HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem.
Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo, Peter Richtrik, Dan Alistarh
Browse the full NAACL paper archive.
Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo, Peter Richtrik, Dan Alistarh
Browse the full NAACL paper archive.