Hackaday

TurboQuant: Reducing LLM Memory Usage With Vector Quantization

Large language models (LLMs) aren’t actually giant computer brains. Instead, they are effectively massive vector spaces in ...
IEEE

Reversible Data Hiding for JPEG Images Based on Quantization-Table-Modification and STC

Abstract: Reversible data hiding (RDH) for JPEG images has attracted extensive attentions in recent years. Particularly, quantized-DCT-coefficients-modification and quantization-table-modification are ...
GitHub

alexnet_accuracy_imagenet.py

# e.g., python generate_RD_curves_vgg16.py 3 1 5 -> run GPU3 to do the statistics for the 5th kernal in layer 1. # the path of checkpoint file of pre-trained VGG16 ...
GitHub

generate_RD_curves_vgg16_baseline.py

# e.g., python generate_RD_curves_vgg16.py 3 1 5 -> run GPU3 to do the statistics for the 5th kernal in layer 1. # the number of convolutional layers in VGG16. Totally 13 conv layers and 3 fully ...