-
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 86 -
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
Paper • 2404.05961 • Published • 64 -
Compression Represents Intelligence Linearly
Paper • 2404.09937 • Published • 27 -
Multi-Head Mixture-of-Experts
Paper • 2404.15045 • Published • 59
Peter Liu
Aozaki-Shinji
·
AI & ML interests
None yet
Organizations
None yet
Collections
1
models
None public yet
datasets
None public yet