Noise Perturbation Fine-tuning (NPFT) reduces the quantization sensitivity of outlier weights via LoRA fine-tuning with random perturbations, letting standard RTN quantization match GPTQ on LLaMA2-7B-4bit without mixed-precision outlier retention.
Hawq: Hessian aware quantization of neural networks with mixed-precision
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization
Noise Perturbation Fine-tuning (NPFT) reduces the quantization sensitivity of outlier weights via LoRA fine-tuning with random perturbations, letting standard RTN quantization match GPTQ on LLaMA2-7B-4bit without mixed-precision outlier retention.