JeanKaddour

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

imagen-pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

dowhy

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

x-transformers

A concise but complete full-attention transformer with a set of promising experimental features from various papers

awesome-causality-algorithms

An index of algorithms for learning causality with data

pigar

:coffee: A tool to generate requirements.txt for Python project, and more than that. (IT IS NOT A PACKAGE MANAGEMENT TOOL)

objax

causal-ml

Must-read papers and resources related to causal inference and machine (deep) learning

torchopt

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

evosax

Evolution Strategies in JAX 🦎

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Models in PyTorch

Adan-pytorch

Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch

GSAM

PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)

Extended-Analytic-DPM

Official implementation for Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models (ICML 2022), and a reimplementation of Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models (ICLR 2022)

magi

Reinforcement learning library in JAX.

NoTrainNoGain

Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)

csuite

CSuite: A Suite of Benchmark Datasets for Causality

TWA

[ICLR 2023] Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions

WASAM

Weight-Averaged Sharpness-Aware Minimization (NeurIPS 2022)

spawrious

LAWA

Latest Weight Averaging (NeurIPS HITY 2022)

ReFactorGNN

Implementation for ReFactor GNNs

AL_vs_SubsetSelection

QA-generalize

We introduce and annotate questions according to three categories that measure different levels and kinds of generalization: training set overlap, compositional generalization (comp-gen), and novel-entity generalization (novel-entity).

DAGuerreotype

source code of the paper: DAG LEARNING ON THE PERMUTAHEDRON

manipulation-chatarena

Fork of chatarena: add examples that help to study the manipulation capabilities of LLMs

composite-tests

Kernel-based statistical tests to check if data is drawn from any distribution in a parametric family

typed-configs

Define configs using Python dataclasses and override them on the CLI