Commit Graph

5 Commits

Author SHA1 Message Date
google-labs-jules[bot]
51927a9e60 feat: Add comprehensive end-to-end documentation
This commit introduces extensive documentation across the entire nanochat codebase. The goal is to make the project more accessible, educational, and easier for new contributors to understand.

Key additions include:
- A new "Codebase Overview and Data Flow" section in the main README.md, providing a high-level guide to the project structure and training pipeline.
- Detailed, educational docstrings and inline comments in all Python modules within the `nanochat/`, `scripts/`, and `tasks/` directories.
- Explanations of the rationale and implementation details for key components, including Python equivalents for non-Python code where applicable.
- A new `README.md` in the `rustbpe/` directory explaining the BPE algorithm and the decision to use Rust.
- Comprehensive comments in shell scripts and development scripts in the `dev/` directory, clarifying their purpose and usage.
2025-11-24 12:57:49 +00:00
svlandeg
8c9b004c99 typo fixes in scripts 2025-10-28 20:17:31 +01:00
Andrej Karpathy
8892470f29 add the SpellingBee task so that nanochat can count r in strawberry etc. along the way we had to add a bunch of new functionality, e.g. extend the calculator to support the count function of python. possibly the current TaskMixture uses way too many synthetic examples of SpellingBee because the eval gives us exactly 100% performance on spelling. We can tune this later to reclaim some wall clock time here I think 2025-10-24 14:02:48 +00:00
karpathy
2e9669e03a upgrading all other files to be able to use cpu/mps as well as cuda. various minor other changes ,e.g. changing max_iterations to num_iterations in sft script for consistency in naming 2025-10-20 10:15:17 -07:00
karpathy
3a5e0bc50b initial commit 2025-10-13 06:49:24 -07:00