English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

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

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