Jason Wei's repositories
evals
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.
BIG-bench
Beyond the Imitation Game collaborative benchmark for enormous language models
bash_profile
general bash profile commands
COVID-Q
COVID-19 Question Dataset from the paper "What Are People Asking About COVID-19? A Question Classification Dataset"
awd-lstm-lm
LSTM and QRNN Language Model Toolkit for PyTorch
uda
Unsupervised Data Augmentation (UDA)
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
adaptable-image-classification
Readable and adaptable image classification with ResNet
fair_self_supervision_benchmark
Scaling and Benchmarking Self-Supervised Visual Representation Learning
GNNs-for-NLP
Graph Neural Networks for Natural Language Processing tutorial at EMNLP 2019
text_discovery_nn
Discovering notable events in historical texts with deep learning.
campus-gan
Generating synthetic images of colleges campuses with DCGAN.
Chatbot_hred
It is a hred sequence 2 sequence chart bot model
CycleGAN-tensorflow
Tensorflow implementation for learning an image-to-image translation without input-output pairs. https://arxiv.org/pdf/1703.10593.pdf