Add support of Microsoft Phi-2 model to DeepSpeed-FastGen (#4812)
This PR adds support for Microsoft Phi-2 model.
HF output with prompt "DeepSpeed is":
```
a company that helps make videos and movies look really good. They have a special way of making videos that makes them look like they were made in a movie theater. This is called "4K Ultra HD" and it makes the videos look very clear and detailed. DeepSpeed also has a special way of making videos that makes them look like they were made in a movie theater. This is called "4K Ultra HD" and it makes the videos look very clear and detailed. DeepSpeed also has a special way of making videos that makes them look like they were made in a movie theater. This is called "4K Ultra HD"
```
DeepSpeed-FastGen output with prompt "DeepSpeed is":
```
a company that helps make videos and movies look really good. They have a special way of making videos that makes them look like they were made in a movie theater. This is called "4K Ultra HD" and it makes the videos look very clear and detailed. DeepSpeed also has a special way of making videos that makes them look like they were made in a movie theater. This is called "4K Ultra HD" and it makes the videos look very clear and detailed. DeepSpeed also has a special way of making videos that makes them look like they were made in a movie theater. This is called "4K Ultra HD"
```
---------
Co-authored-by: Connor Holmes <connorholmes@microsoft.com>
Co-authored-by: Michael Wyatt <michaelwyatt@microsoft.com>