18jeffreyma

afl-bench

Test-bench to test aggregation strategies for asynchronous federated learning

bcpmobileapps

iOS development projects, including BCP Justice Summit iOS App connected to a MySQL database with a PHP REST API

cv

draw_convnet

kidlock

Android application to geofence a child's Android device

motion-artifact

Building a convolutional neural network to detect motion artifacts in abdomen MRI slice imaging and assess the diagnostic quality of MR images

multi_cmd

Extending Competitive Mirror Descent to a multi-agent, reinforcement learning setting.

quanteyes

Quantization of SOTA models for gaze tracking and exploring development of custom processing units to perform quantization in HW.

resume

link to my resume

tfx

TFX is an end-to-end platform for deploying production ML pipelines

18jeffreyma/tfx

TFX is an end-to-end platform for deploying production ML pipelines

18jeffreyma/afl-bench

Test-bench to test aggregation strategies for asynchronous federated learning

18jeffreyma/cv

18jeffreyma/multi_cmd

Extending Competitive Mirror Descent to a multi-agent, reinforcement learning setting.

18jeffreyma/quanteyes

Quantization of SOTA models for gaze tracking and exploring development of custom processing units to perform quantization in HW.

18jeffreyma/resume

link to my resume

18jeffreyma/beam_streaming_experiments

18jeffreyma/CNN-HowManyFingers

Count how many fingers are being held up, via a convolutional neural network (CNN) implemented in Keras + TensorFlow + OpenCV.

18jeffreyma/CodeGen

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

18jeffreyma/copg

This repository contains all code and experiments for competitive policy gradient (CoPG) algorithm.

18jeffreyma/cs249r_book

Collaborative book for CS249r: Tiny Machine Learning

18jeffreyma/Deep-Learning-Experiments

Videos, notes and experiments to understand deep learning

18jeffreyma/EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

18jeffreyma/GAug

AAAI'21: Data Augmentation for Graph Neural Networks

18jeffreyma/Kyuu

Kyuu Keyboard Design

18jeffreyma/llama-2-jax

JAX implementation of the Llama 2 model

18jeffreyma/llama-cpp-python

Python bindings for llama.cpp

18jeffreyma/llama.cpp

Port of Facebook's LLaMA model in C/C++

18jeffreyma/llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

18jeffreyma/LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

18jeffreyma/lorahub

The official repository of paper "LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition".

18jeffreyma/marlenv

ML2-Multi Agent Environments

18jeffreyma/multiagent-particle-envs

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

18jeffreyma/pie-perf

Training language models to make programs faster

18jeffreyma/pycparser

:snake: Complete C99 parser in pure Python

18jeffreyma/resume_src

18jeffreyma/spinningup_pytorch

An educational resource to help anyone learn deep reinforcement learning, with support for PyTorch

18jeffreyma/task_vectors

Editing Models with Task Arithmetic

18jeffreyma/tensorflow

An Open Source Machine Learning Framework for Everyone

18jeffreyma/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.