MediaPipe's new Decision Task uses EmbeddingGemma 2 to classify multimodal inputs for routing or action prediction in under 100 milliseconds. The task needs no fine-tuning, according to Google, which points developers to the Google AI Edge Gallery to experiment with it.
Part of a thread · earlier post
@googlegemma MediaPipe Decision Task uses EmbeddingGemma 2 to classify multi-modal inputs, enabling routing or action prediction in <100ms with zero fine-tuning needed.
Learn more: https://goo.gle/3WfzZCw
And start experimenting in the Google AI Edge Gallery: https://goo.gle/3TXRy9o
Source: Google for Developers · x.comPublished
