tokenizers 0.22.1__tar.gz → 0.22.2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {tokenizers-0.22.1 → tokenizers-0.22.2}/PKG-INFO +6 -2
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/Cargo.lock +136 -383
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/Cargo.toml +5 -5
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/Makefile +2 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/README.md +4 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/benches/test_tiktoken.py +19 -24
- tokenizers-0.22.2/bindings/python/docs/pyo3.md +7 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/examples/example.py +1 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/examples/train_with_datasets.py +2 -2
- {tokenizers-0.22.1 → tokenizers-0.22.2/bindings/python}/py_src/tokenizers/__init__.py +1 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2/bindings/python}/py_src/tokenizers/__init__.pyi +440 -2
- {tokenizers-0.22.1 → tokenizers-0.22.2/bindings/python}/py_src/tokenizers/decoders/__init__.pyi +291 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/implementations/base_tokenizer.py +1 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/implementations/sentencepiece_unigram.py +2 -2
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/models/__init__.pyi +159 -6
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/normalizers/__init__.pyi +310 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.pyi +327 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/processors/__init__.pyi +179 -2
- tokenizers-0.22.2/bindings/python/py_src/tokenizers/tokenizers.pyi +17 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2/bindings/python}/py_src/tokenizers/tools/visualizer.py +8 -4
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/trainers/__init__.pyi +289 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/scripts/convert.py +19 -19
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/scripts/sentencepiece_extractor.py +2 -2
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/scripts/spm_parity_check.py +6 -5
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/decoders.rs +44 -59
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/encoding.rs +3 -3
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/lib.rs +1 -10
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/models.rs +22 -28
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/normalizers.rs +26 -57
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/pre_tokenizers.rs +25 -51
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/processors.rs +28 -29
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/token.rs +6 -2
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/tokenizer.rs +52 -87
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/trainers.rs +14 -20
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/utils/iterators.rs +1 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/utils/normalization.rs +6 -8
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/utils/regex.rs +1 -1
- tokenizers-0.22.2/bindings/python/stub.py +305 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/bindings/test_processors.py +14 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/bindings/test_tokenizer.py +2 -2
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/documentation/test_tutorial_train_from_iterators.py +2 -2
- {tokenizers-0.22.1/bindings/python → tokenizers-0.22.2}/py_src/tokenizers/__init__.py +1 -1
- {tokenizers-0.22.1/bindings/python → tokenizers-0.22.2}/py_src/tokenizers/__init__.pyi +440 -2
- {tokenizers-0.22.1/bindings/python → tokenizers-0.22.2}/py_src/tokenizers/decoders/__init__.pyi +291 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/implementations/base_tokenizer.py +1 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/implementations/sentencepiece_unigram.py +2 -2
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/models/__init__.pyi +159 -6
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/normalizers/__init__.pyi +310 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/pre_tokenizers/__init__.pyi +327 -1
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/processors/__init__.pyi +179 -2
- tokenizers-0.22.2/py_src/tokenizers/tokenizers.pyi +17 -0
- {tokenizers-0.22.1/bindings/python → tokenizers-0.22.2}/py_src/tokenizers/tools/visualizer.py +8 -4
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/trainers/__init__.pyi +289 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/pyproject.toml +1 -4
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/Cargo.toml +7 -2
- tokenizers-0.22.2/tokenizers/benches/added_vocab_deserialize.rs +86 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/mod.rs +2 -2
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/tokenizer/added_vocabulary.rs +22 -16
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/truncation.rs +2 -7
- tokenizers-0.22.1/bindings/python/stub.py +0 -185
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/.cargo/config.toml +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/.gitignore +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/CHANGELOG.md +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/MANIFEST.in +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/conftest.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/examples/custom_components.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/examples/train_bert_wordpiece.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/examples/train_bytelevel_bpe.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/examples/using_the_visualizer.ipynb +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/decoders/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/implementations/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/implementations/bert_wordpiece.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/implementations/byte_level_bpe.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/implementations/char_level_bpe.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/implementations/sentencepiece_bpe.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/models/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/normalizers/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/processors/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/tools/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/tools/visualizer-styles.css +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/py_src/tokenizers/trainers/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/rust-toolchain +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/setup.cfg +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/error.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/utils/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/utils/pretokenization.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/src/utils/serde_pyo3.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/test.txt +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/bindings/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/bindings/test_decoders.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/bindings/test_encoding.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/bindings/test_models.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/bindings/test_normalizers.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/bindings/test_pre_tokenizers.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/bindings/test_trainers.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/documentation/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/documentation/test_pipeline.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/documentation/test_quicktour.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/implementations/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/implementations/test_base_tokenizer.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/implementations/test_bert_wordpiece.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/implementations/test_byte_level_bpe.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/implementations/test_char_bpe.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/implementations/test_sentencepiece.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/test_serialization.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/bindings/python/tests/utils.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/decoders/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/implementations/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/implementations/bert_wordpiece.