🐠
Fraser Greenlee
Fraser
Homepage
Research interests
Transformers for code.
Organizations
spaces 1
models 4
datasets 7
Fraser/mnist-text-default
21MNIST dataset adapted to a text-based representation. This allows testing interpolation quality for Transformer-VAEs. System is heavily inspired by Matthew Rayfield's work https://youtu.be/Z9K3cwSL6uM Works by quantising each MNIST pixel into one of 64 characters. Every sample has an up & down version to encourage the model to learn rotation ...
Fraser/mnist-text-no-spaces
21MNIST dataset adapted to a text-based representation. This allows testing interpolation quality for Transformer-VAEs. System is heavily inspired by Matthew Rayfield's work https://youtu.be/Z9K3cwSL6uM Works by quantising each MNIST pixel into one of 64 characters. Every sample has an up & down version to encourage the model to learn rotation ...
Fraser/mnist-text-small
23MNIST dataset adapted to a text-based representation. *Modified images to be ~1/4 the original area.* Done by taking a max pool. This allows testing interpolation quality for Transformer-VAEs. System is heavily inspired by Matthew Rayfield's work https://youtu.be/Z9K3cwSL6uM Works by quantising each MNIST pixel into one of 64 characters. Eve...
Fraser/news-category-dataset
55Copy of [Kaggle dataset](https://www.kaggle.com/rmisra/news-category-dataset), adding to Huggingface for ease of use. Description from Kaggle: Context This dataset contains around 200k news headlines from the year 2012 to 2018 obtained from HuffPost. The model trained on this dataset could be used to identify tags for untracked news articles ...
Fraser/python-lines
177Dataset of single lines of Python code taken from the [CodeSearchNet](https://github.com/github/CodeSearchNet) dataset. Context This dataset allows checking the validity of Variational-Autoencoder latent spaces by testing what percentage of random/intermediate latent points can be greedily decoded into valid Python code. Content Each row has...
Fraser/short-jokes
15Copy of [Kaggle dataset](https://www.kaggle.com/abhinavmoudgil95/short-jokes), adding to Huggingface for ease of use. Description from Kaggle: Context Generating humor is a complex task in the domain of machine learning, and it requires the models to understand the deep semantic meaning of a joke in order to generate new ones. Such problems, ...