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
View all 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 • 101k • • 108
jhu-clsp/mmBERT-base
Fill-Mask • Updated • 443k • • 269
jhu-clsp/mmBERT-checkpoints
Updated • 5
jhu-clsp/ettin-decoder-1b
Fill-Mask • Updated • 633 • 5
jhu-clsp/ettin-decoder-32m
Text Generation • Updated • 1k
jhu-clsp/ettin-encoder-1b
Feature Extraction • Updated • 21.6k • • 33
jhu-clsp/ettin-encoder-68m
Fill-Mask • Updated • 16.9k • • 8
jhu-clsp/ettin-dec-from-enc-32m
Text Generation • Updated • 68
jhu-clsp/ettin-encoder-150m
Fill-Mask • Updated • 24.1k • • 17
jhu-clsp/ettin-decoder-400m
Text Generation • Updated • 1.65k • 4
datasets 41
jhu-clsp/cc-temporal-65M
Viewer • Updated • 61.6M • 2
jhu-clsp/SciTaRC
Viewer • Updated • 371 • 75 • 1
jhu-clsp/ManyIH-Bench
Preview • Updated • 304 • 3
jhu-clsp/robust04-instructions
Viewer • Updated • 136k • 540 • 2
jhu-clsp/core17-instructions
Viewer • Updated • 49.4k • 496 • 2
jhu-clsp/news21-instructions
Viewer • Updated • 71.5k • 478 • 1
jhu-clsp/megawika-2
Updated • 9.37k • 6
jhu-clsp/mmBERT-decay-data
Updated • 22.5k • 6
jhu-clsp/mmBERT-midtraining-data
Updated • 61k • 1
jhu-clsp/ettin-pretraining-data
Updated • 28k • 10