Update CLAUDE.md for lazy loading and langmap rename

- Document CPU fallback with warning instead of hard GPU requirement
- Update package name from LangMap/ to langmap/
- Note lazy loading behavior and fast import-safety test

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

CLAUDE.md

@@ -0,0 +1,45 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+A Hugging Face Spaces app that translates English text to ~400 languages using Google's [MADLAD-400](https://arxiv.org/pdf/2309.04662) 3B Seq2Seq model. Built with Gradio and deployed on HF Spaces. Falls back to CPU with a warning when no GPU is available.
+
+## Commands
+
+```bash
+# Setup
+python -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+
+# Run (launches on http://localhost:7860)
+python app.py
+
+# Lint and format
+ruff check .
+ruff format .
+
+# Type check
+ty check
+
+# Test
+pytest                     # all tests (slow tests require GPU + model download)
+pytest -m "not slow"       # fast tests only
+pytest -m slow             # model tests only
+```
+
+## Architecture
+
+**`app.py`** — Single-file application. Uses `@lru_cache` for lazy loading of the `google/madlad400-3b-mt` tokenizer and model with `float16` precision (no download on import). Translation prepends a language token to the input text (e.g., `<2fr>Hello`) before tokenization and generation. The `@spaces.GPU` decorator allocates GPU on HF Spaces infrastructure.
+
+**`langmap/`** — Package with `langid_mapping.py`, a hand-maintained dictionary mapping ~400 language tokens to human-readable language names (sourced from pages 16–21 of the MADLAD-400 paper). Available languages at runtime are the intersection of this mapping and the model's vocabulary.
+
+**`tests/`** — Pytest suite split into fast (`test_langmap.py`) and slow (`test_app.py`). Slow tests require GPU and model download; they are auto-skipped without MPS/CUDA. Fast tests in `test_app.py` verify the module imports without triggering model download.
+
+## Tooling
+
+- **Ruff** — linter and formatter (`ruff.toml`). Rules: `E`, `F`, `I`, `W`. Line length: 120.
+- **ty** — type checker (`ty.toml`). Python 3.12 target.
+- **pytest** — test runner (`pytest.ini`). Custom `slow` marker for GPU-dependent tests.