BENCHMARK_RESULTS.md
CHANGELOG.md
CRAYON_RESEARCH_PAPER.md
DAT_BUILDING_EXPLAINED.md
IMPLEMENTATION_SUMMARY.md
LICENSE
MANIFEST.in
README.md
benchmark_all.py
benchmark_comparison.png
benchmark_competitive.py
benchmark_dat.py
benchmark_quick.py
benchmark_results.json
build_production_dat.py
compile_profiles.py
demo.py
demo_tokenize.py
hf_training.log
image-1.png
image.png
init_profiles.py
load_and_go.py
pyproject.toml
setup.py
test.dat
test_readme_examples.py
train_code_datasets.py
train_grad_full.py
train_hf_datasets.py
train_vocab.py
trained_vocab.json
trained_vocab.txt
trained_vocab_arts_commerce.json
trained_vocab_code.json
trained_vocab_lite.json
trained_vocab_multilingual.json
trained_vocab_science.json
verify_and_benchmark.py
verify_code_vocab.py
verify_dat_engine.py
vocab.json
.github/workflows/build_wheels.yml
benchmarks/micro_bench.py
benchmarks/run_benchmarks.py
dat_profiles/vocab_arts_commerce.dat
dat_profiles/vocab_arts_commerce.json
dat_profiles/vocab_code.dat
dat_profiles/vocab_code.json
dat_profiles/vocab_multilingual.dat
dat_profiles/vocab_multilingual.json
dat_profiles/vocab_science.dat
dat_profiles/vocab_science.json
src/crayon/c_ext/crayon_module.c
src/crayon/c_ext/engine.cpp
src/crayon/c_ext/simd_ops.c
src/crayon/__init__.py
src/crayon/cli.py
src/crayon/resources.py
src/crayon/training.py
src/crayon/adaptive/__init__.py
src/crayon/adaptive/manager.py
src/crayon/adaptive/stability.py
src/crayon/adaptive/updater.py
src/crayon/c_ext/__init__.py
src/crayon/c_ext/crayon_module.c
src/crayon/c_ext/dat_builder.py
src/crayon/c_ext/engine.cpp
src/crayon/c_ext/simd_ops.c
src/crayon/c_ext/simd_ops.h
src/crayon/c_ext/trie_node.h
src/crayon/concurrency/__init__.py
src/crayon/concurrency/pipeline.py
src/crayon/concurrency/thread_local.py
src/crayon/core/__init__.py
src/crayon/core/dat_compiler.py
src/crayon/core/primitives.py
src/crayon/core/profiles.py
src/crayon/core/tokenizer.py
src/crayon/core/vocab_builder.py
src/crayon/core/vocabulary.py
src/crayon/memory/__init__.py
src/crayon/memory/cache.py
src/crayon/memory/pool.py
src/crayon/memory/zerocopy.py
src/crayon/resources/arts_commerce_corpus.txt
src/crayon/resources/code_corpus.txt
src/crayon/resources/data.csv
src/crayon/resources/graduate_math.txt
src/crayon/resources/input.txt
src/crayon/resources/multilingual_corpus.txt
src/crayon/resources/physics_detailed_dataset_700_rows.csv
src/crayon/resources/science_corpus.txt
src/crayon/resources/dat/vocab_arts_commerce.dat
src/crayon/resources/dat/vocab_arts_commerce.json
src/crayon/resources/dat/vocab_code.dat
src/crayon/resources/dat/vocab_code.json
src/crayon/resources/dat/vocab_lite.dat
src/crayon/resources/dat/vocab_lite.json
src/crayon/resources/dat/vocab_multilingual.dat
src/crayon/resources/dat/vocab_multilingual.json
src/crayon/resources/dat/vocab_science.dat
src/crayon/resources/dat/vocab_science.json
src/crayon/unicode/__init__.py
src/crayon/unicode/multilingual.py
src/crayon/unicode/normalizer.py
src/xerv_crayon.egg-info/PKG-INFO
src/xerv_crayon.egg-info/SOURCES.txt
src/xerv_crayon.egg-info/dependency_links.txt
src/xerv_crayon.egg-info/entry_points.txt
src/xerv_crayon.egg-info/not-zip-safe
src/xerv_crayon.egg-info/requires.txt
src/xerv_crayon.egg-info/top_level.txt