Search Results for author:
Found 1 papers, 0 papers with code
QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning
Firstly, our analysis revealed that, on average, 65\% of quantization errors result from the precision loss incurred by the dynamic range amplification effect of outliers across the target Transformer-based models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
