noahtren
/

phi-2

@@ -10,6 +10,9 @@ tags:
 - code
 ---
 ## Model Summary
 Phi-2 is a Transformer with **2.7 billion** parameters. It was trained using the same data sources as [Phi-1.5](https://huggingface.co/microsoft/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.

 - code
 ---
+DISCLAIMER: I don't own the weights to this model, this is a property of Microsoft and taken from their official repository : microsoft/phi-2. The only modification to their original implementation is to return `hidden_states`, to use in downstream tasks besides autoregressive language modeling.
 ## Model Summary
 Phi-2 is a Transformer with **2.7 billion** parameters. It was trained using the same data sources as [Phi-1.5](https://huggingface.co/microsoft/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.