join the conversation.

No comments yet. Be the first.