Vibe Coding DiscoverMade-With-ML
View on GitHubLearn how to develop, deploy and iterate on production-grade ML applications.
Course repo (Made With ML) that walks through a full production ML workflow: data engineering, Ray-based distributed training/tuning, LLM fine-tuning in PyTorch, MLflow tracking, FastAPI serving and CI/CD. It is an educational reference implementation, not a reusable library or agent framework.
Use Cases
Fine-tuning transformer/LLM models for text classificationRunning distributed training and hyperparameter tuning with RayTracking experiments and model registry with MLflowServing models as a FastAPI prediction endpointData quality checks and weak supervision labelingWriting tests, CI/CD and pre-commit workflows for ML codeGoing from notebook experimentation to production scriptsLearning end-to-end MLOps system design
Built With
- Language
- Jupyter Notebook
- Frameworks
- PyTorch · Ray (Train/Tune/Serve/AIR) · MLflow · FastAPI · Hugging Face Transformers · scikit-learn · Snorkel · Great Expectations · Anyscale · Hyperopt · NLTK · Cleanlab · pandas · SQLAlchemy
Tags
mlops · machine-learning · llm-fine-tuning · pytorch · ray · distributed-training · experiment-tracking · mlflow · model-serving · fastapi · data-quality · hyperparameter-tuning · ci-cd · nlp · tutorial · python