Microsoft Phi-3 Mini Launched: Tech Giant Says Its New Cost-Effective ‘Phi-3 Mini’ Small Language Models Have Big Potentials; Check Parameters and Key Details

Microsoft launched Phi-3 Mini, a family of small language models (SLMs) that could outperform large language models (LLMs) on different benchmarks. Microsoft Phi-3 SLMs would be a gold standard for solving many complex tasks, said the tech giant in its official announcement. The Microsoft Phi-3 family of open models is available in two contexts - Phi-3 Mini 4K tokens and Phi-3 Mini 128K tokens. Microsoft said its Phi-3 3.8B language model is available on Microsoft Azure AI Studio, Hugging Face, and Ollama for developers to run locally on laptops. According to the post by Microsoft, the Phi-3 Mini model had been optimised for ONNX Runtime with support for Windows DirectML and the support of a cross-platform system across GPU, CPU, and mobile software. Microsoft Phi-3 Mini would be available as an NVIDIA NIM microservice with a standard API interface and would also be optimised for NVIDIA GPUs. Microsoft Phi-3 Mini measured 3.8 billion parameters and was trained on a smaller dataset than LLMs like ChatGPT. TikTok Ban: List of Countries That Banned Chinese Short-Video Making App Over Cybersecurity, Misinformation and Privacy Concerns.

Microsoft Phi-3 Mini 3.8 Billion Language Model Launched; Check Official Post: 

We're excited to announce the launch of Phi-3, a groundbreaking family of small language models that outperform larger models on a range of benchmarks. Learn how these small language models trained on high-quality data are doing more with less: https://t.co/dFfyktuEUL

— Microsoft (@Microsoft) April 23, 2024

(The above story first appeared on LatestLY on Apr 24, 2024 02:06 PM IST. For more news and updates on politics, world, sports, entertainment and lifestyle, log on to our website latestly.com).