Iterative Layer Pruning for Efficient Translation Inference
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914116155736064 |
|---|---|
| author | Moslem, Yasmin Farouq, Muhammad Hazim Al Kelleher, John D. |
| author_facet | Moslem, Yasmin Farouq, Muhammad Hazim Al Kelleher, John D. |
| contents | Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requirements. In this paper, we address this challenge and present our submissions to the Model Compression track at the Conference on Machine Translation (WMT 2025). In our experiments, we investigate iterative layer pruning guided by layer importance analysis. We evaluate this method using the Aya-Expanse-8B model for translation from Czech to German, and from English to Egyptian Arabic. Our approach achieves substantial reductions in model size and inference time, while maintaining the translation quality of the baseline models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_22763 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Iterative Layer Pruning for Efficient Translation Inference Moslem, Yasmin Farouq, Muhammad Hazim Al Kelleher, John D. Computation and Language Performance Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requirements. In this paper, we address this challenge and present our submissions to the Model Compression track at the Conference on Machine Translation (WMT 2025). In our experiments, we investigate iterative layer pruning guided by layer importance analysis. We evaluate this method using the Aya-Expanse-8B model for translation from Czech to German, and from English to Egyptian Arabic. Our approach achieves substantial reductions in model size and inference time, while maintaining the translation quality of the baseline models. |
| title | Iterative Layer Pruning for Efficient Translation Inference |
| topic | Computation and Language Performance |
| url | https://arxiv.org/abs/2510.22763 |