Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo
Paper
•
2503.09799
•
Published
•
10
Gabriel Teston
Gabriel-Teston
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 12 hours ago
Communication-Efficient Language Model Training Scales Reliably and
Robustly: Scaling Laws for DiLoCo
Organizations
