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 • 16 items • Updated 15 days ago • 37
view article Article mmBERT: ModernBERT goes Multilingual By orionweller and 5 others • 15 days ago • 93
google/embeddinggemma-300m-qat-q4_0-unquantized Sentence Similarity • 0.3B • Updated 20 days ago • 4.41k • • 30
FastVLM Collection Efficient Vision Encoding for Vision Language Models • 9 items • Updated 21 days ago • 99