On the Way to Lossless Compression of Language Transformers: Exploring Cross-Domain Properties of Quantization

Nikita Martynov, Aleksei Goncharov, Gleb Kumichev, Evgeniy Egorov, Stanislav Vladimirovich Pavlov, Mikhail Sergeevich Durinov, Aleksandr Sergeevich Zuev, Egor Anatolievich Filimonov


Abstract
Modern Transformers achieved impressive results on various Natural Language Processing tasks over the last few years. The one downside of this success is the size of these models. Huge capacity, which sometimes surpasses billions of parameters, improves generalization abilities, but makes it difficult to employ. Developing field of model compression seeks to reduce the model size and inference latency. This research focuses on one of the compression techniques — Post-Training Quantization. We present a methodology to effectively quantize at least 95% of Transformer weights and corresponding activations to INT8 without any access to task-specific data so the drop in performance does not exceed 0.02%. Furthermore, we provide intriguing observations that reflect cross-domain nature of some of the quantization properties.
Anthology ID:
2024.lrec-main.1089
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
12435–12442
Language:
URL:
https://aclanthology.org/2024.lrec-main.1089
DOI:
Bibkey:
Cite (ACL):
Nikita Martynov, Aleksei Goncharov, Gleb Kumichev, Evgeniy Egorov, Stanislav Vladimirovich Pavlov, Mikhail Sergeevich Durinov, Aleksandr Sergeevich Zuev, and Egor Anatolievich Filimonov. 2024. On the Way to Lossless Compression of Language Transformers: Exploring Cross-Domain Properties of Quantization. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12435–12442, Torino, Italia. ELRA and ICCL.
Cite (Informal):
On the Way to Lossless Compression of Language Transformers: Exploring Cross-Domain Properties of Quantization (Martynov et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1089.pdf