Linjian Ma's repositories
AutoHOOT.jl
Julia interface for the AutoHOOT library
pairwise-perturbation
Pairwise Perturbation: an efficient numerical algorithm for alternating least squares in tensor decompositions
catn
Contracting Arbitrary Tensor Networks
cotengra
Hyper optimized contraction trees for large tensor networks - compatible with opt_einsum and quimb
DataGraphs.jl
A simple graph type with data on the vertices and edges.
generative-recommenders
Repository hosting code used to reproduce results in "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152, ICML'24).
ITensorNetworkAD.jl
Tools for using AD to optimize tensor networks, built on top of ITensor and AutoHOOT.
ITensorNetworks.jl
A package with general tools for working with higher-dimensional tensor networks based on ITensor.
ITensors.jl
A Julia library for efficient tensor computations and tensor network calculations
koala
A quantum system simulator using PEPS tensor network
metaseq
Repo for external large-scale work
MultiDimDictionaries.jl
Multidimensional dictionaries in Julia, built on top of Dictionaries.jl.
NamedGraphs.jl
Extension of `Graphs.jl` to graphs with named vertices.
OptimKit.jl
OptimKit: A blissfully ignorant Julia package for gradient optimization
PastaQ.jl
Package for Simulation, Tomography and Analysis of Quantum Computers
pytorch-cifar
95.47% on CIFAR10 with PyTorch
pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
SweepContractor.jl
Julia package for contraction of tensor networks, based on the sweep line algorithm outlined in the paper "General tensor network decoding of 2D Pauli codes" (arXiv:2101.04125).
t5_11
housing our model example of fine tuning an 11B t5 with FSDP
torchrec
Pytorch domain library for recommendation systems
transformer_framework
framework for plug and play of various transformers (vision and nlp) with FSDP