Softmax Bias Correction for Quantized Generative Models von Pandey, Nilesh Prasad, Fournarakis, Marios, Patel, Chirag, Nagel, Markus

Volltext bestellen

Sparse High Rank Adapters von Bhardwaj, Kartikeya, Pandey, Nilesh Prasad, Priyadarshi, Sweta, Ganapathy, Viswanath, Esteves, Rafael, Kadambi, Shreya, Borse, Shubhankar, Whatmough, Paul, Garrepalli, Risheek, Van Baalen, Mart, Teague, Harris, Nagel, Markus

Volltext bestellen

Softmax Bias Correction for Quantized Generative Models von Nilesh Prasad Pandey, Fournarakis, Marios, Patel, Chirag, Nagel, Markus

Volltext

Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models von Bhardwaj, Kartikeya, Nilesh Prasad Pandey, Priyadarshi, Sweta, Lee, Kyunggeun, Ma, Jun, Teague, Harris

Volltext

A Practical Mixed Precision Algorithm for Post-Training Quantization von Nilesh Prasad Pandey, Nagel, Markus, Mart van Baalen, Huang, Yin, Patel, Chirag, Blankevoort, Tijmen

Volltext

Sparse High Rank Adapters von Bhardwaj, Kartikeya, Nilesh Prasad Pandey, Priyadarshi, Sweta, Ganapathy, Viswanath, Esteves, Rafael, Kadambi, Shreya, Borse, Shubhankar, Whatmough, Paul, Garrepalli, Risheek, Mart Van Baalen, Teague, Harris, Nagel, Markus

Volltext

FouRA: Fourier Low Rank Adaptation von Borse, Shubhankar, Kadambi, Shreya, Nilesh Prasad Pandey, Bhardwaj, Kartikeya, Ganapathy, Viswanath, Priyadarshi, Sweta, Garrepalli, Risheek, Esteves, Rafael, Hayat, Munawar, Porikli, Fatih

Volltext