Phi-2: A Dataset for Language Model Evaluation

The Phi-2 dataset is a collection of language models used to evaluate the performance of language models.

Data and Resources

Cite this as

Mojan Javaheripi, S´ebastien Bubeck (2024). Dataset: Phi-2: A Dataset for Language Model Evaluation. https://doi.org/10.57702/3plsj7yx

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2309.02632
Author Mojan Javaheripi
More Authors
S´ebastien Bubeck
Homepage https://www.microsoft.com/en-us/research/blog/phi-2-the-surprising-power-of-small-language-models/