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
Genomic Next-Token Predictors are In-Context Learners
Controlled Generation for Private Synthetic Text
models 53
jhu-clsp/mmBERT-small
Fill-Mask • Updated
• 14.7k • • 62
jhu-clsp/mmBERT-base
Fill-Mask • Updated
• 252k • • 190
jhu-clsp/mmBERT-checkpoints
Updated
• 4
jhu-clsp/ettin-decoder-1b
Fill-Mask • Updated
• 120 • 5
jhu-clsp/ettin-decoder-32m
Text Generation • Updated
• 192
jhu-clsp/ettin-encoder-1b
Feature Extraction • Updated
• 234 • 21
jhu-clsp/ettin-encoder-68m
Fill-Mask • Updated
• 608 • 3
jhu-clsp/ettin-dec-from-enc-32m
Text Generation • Updated
• 3
jhu-clsp/ettin-encoder-150m
Fill-Mask • Updated
• 18.2k • • 8
jhu-clsp/ettin-decoder-400m
Text Generation • Updated
• 77 • 4
datasets 38
jhu-clsp/mmBERT-decay-data
Updated
• 12.4k • 4
jhu-clsp/mmBERT-midtraining-data
Updated
• 12k • 1
jhu-clsp/megawika-2
Updated
• 187 • 2
jhu-clsp/ettin-pretraining-data
Updated
• 10k • 8
jhu-clsp/ettin-decay-data
Updated
• 2.5k • 1
jhu-clsp/astro-llms-benchmark-dataset
Viewer
• Updated
• 40 • 93
jhu-clsp/astro-llms-full-query-data
Viewer
• Updated
• 368 • 80
jhu-clsp/ettin-extension-data
Updated
• 1.96k
jhu-clsp/ettin-data-order
Viewer
• Updated
• 3B • 2 • 1
jhu-clsp/rank1-R1-MSMARCO
Viewer
• Updated
• 635k • 28 • 2