✨ Microsoft debuts Phi-4, a new generative AI model, in research preview Microsoft has introduced Phi-4, the latest model in its Phi family of generative AI, claiming improvements particularly in math problem solving due to enhanced training data quality. Currently, Phi-4 is available in limited access on the Azure AI Foundry platform for research purposes only. This model features 14 billion parameters, competing with other small models like GPT-4o mini and Gemini 2.0 Flash. The performance boost is attributed to the use of high-quality synthetic datasets and human-generated content, along with unspecified post-training enhancements. Many AI labs are exploring innovations in synthetic data and post-training techniques. Phi-4 is notable as the first model launched after the departure of Sébastien Bubeck, a key figure in its development, who left Microsoft for OpenAI in October. 💬 Source 📌 Powered by V3V Ventures