Menu

#EmbeddinggEmma

3 posts

Feed·
3 of 3 posts
EmbeddingGemma 2: Google's open multimodal embedding model maps text, code, images, video and audio into one space
📰
0Read More

EmbeddingGemma 2: Google's open multimodal embedding model maps text, code, images, video and audio into one space

DEV Community: ai·IA Compa·about 8 hours ago
#y3dOIQXW
#devtoai#devto#dev#embeddinggemma#embedding

Google DeepMind has released EmbeddingGemma 2, a small open multimodal embedding model that turns...

15s
0Read More

[R] Taking EmbeddingGemma-2 (577M) from Rank #26 to #1 on the MAEB audio benchmark by filling its 256d null space with PCA-reduced intermediate Conformer layers (zero training) [R]

Model & weights: BrunoHays/embeddinggemma-2-nullspace-audio I wanted to share an experiment on google/embeddinggemma-2 (577M) for MAEB, the 30-task audio benchmark on the MTEB leaderboard.…

15s