Pith. sign in

Llama 2: Open Foundation and Fine-Tuned Chat Models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Turning LLM Activations Quantization-Friendly

cs.LG · 2025-05-11 · conditional · novelty 4.0

Channel-wise scaling applied before Hadamard rotation reduces 4-bit layer-wise quantization error in LLaMA2-7B, especially on down-projection layers with massive activation outliers.

citing papers explorer

Showing 1 of 1 citing paper.

  • Turning LLM Activations Quantization-Friendly cs.LG · 2025-05-11 · conditional · none · ref 1

    Channel-wise scaling applied before Hadamard rotation reduces 4-bit layer-wise quantization error in LLaMA2-7B, especially on down-projection layers with massive activation outliers.