Update README

README.md

@@ -69,7 +69,7 @@ At inference time, images are resized/rescaled to the same resolution (256x256),
 
 ### Pretraining
 
-The model was trained on a single 8-GPU node for 3 days. Training resolution is 224.
+The model was trained on a single 8-GPU node for 3 days. Training resolution is 224. For all hyperparameters (such as batch size and learning rate) we refer to table 9 of the original paper.
 
 ## Evaluation results
 
@@ -80,22 +80,22 @@ Note that for fine-tuning, the best results are obtained with a higher resolutio
 ### BibTeX entry and citation info
 
 ```bibtex
-@misc{wu2020visual,
-      title={Visual Transformers: Token-based Image Representation and Processing for Computer Vision}, 
-      author={Bichen Wu and Chenfeng Xu and Xiaoliang Dai and Alvin Wan and Peizhao Zhang and Zhicheng Yan and Masayoshi Tomizuka and Joseph Gonzalez and Kurt Keutzer and Peter Vajda},
-      year={2020},
-      eprint={2006.03677},
+@misc{touvron2021training,
+      title={Training data-efficient image transformers & distillation through attention}, 
+      author={Hugo Touvron and Matthieu Cord and Matthijs Douze and Francisco Massa and Alexandre Sablayrolles and Hervé Jégou},
+      year={2021},
+      eprint={2012.12877},
       archivePrefix={arXiv},
       primaryClass={cs.CV}
 }
 ```
 
 ```bibtex
-@misc{touvron2021training,
-      title={Training data-efficient image transformers & distillation through attention}, 
-      author={Hugo Touvron and Matthieu Cord and Matthijs Douze and Francisco Massa and Alexandre Sablayrolles and Hervé Jégou},
-      year={2021},
-      eprint={2012.12877},
+@misc{wu2020visual,
+      title={Visual Transformers: Token-based Image Representation and Processing for Computer Vision}, 
+      author={Bichen Wu and Chenfeng Xu and Xiaoliang Dai and Alvin Wan and Peizhao Zhang and Zhicheng Yan and Masayoshi Tomizuka and Joseph Gonzalez and Kurt Keutzer and Peter Vajda},
+      year={2020},
+      eprint={2006.03677},
       archivePrefix={arXiv},
       primaryClass={cs.CV}
 }