Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)

Byte-sized summaries or questions-and-answers, including math and code snippets for ML/DL/CV/NLP/GenAI/LLM interview preparation.

Knowledge base for software engineers and research engineers

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

Awesome-LLM: a curated list of Large Language Model

Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.

A collection of design patterns/idioms in Python

Inference code for CodeLlama models

This repository contains all the DSA problems that I have solved.

An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules.

Inference Llama 2 in one file of pure C

Microsoft REST API Guidelines

QLoRA: Efficient Finetuning of Quantized LLMs

LLM training code for Databricks foundation models

Code and documentation to train Stanford's Alpaca models, and generate the data.

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

A playbook for systematically maximizing the performance of deep learning models.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

git extension for {collaborative, communal, continual} model development

Drive a browser with Cohere

🎢 Creating and sharing simulation environments for embodied and synthetic data research

A framework for the evaluation of autoregressive code generation language models.

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models