Eugene Yan

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

Curated reading list of real-world machine learning case studies from companies like Airbnb, Netflix, and Google showing how they deployed ML systems in production.

📋 A list of open LLMs available for commercial use.

A curated reference list of large language models licensed for commercial use, covering model size, context length, download links, and license type for each entry.

📋 Survey papers summarizing advances in deep learning, NLP, CV, graphs, reinforcement learning, recommendations, graphs, etc.

📝 Design doc template & examples for machine learning systems (requirements, methodology, implementation, etc.)

🤖 A prototype assistant for writing and thinking

🌱 1-on-1 questions and resources from my time as a manager.

📰 Building News Agents to Summarize News with MCP, Q, and tmux

🔍 Minimal examples of machine learning tests for implementation, behaviour, and performance.

Notes from the Latent Space paper club. Follow along or start your own!

📌 Papers, guides, and mentor interviews on applying machine learning for ApplyingML.com—the ghost knowledge of machine learning.

🧪 Simple data science experimentation & tracking with jupyter, papermill, and mlflow.

🛠 Python project template with unit tests, code coverage, linting, type checking, Makefile wrapper, and GitHub Actions.

🛒 Simple recommender with matrix factorization, graph, and NLP. Beating the regular collaborative filtering baseline.

Semantic IDs: How to train an LLM-Recommender Hybrid with steerability and reasoning on recommendations.

No description.

No description.

Sample repository demonstrating how to use FastAPI to serve HTML web apps.

No description.

No description.

Experimenting with LLMs to Research, Reflect, and Plan (LLM assistants, retrieval, and Discord integration)

Calling LLM APIs on a Raspberry Pi for lulz

Simple template showing how to set up docker for reproducible data science with Jupyter notebooks.

No description.

A CS degree I designed for myself, 2020

No description.

A curated list of references for MLOps

😝 End-to-end machine learning; "no code" required!

A curated list of awesome things related to FastAPI

Repository for deep reinforcement learning with OpenAI

No description.

No description.

Code for Kaggle Springleaf Email Prediction Challenge

edX: Introduction to Computational Thinking and Data Science (Oct 2014)

MIT Deep Learning Book in PDF format

Coursera: Mining Massive Datasets (Sep 2014)

Ask Me Anything

Search Engineering course materials

edX: Introduction to Computer Science and Programming in Python (July 2014)

No description.

Coursera: Data Analysis & Statistical Inference Project (Feb 2014)

Stanford OpenX: Introduction to Statistical Learning

This repository contains the lab assignments for the facilitation of John Hopkins University' Coursera MOOC on Statistical Inference.

Code for Kaggle Titanic Challenge (and other learning)

Examples and guides for using the OpenAI API

No description.

AI and Machine Learning with Kubeflow, Amazon EKS, and SageMaker

No description.

Coursera: Getting and Cleaning Data (May 2014)

No description.

Simple forecasting with Regression Model

Coursera: R Programming (May 2014)

Coursera: Machine Learning (Aug 2014)

Code for Kaggle Otto Production Classification Challenge

Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.

Just me playing around with OpenAI

A proof of concept library for generating and running machine learning model tests

Twitter Streaming and Analysis with Python and R

No description.

No description.

Repository for Programming Assignment 2 for R Programming on Coursera

React specific linting rules for ESLint

Coursera: Interactive Programming in Python (Apr 2014)

Random Visualizations

Prototyping various forecasting techniques

No description.

No description.

active angel investors in developer tools!

A curated list of awesome self-supervised methods

No description.

Large-scale and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, on single node, hadoop yarn and more.

Some small utility modules to help with pandas, numpy and sklearn usage in other projects

Information for setting up for the BerkeleyX Spark Intro MOOC, and lab assignments for the course

Sharing my R script used in the DKSG DataLearn for home

Tensorflow MNIST example using Dataset API

Notes and exercise attempts for "An Introduction to Statistical Learning"

No description.

openai function calls for humans

The barebones NextJS app

dssg

Some js extension for IPython notebook