OhadRubin

SmBop

lightning-transformers

Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

allennlp

An open-source NLP research library, built on PyTorch.

build-your-own-x

🤓 Build your own (insert technology here)

Colab-Hacks

Simple Hacks for Google Colaboratory to boost your productivity and help you to perform daily tasks.

colabcode

Run VSCode (codeserver) on Google Colab or Kaggle Notebooks

dalle-lightning

Refactoring dalle-pytorch and taming-transformers for TPU VM

dasd

DPR

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

findimports

Static analysis of Python import statements

GC-DPR

Train Dense Passage Retriever (DPR) with a single GPU

git-t5

Open source machine learning framework for training T5 models on source code in JAX/Flax.

GNUColab

A persistent Google Colab notebook that lets you run a full GNU desktop.

GooseSLURM

SLURM command line tools and scripts

gradio

Create UIs for prototyping your machine learning model in 3 minutes

hydra

Hydra is a framework for elegantly configuring complex applications

LHOPT

Learned Hyperparameter Optimizers

lightning-hydra-template

PyTorch Lightning + Hydra. A very user-friendly template for rapid and reproducible ML experimentation with best practices. ⚡🔥⚡

Lightweighting_Cookbook

This project attempts to build neural network training and lightweighting cookbook including three kinds of lightweighting solutions, i.e., knowledge distillation, filter pruning, and quantization.

prompt_sel

pure-bash-bible

📖 A collection of pure bash alternatives to external processes.

pypeln

Concurrent data pipelines in Python >>>

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

python-package-template

A template repo for Python packages

pytorch-lightning

The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate

PyTorch-Radial-Basis-Function-Layer

An implementation of an RBF layer/module using PyTorch.

swarm

swarm-jax

Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodes

trl

Train transformer language models with reinforcement learning.