Модели

Microsoft's Phi-4 Mini model with 3.8B parameters providing lightweight yet capable language understanding and code generation, optimized for resource-constrained deployments with a large 128K context window.

Microsoft's Phi-4 model with 14B parameters excelling at reasoning and code generation tasks, delivering strong performance relative to its compact size with efficient inference characteristics.

OpenAI's Whisper automatic speech recognition model capable of multilingual audio transcription and translation, trained on a large dataset of diverse audio for robust real-world performance.