hugpadhugpad

FacebookAI / xlm-roberta-large

Other561M2.3M555Updated Feb 19, 2024
Hugging Face

Downloads

2.3M

Likes

555

Last updated

Feb 19, 2024

License

mit

XLM-RoBERTa model pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. It was introduced in the paper Unsupervised Cross-lingual Representation Learning at Scale by Conneau et al. and first released in this repository.

Tasks & library

  • fill mask
  • transformers

Tags

  • transformers
  • pytorch
  • tf
  • jax
  • onnx
  • xlm-roberta

Technical specifications

Parameters561M
Librarytransformers
Languages94 languages
Licensemit