Skip to content

Latest commit

 

History

4 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 

Repository files navigation

routing-llm_problem1

routing llm - problem 1 : static finetuning problem

Can a small model be finetuned or altered to increase the frequency of queries that are sent to it relative to a large model? The notion of ‘easy’ queries (queries that have nearly the same performance for both large and small models) was introduced in [Wan+24]. Is it possible for small models to get more share of routing?

About

routing llm - problem 1 : static finetuning problem

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors