Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Snell, Charlie, Lee, Jaehoon, Xu, Kelvin, Kumar, Aviral
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2408.03314