Blockwise Compression of Transformer-based Models without Retraining.

Gaochen Dong Wei Chen

Published in: CoRR (2023)

Keyphrases

databases
accurate models
mathematical models
complex systems
fuzzy logic
real time
modeling framework
statistical models
probabilistic model
neural network
image compression
model selection
multiresolution
data structure
statistical methods
data compression
classification models
machine learning
database