mgoin chrisxx commited on
Commit
df8624b
1 Parent(s): 607f078

Update README.md (#4)

Browse files

- Update README.md (51d9443dfee220c6585e55909fc9fc179b0ed8de)


Co-authored-by: Chris Wendler <[email protected]>

Files changed (1) hide show
  1. README.md +5 -3
README.md CHANGED
@@ -15,12 +15,14 @@ On an Intel avx512 CPU machine with 64 cores and VNNI support, this model achiev
15
  and **2.84x** speedup for visual inputs as compared to the full-precision model. With a batch size of 64,
16
  the throughput was measured as **1230 items/sec** for images and **2009 items/sec** for text.
17
 
18
- This model and the example pipeline were created by Eugenia Iofinova, Michael Goin, Chris Wendler, and Dan Alistarh.
19
- Special thanks to Abhinav Agarwalla and Alexandre Marques for technical support with parts of the project.
20
-
21
  Notebook for basic usage: [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1ZvU9ZSHJKSeJyH5bgxo_A-GSVIUcSt2E?usp=sharing)
22
  Notebook for Imagenette evaluation: [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1-Duq0YNtjzOnmuXCYo-5DDiOzeCItXpN?usp=sharing)
23
 
 
 
 
 
 
24
  ## Setup for usage
25
  First, install DeepSparse with extensions for CLIP:
26
  ```
 
15
  and **2.84x** speedup for visual inputs as compared to the full-precision model. With a batch size of 64,
16
  the throughput was measured as **1230 items/sec** for images and **2009 items/sec** for text.
17
 
 
 
 
18
  Notebook for basic usage: [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1ZvU9ZSHJKSeJyH5bgxo_A-GSVIUcSt2E?usp=sharing)
19
  Notebook for Imagenette evaluation: [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1-Duq0YNtjzOnmuXCYo-5DDiOzeCItXpN?usp=sharing)
20
 
21
+ ## The team
22
+
23
+ This model and the example pipeline were created by Eugenia Iofinova, Michael Goin, Chris Wendler, and Dan Alistarh.
24
+ Special thanks to Abhinav Agarwalla and Alexandre Marques for technical support with parts of the project.
25
+
26
  ## Setup for usage
27
  First, install DeepSparse with extensions for CLIP:
28
  ```