*No copyright* Apache License ----------------------------- python-tokenizers-0.22.2-build/tokenizers-0.22.2/PKG-INFO python-tokenizers-0.22.2-build/tokenizers-0.22.2/pyproject.toml *No copyright* Apache License 2.0 --------------------------------- python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/LICENSE Unknown or generated -------------------- python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/.cargo/config.toml python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/CHANGELOG.md python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/Cargo.lock python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/Cargo.toml python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/MANIFEST.in python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/Makefile python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/README.md python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/benches/test_tiktoken.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/conftest.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/docs/pyo3.md python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/examples/custom_components.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/examples/example.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/examples/train_bert_wordpiece.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/examples/train_bytelevel_bpe.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/examples/train_with_datasets.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/examples/using_the_visualizer.ipynb python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/decoders/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/decoders/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/implementations/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/implementations/base_tokenizer.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/implementations/bert_wordpiece.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/implementations/byte_level_bpe.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/implementations/char_level_bpe.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/implementations/sentencepiece_bpe.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/implementations/sentencepiece_unigram.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/models/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/models/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/normalizers/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/normalizers/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/processors/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/processors/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/tokenizers.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/tools/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/tools/visualizer-styles.css python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/tools/visualizer.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/trainers/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/py_src/tokenizers/trainers/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/rust-toolchain python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/scripts/convert.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/scripts/sentencepiece_extractor.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/scripts/spm_parity_check.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/setup.cfg python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/decoders.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/encoding.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/error.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/lib.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/models.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/normalizers.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/pre_tokenizers.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/processors.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/token.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/tokenizer.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/trainers.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/utils/iterators.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/utils/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/utils/normalization.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/utils/pretokenization.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/utils/regex.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/src/utils/serde_pyo3.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/stub.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/test.txt python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/bindings/test_decoders.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/bindings/test_encoding.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/bindings/test_models.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/bindings/test_normalizers.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/bindings/test_pre_tokenizers.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/bindings/test_processors.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/bindings/test_tokenizer.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/bindings/test_trainers.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/documentation/test_pipeline.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/documentation/test_quicktour.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/documentation/test_tutorial_train_from_iterators.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/implementations/test_base_tokenizer.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/implementations/test_bert_wordpiece.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/implementations/test_byte_level_bpe.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/implementations/test_char_bpe.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/implementations/test_sentencepiece.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/test_serialization.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/bindings/python/tests/utils.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/decoders/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/decoders/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/implementations/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/implementations/base_tokenizer.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/implementations/bert_wordpiece.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/implementations/byte_level_bpe.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/implementations/char_level_bpe.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/implementations/sentencepiece_bpe.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/implementations/sentencepiece_unigram.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/models/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/models/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/normalizers/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/normalizers/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/pre_tokenizers/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/pre_tokenizers/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/processors/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/processors/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/tokenizers.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/tools/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/tools/visualizer-styles.css python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/tools/visualizer.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/trainers/__init__.py python-tokenizers-0.22.2-build/tokenizers-0.22.2/py_src/tokenizers/trainers/__init__.pyi python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/CHANGELOG.md python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/Cargo.toml python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/Makefile python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/README.md python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/README.tpl python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/benches/added_vocab_deserialize.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/benches/bert_benchmark.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/benches/bpe_benchmark.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/benches/common/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/benches/layout_benchmark.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/benches/llama3_benchmark.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/benches/unigram_benchmark.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/examples/encode_batch.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/examples/serialization.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/decoders/bpe.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/decoders/byte_fallback.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/decoders/ctc.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/decoders/fuse.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/decoders/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/decoders/sequence.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/decoders/strip.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/decoders/wordpiece.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/lib.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/bpe/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/bpe/model.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/bpe/serialization.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/bpe/trainer.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/bpe/word.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/unigram/lattice.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/unigram/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/unigram/model.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/unigram/serialization.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/unigram/trainer.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/unigram/trie.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/wordlevel/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/wordlevel/serialization.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/wordlevel/trainer.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/wordpiece/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/wordpiece/serialization.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/models/wordpiece/trainer.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/normalizers/bert.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/normalizers/byte_level.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/normalizers/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/normalizers/precompiled.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/normalizers/prepend.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/normalizers/replace.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/normalizers/strip.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/normalizers/unicode.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/normalizers/utils.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/bert.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/byte_level.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/delimiter.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/digits.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/fixed_length.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/metaspace.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/punctuation.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/sequence.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/split.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/unicode_scripts/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/unicode_scripts/pre_tokenizer.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/unicode_scripts/scripts.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/pre_tokenizers/whitespace.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/processors/bert.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/processors/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/processors/roberta.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/processors/sequence.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/processors/template.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/tokenizer/added_vocabulary.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/tokenizer/encoding.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/tokenizer/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/tokenizer/normalizer.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/tokenizer/pattern.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/tokenizer/pre_tokenizer.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/tokenizer/serialization.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/cache.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/fancy.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/from_pretrained.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/iter.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/onig.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/padding.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/parallelism.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/progress.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/src/utils/truncation.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/tests/added_tokens.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/tests/common/mod.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/tests/documentation.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/tests/from_pretrained.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/tests/offsets.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/tests/serialization.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/tests/stream.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/tests/training.rs python-tokenizers-0.22.2-build/tokenizers-0.22.2/tokenizers/tests/unigram.rs