Phi-2: The surprising power of small language models

Phi-2 is now accessible on the Azure model catalog. Its compact size and new innovations in model scaling and training data curation make it ideal for exploration around mechanistic interpretability, safety improvements, and fine-tuning experimentation on a variety of tasks.

The post Phi-2: The surprising power of small language models appeared first on Microsoft Research.

azure curation data data curation experimentation exploration fine-tuning improvements innovations interpretability language language models model scaling phi power research blog safety scaling small small language models tasks training training data