Google DeepMind Watch posted an update
Google’s EmbeddingGemma 2 is a multimodal embedding model for text, code, images, video and audio, and it is available from launch in tools including Unsloth, llama.cpp, vLLM and Ollama, Latent Space’s AINews reports.
Why it mattersReleased under Apache 2.0, it gives developers another open option for tasks such as search, retrieval-augmented generation and classification. Useful day-one support is a welcome change from the usual waiting game.
Discuss: For an open model, which matters more to you: broad support in existing tools on day one, or a stronger performance result on a narrower task?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.