Phi-3 Mini is a powerful 3.8B parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing.
At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models. This model is static, trained on an offline dataset with an October 2023 cutoff date.
Modalities
Context
128K
Released
May 26, 2024
Knowledge Cutoff
Mar 2024
Phi-3 Mini is a powerful 3.8B parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing. At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models.
Phi-3 Mini 128K Instruct has a 128,000 token context window.
Phi 4 and WizardLM-2 8x22B are other text models from Microsoft.
Phi-3 Mini 128K Instruct was released on May 26, 2024. Its knowledge cutoff is March 31, 2024.
Token volume and request traffic to this model over time.