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
•
6.29k
•
•
56
jhu-clsp/mmBERT-base
Fill-Mask
•
Updated
•
362k
•
•
166
jhu-clsp/mmBERT-checkpoints
Updated
•
3
jhu-clsp/ettin-decoder-1b
Fill-Mask
•
Updated
•
120
•
4
jhu-clsp/ettin-decoder-32m
Text Generation
•
Updated
•
55
jhu-clsp/ettin-encoder-1b
Feature Extraction
•
Updated
•
4.89k
•
•
21
jhu-clsp/ettin-encoder-68m
Fill-Mask
•
Updated
•
799
•
•
3
jhu-clsp/ettin-dec-from-enc-32m
Text Generation
•
Updated
•
16
jhu-clsp/ettin-encoder-150m
Fill-Mask
•
Updated
•
17.2k
•
•
8
jhu-clsp/ettin-decoder-400m
Text Generation
•
Updated
•
34
•
2
datasets
38
jhu-clsp/mmBERT-midtraining-data
Updated
•
44.2k
•
1
jhu-clsp/mmBERT-decay-data
Updated
•
17k
•
3
jhu-clsp/megawika-2
Updated
•
315
•
2
jhu-clsp/ettin-pretraining-data
Updated
•
8.31k
•
7
jhu-clsp/ettin-decay-data
Updated
•
1.73k
jhu-clsp/astro-llms-benchmark-dataset
Viewer
•
Updated
•
40
•
30
jhu-clsp/astro-llms-full-query-data
Viewer
•
Updated
•
368
•
46
jhu-clsp/ettin-extension-data
Updated
•
256
jhu-clsp/ettin-data-order
Viewer
•
Updated
•
3B
•
9
•
1
jhu-clsp/rank1-R1-MSMARCO
Viewer
•
Updated
•
635k
•
64
•
2