mmBERT: a modern multilingual encoder mmBERT is trained on 3T tokens from over 1800 languages, showing SoTA scores on benchmarks and exceptional low-resource performance jhu-clsp/mmBERT-base Fill-Mask • Updated 9 days ago • 27.7k • • 125 jhu-clsp/mmBERT-small Fill-Mask • Updated 9 days ago • 4.3k • • 40 jhu-clsp/mmBERT-checkpoints Updated 13 days ago • 2 jhu-clsp/mmBERT-pretrain-p1-fineweb2-langs Updated 8 days ago • 3.56k • 2
rank1 rank1 is the first test-time compute reasoning model in IR Sleeping 3 3 Rank1 Demo -- Test Time Compute in Reranking 🏆 Determine if a passage is relevant to a query jhu-clsp/rank1-0.5b Text Ranking • 0.6B • Updated Apr 8 • 18 • 1 jhu-clsp/rank1-1.5b Text Ranking • 2B • Updated Apr 8 • 248 jhu-clsp/rank1-3b Text Ranking • 3B • Updated Apr 8 • 158
Sleeping 3 3 Rank1 Demo -- Test Time Compute in Reranking 🏆 Determine if a passage is relevant to a query
Encoders vs Decoders: the Ettin Suite A collection of SOTA, open-data, paired encoder-only and decoder only models ranging from 17M params to 1B. See the paper at https://arxiv.org/abs/250 Seq vs Seq: An Open Suite of Paired Encoders and Decoders Paper • 2507.11412 • Published Jul 15 • 25 jhu-clsp/ettin-encoder-17m Fill-Mask • Updated Jul 16 • 3.39k • 7 jhu-clsp/ettin-encoder-32m Feature Extraction • Updated Jul 18 • 1.5k • • 3 jhu-clsp/ettin-encoder-68m Fill-Mask • Updated Jul 18 • 781 • • 2
mmBERT: a modern multilingual encoder mmBERT is trained on 3T tokens from over 1800 languages, showing SoTA scores on benchmarks and exceptional low-resource performance jhu-clsp/mmBERT-base Fill-Mask • Updated 9 days ago • 27.7k • • 125 jhu-clsp/mmBERT-small Fill-Mask • Updated 9 days ago • 4.3k • • 40 jhu-clsp/mmBERT-checkpoints Updated 13 days ago • 2 jhu-clsp/mmBERT-pretrain-p1-fineweb2-langs Updated 8 days ago • 3.56k • 2
Encoders vs Decoders: the Ettin Suite A collection of SOTA, open-data, paired encoder-only and decoder only models ranging from 17M params to 1B. See the paper at https://arxiv.org/abs/250 Seq vs Seq: An Open Suite of Paired Encoders and Decoders Paper • 2507.11412 • Published Jul 15 • 25 jhu-clsp/ettin-encoder-17m Fill-Mask • Updated Jul 16 • 3.39k • 7 jhu-clsp/ettin-encoder-32m Feature Extraction • Updated Jul 18 • 1.5k • • 3 jhu-clsp/ettin-encoder-68m Fill-Mask • Updated Jul 18 • 781 • • 2
rank1 rank1 is the first test-time compute reasoning model in IR Sleeping 3 3 Rank1 Demo -- Test Time Compute in Reranking 🏆 Determine if a passage is relevant to a query jhu-clsp/rank1-0.5b Text Ranking • 0.6B • Updated Apr 8 • 18 • 1 jhu-clsp/rank1-1.5b Text Ranking • 2B • Updated Apr 8 • 248 jhu-clsp/rank1-3b Text Ranking • 3B • Updated Apr 8 • 158
Sleeping 3 3 Rank1 Demo -- Test Time Compute in Reranking 🏆 Determine if a passage is relevant to a query