FacebookAI/xlm-roberta-base
🧠 AI ModelFacebookAI
Multilingual masked language model pretrained on 100+ languages.
XLM-RoBERTa base is a transformer model with 12 layers, 768 hidden units, 12 attention heads, and 270M parameters. It uses a multilingual masked language modeling objective, trained on filtered CommonCrawl data. The model supports PyTorch, TensorFlow, JAX, and ONNX. It achieves state-of-the-art results on cross-lingual benchmarks like XNLI and MLQA.
💡Highlights
- ├─270M parameters, 100+ languages
- ├─Pretrained on 2.5TB CommonCrawl data
- └─Multilingual masked language modeling
🎯For
- ├─NLP researchers
- ├─multilingual AI developers
- └─language technology teams