RegMix: Data Mixture as Regression for Language Model Pre-training
Paper
•
2407.01492
•
Published
•
37
•
7
Xiaosen Zheng
xszheng2020
AI & ML interests
Data-Centric AI and AI Safety.
Recent Activity
liked
a model
4 days ago
lkevinzc/Llama-3.2-3B-NuminaQA
liked
a model
14 days ago
GAIR/LIMO
liked
a dataset
14 days ago
GAIR/MathPile
Organizations
xszheng2020's activity
commented
a
paper
7 months ago