-
Microsoft Phi-4 Multi-Modal and Mini-Models Online, Speech Vision Text All-in-One
February 27, 2011 - Microsoft released Phi-4 in December 2024, a small language model (SLM) that excels in its class. Today, Microsoft extends the Phi-4 family with two new models: Phi-4-multimodal and Phi-4-mini. The Phi-4 multimodal model is Microsoft's first unified architecture multimodal language model that integrates speech, vision, and text processing with 5.6 billion parameters. In multiple benchmarks...- 1.8k