Hongnan Gao's repositories
TheBareOps
This is a proof of concept MLOps pipeline with minimal usage of modern tech stacks.
modal-examples
Examples of programs built using Modal
PeekingDuck
A modular framework built to simplify Computer Vision inference workloads.
peekingduck-trainer
This repository contains a prototype training pipeline for PeekingDuck/CV HUB/AISG.
awesome-modal
A curated list of amazingly awesome Modal applications, demos, and shiny things. Inspired by awesome-php.
core-pytorch-utils
Yet another PyTorch Trainer and some core components for deep learning.
d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.
energy-forecasting
π The Full Stack 7-Steps MLOps Framework - Learn ML Engineering & MLOps for free by designing, implementing, deploying and monitoring your own energy consumption forecaster.
instructor
structured outputs for llms
llm-paper-club-asia-notes
Notes for LLM Paper Club asia
multiverse
π Omniverse: A cosmic collection of machine learning, deep learning, data science, math, and software engineering explorations. Dive into the universe of knowledge! π
transformer-lm
Transform LM written from scratched - implements Byte-pair encoding Tokenizer, AdamW optimizer, and Transformer with Multi-headed Attention