mmBERT is trained on 3T tokens from over 1800 languages, showing SoTA scores on benchmarks and exceptional low-resource performance
AI & ML interests
None defined yet.
Recent Activity
Papers
Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification
Convergent Emergence of In-Context Learning Across Modalities
models 53
jhu-clsp/mmBERT-small
Fill-Mask • Updated • 94.5k • • 107
jhu-clsp/mmBERT-base
Fill-Mask • Updated • 391k • • 260
jhu-clsp/mmBERT-checkpoints
Updated • 4
jhu-clsp/ettin-decoder-1b
Fill-Mask • Updated • 356 • 5
jhu-clsp/ettin-decoder-32m
Text Generation • Updated • 782
jhu-clsp/ettin-encoder-1b
Feature Extraction • Updated • 42.4k • 29
jhu-clsp/ettin-encoder-68m
Fill-Mask • Updated • 15.1k • • 5
jhu-clsp/ettin-dec-from-enc-32m
Text Generation • Updated • 60
jhu-clsp/ettin-encoder-150m
Fill-Mask • Updated • 26.7k • • 14
jhu-clsp/ettin-decoder-400m
Text Generation • Updated • 1.8k • 4
datasets 41
jhu-clsp/cc-temporal-65M
Viewer • Updated • 61.6M • 26
jhu-clsp/SciTaRC
Viewer • Updated • 371 • 68 • 1
jhu-clsp/ManyIH-Bench
Preview • Updated • 393 • 3
jhu-clsp/robust04-instructions
Viewer • Updated • 136k • 412 • 2
jhu-clsp/core17-instructions
Viewer • Updated • 49.4k • 453 • 2
jhu-clsp/news21-instructions
Viewer • Updated • 71.5k • 394 • 1
jhu-clsp/megawika-2
Updated • 2.5k • 6
jhu-clsp/mmBERT-decay-data
Updated • 21.5k • 6
jhu-clsp/mmBERT-midtraining-data
Updated • 7.65k • 1
jhu-clsp/ettin-pretraining-data
Updated • 59.2k • 10