← Search

Paul Ioan Clotan

2 accepted papers

2025

Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs

ACL 2025finding

We present a simple meta quantization approach that quantizes different layers of a large language model (LLM) at different bit levels, and is independent of the underlying quantization technique. Specifically, we quantize the most important layers to higher bit precision and less important layers t…

2024

Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy

EMNLP 2024finding

This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established by SliceGPT. By transitioning from constant to dynamic slicing, our method leverages the newly proposed Layer Redundancy…