Max Ma

megalodon. Reference implementation of Megalodon 7B model

NeuroNLP2. Deep neural models for core NLP tasks (Pytorch version)

flowseq. Generative Flow based Sequence-to-Sequence Toolkit written in Python.

apollo. Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization

fairseq-apollo. FairSeq repo with Apollo optimizer

wolf. Invertible Generative Flows

LasagneNLP. NLP tools on Lasagne

macow. Masked Convolutional Flow

mae. MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders

gecko-llm. Gecko Architecture

NeuroNLP. Deep neural models for core NLP tasks

mega-image. Implementation of Mega on Image Classification

ReLiefParser. Reinforcement Learning Easy First Parser

cmucoref. CMU Conference Resolution System developed by Max Ma

s4. Sequence Modeling with Structured State Spaces

MaxParser. MaxParser in Java