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/implementations/byte_level_bpe.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/implementations/char_level_bpe.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/implementations/sentencepiece_bpe.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/models/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/normalizers/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/pre_tokenizers/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/processors/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/tools/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/tools/visualizer-styles.css +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/py_src/tokenizers/trainers/__init__.py +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/CHANGELOG.md +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/LICENSE +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/Makefile +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/README.md +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/README.tpl +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/benches/bert_benchmark.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/benches/bpe_benchmark.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/benches/common/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/benches/layout_benchmark.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/benches/llama3_benchmark.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/benches/unigram_benchmark.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/examples/encode_batch.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/examples/serialization.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/decoders/bpe.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/decoders/byte_fallback.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/decoders/ctc.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/decoders/fuse.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/decoders/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/decoders/sequence.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/decoders/strip.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/decoders/wordpiece.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/lib.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/bpe/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/bpe/model.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/bpe/serialization.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/bpe/trainer.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/bpe/word.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/unigram/lattice.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/unigram/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/unigram/model.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/unigram/serialization.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/unigram/trainer.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/unigram/trie.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/wordlevel/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/wordlevel/serialization.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/wordlevel/trainer.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/wordpiece/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/wordpiece/serialization.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/models/wordpiece/trainer.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/normalizers/bert.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/normalizers/byte_level.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/normalizers/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/normalizers/precompiled.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/normalizers/prepend.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/normalizers/replace.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/normalizers/strip.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/normalizers/unicode.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/normalizers/utils.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/bert.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/byte_level.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/delimiter.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/digits.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/fixed_length.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/metaspace.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/punctuation.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/sequence.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/split.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/unicode_scripts/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/unicode_scripts/pre_tokenizer.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/unicode_scripts/scripts.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/pre_tokenizers/whitespace.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/processors/bert.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/processors/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/processors/roberta.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/processors/sequence.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/processors/template.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/tokenizer/encoding.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/tokenizer/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/tokenizer/normalizer.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/tokenizer/pattern.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/tokenizer/pre_tokenizer.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/tokenizer/serialization.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/cache.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/fancy.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/from_pretrained.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/iter.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/onig.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/padding.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/parallelism.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/src/utils/progress.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/tests/added_tokens.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/tests/common/mod.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/tests/documentation.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/tests/from_pretrained.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/tests/offsets.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/tests/serialization.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/tests/stream.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/tests/training.rs +0 -0
- {tokenizers-0.22.1 → tokenizers-0.22.2}/tokenizers/tests/unigram.rs +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: tokenizers
|
|
3
|
-
Version: 0.22.
|
|
3
|
+
Version: 0.22.2
|
|
4
4
|
Classifier: Development Status :: 5 - Production/Stable
|
|
5
5
|
Classifier: Intended Audience :: Developers
|
|
6
6
|
Classifier: Intended Audience :: Education
|
|
@@ -21,8 +21,8 @@ Requires-Dist: pytest-asyncio ; extra == 'testing'
|
|
|
21
21
|
Requires-Dist: requests ; extra == 'testing'
|
|
22
22
|
Requires-Dist: numpy ; extra == 'testing'
|
|
23
23
|
Requires-Dist: datasets ; extra == 'testing'
|
|
24
|
-
Requires-Dist: black==22.3 ; extra == 'testing'
|
|
25
24
|
Requires-Dist: ruff ; extra == 'testing'
|
|
25
|
+
Requires-Dist: ty ; extra == 'testing'
|
|
26
26
|
Requires-Dist: sphinx ; extra == 'docs'
|
|
27
27
|
Requires-Dist: sphinx-rtd-theme ; extra == 'docs'
|
|
28
28
|
Requires-Dist: setuptools-rust ; extra == 'docs'
|
|
@@ -208,3 +208,7 @@ tokenizer = Tokenizer.from_file("byte-level-bpe.tokenizer.json")
|
|
|
208
208
|
encoded = tokenizer.encode("I can feel the magic, can you?")
|
|
209
209
|
```
|
|
210
210
|
|
|
211
|
+
### Typing support and `stub.py`
|
|
212
|
+
|
|
213
|
+
The compiled PyO3 extension does not expose type annotations, so editors and type checkers would otherwise see most objects as `Any`. The `stub.py` helper walks the loaded extension modules, renders `.pyi` stub files (plus minimal forwarding `__init__.py` shims), and formats them so that tools like mypy/pyright can understand the public API. Run `python stub.py` whenever you change the Python-visible surface to keep the generated stubs in sync.
|
|
214
|
+
|