PCDVQ compresses LLM weights to 2 bits by quantizing vector directions and magnitudes separately with distribution-matched codebooks, reporting modest zero-shot accuracy gains over prior vector quantization baselines.
Language models are few-shot learners.Advances in Neural Information Processing Systems, 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling
PCDVQ compresses LLM weights to 2 bits by quantizing vector directions and magnitudes separately with distribution-matched codebooks, reporting modest zero-shot accuracy gains over prior vector quantization baselines.