Model Terminal

XLM-RoBERTa Base

XLM-RoBERTa Base is a multilingual transformer encoder pretrained on 2.5TB of filtered CommonCrawl text across 100 languages using masked language modeling. It is designed for fine-tuning on cross-lingual understanding tasks such as text classification, named-entity recognition, and question answering. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Peer value bars

Identity

Developer
Hugging Face
Openness
Modalities
Fill-mask
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed