metaai·lightalo unofficial · independent
Universe / Language & LLMs / XLM-R
Language & LLMs · 2019

XLM-R

XLM-R (XLM-RoBERTa)

100 languages in one encoder — the ancestor of NLLB

open source superseded ~280M (base) / ~560M (large) / 3.5B (XL) / 10.7B (XXL) params
★ 32k fairseq❝ 9.1k citationsread 2026-09-03

Latest: XLM-R base/large/XL/XXL (2019-2021)

Cross-lingual RoBERTa trained on 2.5TB of filtered CommonCrawl covering 100 languages (November 2019). It delivered massive gains on low-resource languages and set the standard for multilingual understanding — a direct ancestor of Meta's translation moonshots like NLLB.

Why it matters

XLM-R proved one encoder trained on 2.5TB of CommonCrawl across 100 languages could match monolingual models on high-resource languages while lifting low-resource ones dramatically. It became the default multilingual backbone for years — xlm-roberta-base still sees over 20 million monthly Hugging Face downloads — and set up Meta's NLLB translation push.

Facts

Try it yourself

Lineage

Descends fromRoBERTa

See the whole family tree →

Sources

More in Language & LLMs

BARTBlenderBotfairseqOPT-175BGalacticaLLaMA

Read the Language & LLMs story on the sky →

✦ Open on the map Explore Language & LLMs Quiz me