mmBERT: a modern multilingual encoder Collection mmBERT is trained on 3T tokens from over 1800 languages, showing SoTA scores on benchmarks and exceptional low-resource performance • 16 items • Updated 4 days ago • 28
ContextualAI/ctxl-rerank-v2-instruct-multilingual-6b-nvfp4 Text Ranking • 4B • Updated 10 days ago • 75 • 2
Contextual AI Reranker v2 Collection Family of instruction-following multilingual rerankers on the cost/performance Pareto frontier across public and customer benchmarks • 6 items • Updated 19 days ago • 8