pymia

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

generative-ai-immersion-day

sagemaker-dvc-catboost-demo

aws-workshop-for-kubernetes

AWS Workshop for Kubernetes

laboratory

Some crazy experiments

deequ

Deequ is a library built on top of Apache Spark for defining "unit tests for data", which measure data quality in large datasets.

PySyft

Perform data science on data that remains in someone else's server

TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

PocketFlow

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

model-compression-and-acceleration-progress

Repository to track the progress in model compression and acceleration

morph-net

Fast & Simple Resource-Constrained Learning of Deep Network Structure

distiller

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

aimet

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Image-Harmonization-Dataset-iHarmony4

[CVPR 2020] The first large-scale public benchmark dataset for image harmonization. The code used in our paper "DoveNet: Deep Image Harmonization via Domain Verification", CVPR2020. Useful for image harmonization, image composition, etc.

image-quality-assessment

Convolutional Neural Networks to predict the aesthetic and technical quality of images.

natural-questions

Natural Questions (NQ) contains real user questions issued to Google search, and answers found from Wikipedia by annotators. NQ is designed for the training and evaluation of automatic question answering systems.

data-augmentation-review

List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.

data-validation

Library for exploring and validating machine learning data

snorkel

A system for quickly generating training data with weak supervision

FinMind

Open Data, more than 50 financial data. 提供超過 50 個金融資料(台股為主)，每天更新 https://finmind.github.io/

applied-ml

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

Adversarial-Machine-Learning

对抗样本（Adversarial Examples）和投毒攻击（Poisoning Attacks）相关资料

backdoor-learning-resources

A list of backdoor learning resources

overcooked_ai

A benchmark environment for fully cooperative human-AI performance.

post-mortems

A collection of postmortems. Sorry for the delay in merging PRs!

awesome-bias-mitigation

aws-service-catalog-sagemaker-studio-domain

Workshop to launch Amazon SageMaker Studio domain using AWS Service Catalog and AWS SSO in the AWS Control Tower environment, using AWS CloudFormation templates and lambda functions.

awesome-chaos-engineering

A curated list of Chaos Engineering resources.

awesome-mlops

:sunglasses: A curated list of awesome MLOps tools

amazon-sagemaker-mlops-workshop

Machine Learning Ops Workshop with SageMaker: lab guides and materials.