Cite
Notes
Only stored in your browser.
Attribution
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
arXiv 2024
from 1 papers
Devang Naik
Fartash Faghri
Iman Mirzadeh
Mehrdad Farajtabar
Minsik Cho
Mohammad Samragh
Moin Nabi