Google releases compact multimodal EmbeddingGemma 2 model
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
Google released EmbeddingGemma 2, a 740-million-parameter open model for text, images, video, audio and code. It uses about 191 MB of RAM, processes browser queries in 20–70 milliseconds and, Google says, beats rivals twice its size. Its weights are available on Hugging Face and Kaggle.
Continue in the app — vote & join in ➔Source: The Decoder (AI) · via ahirlevel.hu