activity
20222026
most citedWhere to start? Analyzing the potential value of intermediate models

2 citations · 5 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2022

ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning

Shachar Don-Yehiya, Elad Venezian, Colin Raffel +3

We propose a new paradigm to continually evolve pretrained models, denoted ColD Fusion. It provides the benefits of multitask learning but leverages distributed computation with li…