paper-with-me

Papers

Exploring Quantization for Efficient Pre-Training of Transformer Language Models

2024-07-16 · Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido, Sarath Chandar

The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has proven to be effective after pre-training and during fine-tuning, applying quantization in Transformers during pre-training has remained largely unexplored at scale for language modeling. This study aims to explore the impact of quantization for efficient pre-training of Transformers, with a focus on linear layer components. By systematically applying straightforward linear quantization to weights, activations, gradients, and optimizer states, we assess its effects on model efficiency, stability, and performance during training. By offering a comprehensive recipe of effective quantization strategies to be applied during the pre-training of Transformers, we promote high training efficiency from scratch while retaining language modeling ability. Code is available at https://github.com/chandar-lab/EfficientLLMs.

📄 PDF Abstract BibTeX arXiv:2407.11722

Code (1)

chandar-lab/efficientllms 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingQuantization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Focus 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음

Similar Papers 제목 키워드 기반

Towards Efficient Pre-training: Exploring FP4 Precision in Large Language Models

2025-02-17 · Jiecheng Zhou, Ding Tang, Rong Fu, Boni Hu 외

The burgeoning computational demands for training large language models (LLMs) necessitate efficient methods, including quantized training, which leverages low-bit arithmetic operations to reduce costs. While FP8 precisi…

Quantization

Understanding vision transformer robustness through the lens of out-of-distribution detection

2026-02-01 · Joey Kuang, Alexander Wong arxiv

Vision transformers have shown remarkable performance in vision tasks, but enabling them for accessible and real-time use is still challenging. Quantization reduces memory and inference costs at the risk of performance l…

Out-of-Distribution DetectionData Augmentation

Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT

2024-07-06 · Tianheng Ling, Chao Qian, Gregor Schiele

This paper presents the design of a hardware accelerator for Transformers, optimized for on-device time-series forecasting in AIoT systems. It integrates integer-only quantization and Quantization-Aware Training with opt…

QuantizationTime SeriesTime Series Forecasting

A Comprehensive Study on Quantization Techniques for Large Language Models

2024-10-30 · Jiedong Lang, Zhehao Guo, Shuyu Huang

Large Language Models (LLMs) have been extensively researched and used in both academia and industry since the rise in popularity of the Transformer model, which demonstrates excellent performance in AI. However, the com…

Quantization

Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization

2022-08-10 · Zhengang Li, Mengshu Sun, Alec Lu, Haoyu Ma 외

Vision transformers (ViTs) are emerging with significantly improved accuracy in computer vision tasks. However, their complex architecture and enormous computation/storage demand impose urgent needs for new hardware acce…

Quantization