Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.

Python library to interact with spice simulators such as LTSpice, QSPICE, NGSpice and others.

Convolutions for Sequence Modeling

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

End-to-end training of Retrieval-Augmented LMs (REALM, RAG)

TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.

A Library for Uncertainty Quantification.

Official Repository for the ICLR 2022 paper "Generalization of Neural Combinatorial Solvers through the Lens of Adversarial Robustness"

A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).

A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.

Code for Winning the Lottery Ahead of Time: Efficient Early Network Pruning (ICML 2022)

Differentiable DAG Sampling (ICLR 2022)

Official Implementation of "Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions" (ICLR, 2022)

A Graph Neural Network Library in Jax

Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification (NeurIPS 2021)

Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph Machine Learning.

MLOps using Azure ML Services and Azure DevOps

Large-Scale Machine and Deep Learning in PyTorch.

SEML: Slurm Experiment Management Library

Probabilistic time series modeling in Python

PPRGo model in PyTorch, as proposed in "Scaling Graph Neural Networks with Approximate PageRank" (KDD 2020)

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts (Neurips 2020)

This repository contains the official implementation of the paper "Reliable Graph Neural Networks via Robust Aggregation" (NeurIPS, 2020).

Implementation of the certificates proposed in the paper "Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More"

FUSE extends macOS by adding support for user space file systems

Material for the MUDS Practical Data Science Training

🥶👫🕸Social Knowledge Graph based on data from meetup.com to generate conversation opening iceabreakers (based on RDF(S), RML, Neo4j & other Technologies)

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Repository for benchmarking graph neural networks