A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

Distributed Machine Learning Patterns from Manning Publications by Yuan Tang https://bit.ly/2RKv8Zo

Keras implementation of the renowned publication "DeepFace: Closing the Gap to Human-Level Performance in Face Verification" by Taigman et al. Pre-trained weights on VGGFace2 dataset.

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

Carefully curated list of awesome data science resources.

SOTA Google's Perceiver-AR Music Transformer Implementation and Model

This is the official codebase for KDD 2021 paper Generalized Zero-Shot Extreme Multi-Label Learning

A comprehensive guide designed to empower readers with advanced strategies and practical insights for developing, optimizing, and deploying scalable AI models in real-world applications.

Materials for "Machine Learning on Big Data" course

Execution framework for multi-task model parallelism. Enables the training of arbitrarily large models with a single GPU, with linear speedups for multi-gpu multi-task execution.

A fully adaptive, zero-tuning parameter manager that enables efficient distributed machine learning training

[DEPRECEATED] Multi-Instrumental Music Transformer trained on 12GB/400k MIDIs

[DEPRECEATED] Piano Transformer model trained on 2.6GB of MIDI piano music

Keras implementation of the renowned publication "FaceNet: A Unified Embedding for Face Recognition and Clustering" by Schroff et al.

Crack SWE (ML) / DS MAANG Interviews

Official Code Base for ICLR 2024 paper Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction

This project is for developing a deep neural networks and its variant from scratch. No external libraries are used except for GPU operations.

Our full length research is finally acknowledged through double-blind review procedure.

Analyzing crime in Chicago using large scale computing methods

This repository is a code sample to serve Large Language Models (LLM) on a Google Kubernetes Engine (GKE) cluster with GPUs running NVIDIA Triton Inference Server with FasterTransformer backend.