Sam Havens's repositories
fastT5
⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
image.bert.token.tagger
base image for bert token tagger
bert-syntax
Assessing syntactic abilities of BERT
Character-Level-Language-Modeling-with-Deeper-Self-Attention-pytorch
Reproducing Character-Level-Language-Modeling with Deeper Self-Attention in PyTorch
chime
COVID-19 Hospital Impact Model for Epidemics
errant
ERRor ANnotation Toolkit: Automatically extract and classify grammatical errors in parallel original and corrected sentences.
grpci_slow
Demonstrate slow installation of grpcio
hypothesis-auto
An extensions for Hypothesis that provides fully automatic testing for type hinted functions
NeMo
NeMo: a toolkit for conversational AI
neutralizing-bias
Code and data for the paper, "Automatically Neutralizing Subjective Bias in Text"
picard
Watchlist in preparation for the new series, Picard.
poetry-publish
An action to build and publish python package to pypi (https://pypi.org/) using poetry (https://github.com/sdispater/poetry)
pypi-server
Tornado based server like pypi.python.org. With caching from pypi.
pytorch-pretrained-BERT
The Big-&-Extending-Repository-of-Transformers: PyTorch pretrained models for Google's BERT, OpenAI GPT & GPT-2 and Google/CMU Transformer-XL.
question_generation
Neural question generation using transformers
readability
Measure the readability of a given text using surface characteristics
sanic
Async Python 3.5+ web server that's written to go fast
sanic-guide
Frontpage and user guide for Sanic
spacy_alpine
Spacy takes forever to build on Alpine
symspell
Spelling correction & Fuzzy search based on Symmetric Delete spelling correction algorithm.
symspell-1
Rust python bindings for symspell
TensorRT
TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.
transformer-deploy
Deploy optimized transformer based models in production
websocket-client
websocket client for python