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 • 68.8k • • 109
jhu-clsp/mmBERT-base
Fill-Mask • Updated • 360k • • 281
jhu-clsp/mmBERT-checkpoints
Updated • 6
jhu-clsp/ettin-decoder-1b
Fill-Mask • Updated • 1.16k • 5
jhu-clsp/ettin-decoder-32m
Text Generation • Updated • 1.06k
jhu-clsp/ettin-encoder-1b
Feature Extraction • Updated • 27.2k • 33
jhu-clsp/ettin-encoder-68m
Fill-Mask • Updated • 7.15k • • 9
jhu-clsp/ettin-dec-from-enc-32m
Text Generation • Updated • 28
jhu-clsp/ettin-encoder-150m
Fill-Mask • Updated • 14.5k • • 18
jhu-clsp/ettin-decoder-400m
Text Generation • Updated • 1.19k • 4
datasets 42
jhu-clsp/narrative-bench
Viewer • Updated • 78.6k • 72
jhu-clsp/cc-temporal-65M
Viewer • Updated • 61.6M • 69
jhu-clsp/SciTaRC
Viewer • Updated • 371 • 87 • 1
jhu-clsp/ManyIH-Bench
Preview • Updated • 92 • 3
jhu-clsp/robust04-instructions
Viewer • Updated • 136k • 313 • 2
jhu-clsp/core17-instructions
Viewer • Updated • 49.4k • 346 • 2
jhu-clsp/news21-instructions
Viewer • Updated • 71.5k • 270 • 1
jhu-clsp/megawika-2
Updated • 5.89k • 7
jhu-clsp/mmBERT-decay-data
Updated • 3.13k • 6
jhu-clsp/mmBERT-midtraining-data
Updated • 54.8k • 6