# makemore learning project following andrej karpathy's zero to hero series. builds character-level language models that generate plausible names. ## getting started # check python is installed python3 --version # install uv (fast package manager) curl -LsSf https://astral.sh/uv/install.sh | sh # create and activate virtual environment uv venv source .venv/bin/activate # install dependencies uv pip install -r requirements.txt ## running source .venv/bin/activate python makemore/01-bigram.py start with 01-bigram.py and work through in order. the later files (04, 05) train for 200k steps and take a few minutes. ## dependencies - torch - neural network framework - matplotlib - plotting losses - rich - pretty printing - names.txt - training data (included) ## common gotchas - forgot to activate venv? you'll get "module not found" errors - .venv/ should be in .gitignore (don't commit it) - requirements.txt should be committed (do commit it)