mmBERT: a modern multilingual encoder
Collection
mmBERT is trained on 3T tokens from over 1800 languages, showing SoTA scores on benchmarks and exceptional low-resource performance • 17 items • Updated • 54
Manuel Jaiczay
Jaizo
·
AI & ML interests
None yet
Recent Activity
liked a model about 2 months ago
k2-fsa/OmniVoice liked a model about 2 months ago
nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-NVFP4 liked a model 2 months ago
microsoft/Phi-4-multimodal-instructOrganizations
None yet
upvoted a collection 10 months ago