Update README.md
Browse files
README.md
CHANGED
@@ -181,8 +181,8 @@ The model uses the same sentencepiece-based tokenizer as [japanese-gpt-neox-3.6b
|
|
181 |
title = {{DeepSpeed-Inference}: enabling efficient inference of transformer models at unprecedented scale},
|
182 |
author = {Aminabadi, Reza Yazdani and Rajbhandari, Samyam and Awan, Ammar Ahmad and Li, Cheng and Li, Du and Zheng, Elton and Ruwase, Olatunji and Smith, Shaden and Zhang, Minjia and Rasley, Jeff and others},
|
183 |
booktitle = {SC22: International Conference for High Performance Computing, Networking, Storage and Analysis},
|
184 |
-
pages = {1--15},
|
185 |
year = {2022},
|
|
|
186 |
doi = {10.1109/SC41404.2022.00051}
|
187 |
}
|
188 |
```
|
|
|
181 |
title = {{DeepSpeed-Inference}: enabling efficient inference of transformer models at unprecedented scale},
|
182 |
author = {Aminabadi, Reza Yazdani and Rajbhandari, Samyam and Awan, Ammar Ahmad and Li, Cheng and Li, Du and Zheng, Elton and Ruwase, Olatunji and Smith, Shaden and Zhang, Minjia and Rasley, Jeff and others},
|
183 |
booktitle = {SC22: International Conference for High Performance Computing, Networking, Storage and Analysis},
|
|
|
184 |
year = {2022},
|
185 |
+
pages = {1--15},
|
186 |
doi = {10.1109/SC41404.2022.00051}
|
187 |
}
|
188 |
```
|