PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models
Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Rui Yan
Abstract
While transformer-based pre-trained language models (PLMs) have dominated a number of NLP applications, these models are heavy to deploy and expensive to use. Therefore, effectively compressing large-scale PLMs becomes an increasingly important problem. Quantization, which represents high-precision tensors with low-bit fix-point format, is a viable solution. However, most existing quantization methods are task-specific, requiring customized training and quantization with a large number of trainable parameters on each individual task. Inspired by the observation that the over-parameterization nature of PLMs makes it possible to freeze most of the parameters during the fine-tuning stage, in this work, we propose a novel “quantize before fine-tuning” framework, PreQuant, that differs from both quantization-aware training and post-training quantization. {pasted macro ‘OUR’} is compatible with various quantization strategies, with outlier-aware parameter-efficient fine-tuning incorporated to correct the induced quantization error. We demonstrate the effectiveness of PreQuant on the GLUE benchmark using BERT, RoBERTa, and T5. We also provide an empirical investigation into the workflow of PreQuant, which sheds light on its efficacy.- Anthology ID:
- 2023.findings-acl.511
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8065–8079
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.511
- DOI:
- 10.18653/v1/2023.findings-acl.511
- Cite (ACL):
- Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, and Rui Yan. 2023. PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8065–8079, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models (Gong et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-acl.511.pdf