Search Results for author:
Found 5 papers, 3 papers with code
Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling
The channel-wise shifting aligns the center of each channel for removal of outlier asymmetry.
Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models
With the trends of large NLP models, the increasing memory and computation costs hinder their efficient deployment on resource-limited devices.
Distribution-sensitive Information Retention for Accurate Binary Neural Network
We present a novel Distribution-sensitive Information Retention Network (DIR-Net) that retains the information in the forward and backward propagation by improving internal propagation and introducing external representations.
Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization
We first give a theoretical analysis that the diversity of synthetic samples is crucial for the data-free quantization, while in existing approaches, the synthetic data completely constrained by BN statistics experimentally exhibit severe homogenization at distribution and sample levels.
Diversifying Sample Generation for Accurate Data-Free Quantization
Unfortunately, we find that in practice, the synthetic data identically constrained by BN statistics suffers serious homogenization at both distribution level and sample level and further causes a significant performance drop of the quantized model.
