Model Summary

Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.

Our model hasn’t been fine-tuned through reinforcement learning from human feedback. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.

Intended Uses

Phi-2 is intended for research purposes only. Given the nature of the training data, the Phi-2 model is best suited for prompts using the QA format, the chat format, and the code format.

Notes:

• Phi-2 is intended for research purposes. The model-generated text/code should be treated as a starting point rather than a definitive solution for potential use cases. Users should be cautious when employing these models in their applications.
• Direct adoption for production tasks is out of the scope of this research project. As a result, the Phi-2 model has not been tested to ensure that it performs adequately for any production-level application. Please refer to the limitation sections of this document for more details.
• If you are using transformers>=4.36.0, always load the model with trust_remote_code=True to prevent side-effects.

For more information, visit the Huggingface page