:beers: cheers

README.md

@@ -0,0 +1,27 @@
+---
+tags:
+- image-classification
+- pytorch
+license: apache-2.0
+datasets:
+- cifar10
+metrics:
+- accuracy
+thumbnail: https://avatars3.githubusercontent.com/u/32437151?s=460&u=4ec59abc8d21d5feea3dab323d23a5860e6996a4&v=4
+---
+
+# Vision Transformer Fine Tuned on CIFAR10
+
+Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) and **fine-tuned on CIFAR10** at resolution 224x224.
+
+## Model description
+
+The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. 
+Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder.
+Note that this model does not provide any fine-tuned heads, as these were zero'd by Google researchers. However, the model does include the pre-trained pooler, which can be used for downstream tasks (such as image classification).
+
+By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre-trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image.
+
+## Training procedure
+
+The training procedure can be seen in [my github repo](https://github.com/nateraw/huggingface-vit-finetune)