LLMs From Scratch
Build a ChatGPT-like LLM in PyTorch step by step
Learn to build, deploy and iterate production ML apps
Made With ML teaches how to combine machine learning with software engineering to develop, deploy and iterate on production-grade ML applications. It targets data scientists and ML engineers who can train models but struggle to ship and maintain them.
Notebooks and lessons walk through a full ML lifecycle: data annotation and testing, training and evaluation, serving via an API, testing, CI/CD and monitoring, using a real project as the running example. You follow the modules and adapt the pipeline patterns to your own model.
16 Cool GitHub Repos You WILL Use (no pressure)
Build a ChatGPT-like LLM in PyTorch step by step
Runs huge models on small GPUs by streaming layers
Pretrained foundation model for forecasting numeric time-series data
Bare-bones NumPy implementations of core ML algorithms
Command-line video downloader built to be wired into automated workflows
Open agent skills for documents, PDFs and office files