norabelrose Goto Github PK

amnesic_probing

approxcdf

(Python, R, C) Fast approximations for the CDF of multivariate normal distributions

block-sparse-benchmark

Benchmark for matrix multiplications between dense and block sparse (BSR) matrix in TVM, blocksparse (Gray et al.) and cuSparse.

choix

Inference algorithms for models based on Luce's choice axiom

classroom

Preference-based reinforcement learning in PyTorch and JAX with a browser-based GUI.

crypto

Probably bad pure Python implementations of crypto primitives, not for practical use

datasets

🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

deduplicate-text-datasets

discovering_latent_knowledge

gym

A toolkit for developing and comparing reinforcement learning algorithms.

imitation

Clean PyTorch implementations of imitation and reward learning algorithms

infrabayes

Partial implementation of Vanessa Kosoy's infra-Bayesian decision theory in Python

lightning-bolts

Toolbox of models, callbacks, and datasets for AI/ML researchers.

modularity

Experiments with induced modularity in neural networks

mrp_2020_election

mup

maximal update parametrization (µP)

neural-tangents

Fast and Easy Infinite Neural Networks in Python

nn-clustering-pytorch

Checking the divisibility of neural networks, and investigating the nature of the pieces networks can be divided into.

pathfinder

Python library for simulating and optimizing spacecraft trajectories

performer-pytorch

An implementation of Performer, a linear attention-based transformer, in Pytorch

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-lightning

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

rl-teacher

(This repository is no longer being maintained.) Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for efficiently collecting human feedback.

sente

Sente is an open source python library for the game of Go

simpleparsing

Simple, Elegant, Typed Argument Parsing with argparse

sngp-torch

Simple library implementing Spectral-normalized Neural Gaussian Processes in PyTorch

sparse-vae

sputnik

A library of GPU kernels for sparse matrix operations.

survae_flows

Code for paper "SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows"

tensorboard

TensorFlow's Visualization Toolkit