Shawn Tan's repositories
scattermoe
Triton-based implementation of Sparse Mixture of Experts.
nanotron
Minimalistic large language model 3D-parallelism training
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
zoology
Understand and test language model architectures on synthetic tasks.
transformer_latent_diffusion
Text to Image Latent Diffusion using a Transformer core
lost-in-the-middle
Code and data for "Lost in the Middle: How Language Models Use Long Contexts"
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
icentia-ecg
Working on Icentia ECG data.
CategoricalNF
Official repository for "Categorical Normalizing Flows via Continuous Transformations"
lexical
Lexicon Learning for Few-Shot Neural Sequence Modeling
stack-binary-recursive-nn
Parallelised implementation of Recursive Neural Networks for binary trees in PyTorch
chicken-rice-nn
Miscellaneous code for doing NLP with Theano
text
Data loaders and abstractions for text and NLP
awd-lstm-lm
LSTM and QRNN Language Model Toolkit for PyTorch
NAF
Experiments for the Neural Autoregressive Flows paper
life
Life - a timeline of important events in my life
theano-kaldi
Bunch of scripts for working with Kaldi.
Theano
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.
Lasagne
Lightweight library to build and train neural networks in Theano
theano_toolkit
Collection of useful, re-used routines.
stick-breaking-vae
Infinite MIxture Models with VAEs