shawntan

icentia-ecg

Working on Icentia ECG data.

minicraft-android

Android port of minicraft

neural-turing-machines

Attempt at implementing system described in "Neural Turing Machines." by Graves, Alex, Greg Wayne, and Ivo Danihelka. (http://arxiv.org/abs/1410.5401)

python-crf

Python implementation of linear-chain conditional random fields.

rtdp

Code for the paper titled "Recursive Top-Down Production for Sentence Generation with Latent Trees"

scattermoe

Triton-based implementation of Sparse Mixture of Experts.

stickbreaking-attention

Stick-breaking attention

SUT

Repository for Sparse Universal Transformers

theano-ctc

CTC implementation in Theano.

theano_toolkit

Collection of useful, re-used routines.

shawntan/scattermoe

Triton-based implementation of Sparse Mixture of Experts.

shawntan/stickbreaking-attention

Stick-breaking attention

shawntan/icentia-ecg

Working on Icentia ECG data.

shawntan/SUT

Repository for Sparse Universal Transformers

shawntan/chicken-rice-nn

Miscellaneous code for doing NLP with Theano

shawntan/theano-kaldi

Bunch of scripts for working with Kaldi.

shawntan/stack-binary-recursive-nn

Parallelised implementation of Recursive Neural Networks for binary trees in PyTorch

shawntan/lost-in-the-middle

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

shawntan/rtdp

Code for the paper titled "Recursive Top-Down Production for Sentence Generation with Latent Trees"

shawntan/awd-lstm-lm

LSTM and QRNN Language Model Toolkit for PyTorch

shawntan/cv

CV, typesetted in Helvetica Neue, using XeTeX, TikZ and Biblatex

shawntan/dolomite-engine

pretraining/finetuning codebase for LLMs

shawntan/kernel-hyperdrive

A bunch of kernels that might make stuff slower 😉

shawntan/triton-radix-sort

shawntan/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

shawntan/CategoricalNF

Official repository for "Categorical Normalizing Flows via Continuous Transformations"

shawntan/compound-pcfg

shawntan/IFT6135H19_assignment

shawntan/lexical

Lexicon Learning for Few-Shot Neural Sequence Modeling

shawntan/life

Life - a timeline of important events in my life

shawntan/lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

shawntan/NAF

Experiments for the Neural Autoregressive Flows paper

shawntan/nanotron

Minimalistic large language model 3D-parallelism training

shawntan/neural_networks_chomsky_hierarchy

shawntan/text

Data loaders and abstractions for text and NLP

shawntan/transformer-xl

shawntan/transformer_latent_diffusion

Text to Image Latent Diffusion using a Transformer core

shawntan/transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

shawntan/Triton-Puzzles

shawntan/zoology

Understand and test language model architectures on synthetic tasks.