Iterative Layer Pruning for Efficient Translation Inference
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationModel CompressionSimilar Papers 제목 키워드 기반
CULL-MT: Compression Using Language and Layer pruning for Machine Translation
Multilingual machine translation models often outperform traditional bilingual models by leveraging translation knowledge transfer. Recent advancements have led to these models supporting hundreds of languages and achiev…
Knowledge DistillationMachine Translationparameter-efficient fine-tuningTransfer Learning+1Efficient Speech Translation through Model Compression and Knowledge Distillation
Efficient deployment of large audio-language models for speech translation remains challenging due to their significant computational requirements. In this paper, we address this challenge through our system submissions …
Knowledge DistillationModel CompressionQuantizationTranslationBlockPruner: Fine-grained Pruning for Large Language Models
With the rapid growth in the size and complexity of large language models (LLMs), the costs associated with their training and inference have escalated significantly. Research indicates that certain layers in LLMs harbor…
Heuristic SearchPrune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation
Layer pruning has emerged as a promising technique for compressing large language models (LLMs) while achieving acceleration proportional to the pruning ratio. In this work, we identify that removing any layer induces a …
AfriNLLB: Efficient Translation Models for African Languages
In this work, we present AfriNLLB, a series of lightweight models for efficient translation from and into African languages. AfriNLLB supports 15 language pairs (30 translation directions), including Swahili, Hausa, Yoru…
Knowledge Distillation