shrinkage-bias

Tag

Cards List
#shrinkage-bias

Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe

Hugging Face Daily Papers · 6d ago Cached

This paper identifies a fundamental limitation (shrinkage bias) in non-uniform FP4 quantization formats for LLM pretraining and proposes UFP4, a uniform 4-bit training recipe that outperforms existing E2M1-based methods.

0 favorites 0 likes
← Back to home

Submit Feedback