RegMix: Data Mixture as Regression for Language Model Pre-training
Paper
•
2407.01492
•
Published
•
35
•
7
Xiaosen Zheng
xszheng2020
AI & ML interests
Data-Centric AI and AI Safety.
Recent Activity
liked
a dataset
14 days ago
proj-persona/PersonaHub
liked
a model
15 days ago
Qwen/Qwen2.5-3B-Instruct-AWQ
liked
a model
15 days ago
Qwen/Qwen2.5-1.5B-Instruct-AWQ
Organizations
xszheng2020's activity
commented
a
paper
3 months ago