paper-with-me

홈 › Papers

Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model

2022-12-19 · Yeskendir Koishekenov, Alexandre Berard, Vassilina Nikoulina

The recently released NLLB-200 is a set of multilingual Neural Machine Translation models that cover 202 languages. The largest model is based on a Mixture of Experts architecture and achieves SoTA results across many language pairs. It contains 54.5B parameters and requires at least four 32GB GPUs just for inference. In this work, we propose a pruning method that enables the removal of up to 80% of experts without further finetuning and with a negligible loss in translation quality, which makes it feasible to run the model on a single 32GB GPU. Further analysis suggests that our pruning metrics can identify language-specific experts.

📄 PDF Abstract BibTeX arXiv:2212.09811

Code (0)

등록된 구현이 없습니다.

Tasks

GPUMachine TranslationMixture-of-ExpertsTransfer LearningTranslation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

AfriNLLB: Efficient Translation Models for African Languages

2026-02-10 · Yasmin Moslem, Aman Kassahun Wassie, Amanuel Gizachew Abebe arxiv

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

CULL-MT: Compression Using Language and Layer pruning for Machine Translation

2024-11-10 · Pedram Rostami, Mohammad Javad Dousti

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+1

Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study

2026-08-04 · Ahmed Amine Aliane, Nasredine Semmar, Hassina Aliane arxiv

The adoption of large pre-trained multilingual models for neural machine translation (MNMT) faces a major challenge: excessive memory and computational consumption due to overly large vocabularies and embedding layers. A…

Knowledge DistillationMachine Translation

Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs

2024-07-01 · Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning 외

The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their substantial demands on memory, processing pow…

GPUMixture-of-Experts

How to Score Experts for One-Shot MoE Expert Pruning: A Unified Formulation and Selection Principle

2026-06-14 · Zongfang Liu, Jinghui Zhang, Zijian Ma, Guangyi Chen 외 arxiv

Mixture-of-Experts (MoE) language models reduce per-token computation through sparse expert activation, yet deployment still requires storing the full expert pool, making one-shot expert pruning a practical approach for …