Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models
Paper
•
2506.19697
•
Published
•
44
Mujeen Sung
mjtwins
AI & ML interests
None yet
Recent Activity
liked
a model
2 months ago
dmis-lab/llama-3-meerkat-8b-v1.0
liked
a model
4 months ago
seeklhy/OmniSQL-7B
upvoted
a
paper
6 months ago
Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large
Language Models
Organizations
None yet
upvoted
a
paper
6 months ago