AI updates
EmbeddingGemma: a 308M multilingual embedding model for devices
Google released EmbeddingGemma, a 308M-parameter embedding model with a 2K context supporting 100+ languages; at release it was the top text-only multilingual model under 500M on MTEB.
- Small enough for phones, so retrieval for RAG can happen on-device.
- At release it ranked highest among text-only multilingual embedding models under 500M parameters on MTEB.