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 • 66.7k • • 110
jhu-clsp/mmBERT-base
Fill-Mask • Updated • 336k • • 284
jhu-clsp/mmBERT-checkpoints
Updated • 6
jhu-clsp/ettin-decoder-1b
Fill-Mask • Updated • 1.06k • 5
jhu-clsp/ettin-decoder-32m
Text Generation • Updated • 1.04k
jhu-clsp/ettin-encoder-1b
Feature Extraction • Updated • 26.1k • 33
jhu-clsp/ettin-encoder-68m
Fill-Mask • Updated • 6.44k • • 10
jhu-clsp/ettin-dec-from-enc-32m
Text Generation • Updated • 23
jhu-clsp/ettin-encoder-150m
Fill-Mask • Updated • 12.7k • • 18
jhu-clsp/ettin-decoder-400m
Text Generation • Updated • 1.12k • 4
datasets 43
jhu-clsp/hohw
Viewer • Updated • 922 • 54
jhu-clsp/narrative-bench
Viewer • Updated • 78.6k • 371 • 2
jhu-clsp/cc-temporal-65M
Viewer • Updated • 61.6M • 100
jhu-clsp/SciTaRC
Viewer • Updated • 371 • 78 • 1
jhu-clsp/ManyIH-Bench
Preview • Updated • 91 • 3
jhu-clsp/robust04-instructions
Viewer • Updated • 136k • 323 • 2
jhu-clsp/core17-instructions
Viewer • Updated • 49.4k • 369 • 2
jhu-clsp/news21-instructions
Viewer • Updated • 71.5k • 294 • 1
jhu-clsp/megawika-2
Updated • 5.21k • 7
jhu-clsp/mmBERT-decay-data
Updated • 2.01k • 7