LICENSE README.md pyproject.toml setup.cfg setup.py curated_tokenizers/__init__.py curated_tokenizers/_bbpe.pxd curated_tokenizers/_bbpe.pyx curated_tokenizers/_spp.pxd curated_tokenizers/_spp.pyx curated_tokenizers/_wordpiece.pxd curated_tokenizers/_wordpiece.pyx curated_tokenizers/config.h curated_tokenizers/merges.cc curated_tokenizers/merges.hh curated_tokenizers/py.typed curated_tokenizers/util.hh curated_tokenizers/wordpiece.cc curated_tokenizers/wordpiece.hh curated_tokenizers.egg-info/PKG-INFO curated_tokenizers.egg-info/SOURCES.txt curated_tokenizers.egg-info/dependency_links.txt curated_tokenizers.egg-info/requires.txt curated_tokenizers.egg-info/top_level.txt curated_tokenizers.egg-info/zip-safe curated_tokenizers/tests/__init__.py curated_tokenizers/tests/incorrect-merges.txt curated_tokenizers/tests/robbert-merges-1000.txt curated_tokenizers/tests/robbert-vocab-1000.json curated_tokenizers/tests/test_bbpe_processor.py curated_tokenizers/tests/test_sp.py curated_tokenizers/tests/test_word_piece_processor.py curated_tokenizers/tests/toy-word-pieces.txt curated_tokenizers/tests/toy.model sentencepiece/python/once.h sentencepiece/src/bpe_model.cc sentencepiece/src/bpe_model.h sentencepiece/src/bpe_model_test.cc sentencepiece/src/bpe_model_trainer.cc sentencepiece/src/bpe_model_trainer.h sentencepiece/src/bpe_model_trainer_test.cc sentencepiece/src/builder.cc sentencepiece/src/builder.h sentencepiece/src/builder_test.cc sentencepiece/src/char_model.cc sentencepiece/src/char_model.h sentencepiece/src/char_model_test.cc sentencepiece/src/char_model_trainer.cc sentencepiece/src/char_model_trainer.h sentencepiece/src/char_model_trainer_test.cc sentencepiece/src/common.h sentencepiece/src/compile_charsmap_main.cc sentencepiece/src/error.cc sentencepiece/src/filesystem.cc sentencepiece/src/filesystem.h sentencepiece/src/filesystem_test.cc sentencepiece/src/freelist.h sentencepiece/src/freelist_test.cc sentencepiece/src/init.h sentencepiece/src/init_test.cc sentencepiece/src/model_factory.cc sentencepiece/src/model_factory.h sentencepiece/src/model_factory_test.cc sentencepiece/src/model_interface.cc sentencepiece/src/model_interface.h sentencepiece/src/model_interface_test.cc sentencepiece/src/normalization_rule.h sentencepiece/src/normalizer.cc sentencepiece/src/normalizer.h sentencepiece/src/normalizer_test.cc sentencepiece/src/pretokenizer_for_training.cc sentencepiece/src/pretokenizer_for_training.h sentencepiece/src/pretokenizer_for_training_test.cc sentencepiece/src/sentencepiece_processor.cc sentencepiece/src/sentencepiece_processor.h sentencepiece/src/sentencepiece_processor_test.cc sentencepiece/src/sentencepiece_trainer.cc sentencepiece/src/sentencepiece_trainer.h sentencepiece/src/sentencepiece_trainer_test.cc sentencepiece/src/spec_parser.h sentencepiece/src/spm_decode_main.cc sentencepiece/src/spm_encode_main.cc sentencepiece/src/spm_export_vocab_main.cc sentencepiece/src/spm_normalize_main.cc sentencepiece/src/spm_train_main.cc sentencepiece/src/test_main.cc sentencepiece/src/testharness.cc sentencepiece/src/testharness.h sentencepiece/src/trainer_factory.cc sentencepiece/src/trainer_factory.h sentencepiece/src/trainer_factory_test.cc sentencepiece/src/trainer_interface.cc sentencepiece/src/trainer_interface.h sentencepiece/src/trainer_interface_test.cc sentencepiece/src/unicode_script.cc sentencepiece/src/unicode_script.h sentencepiece/src/unicode_script_map.h sentencepiece/src/unicode_script_test.cc sentencepiece/src/unigram_model.cc sentencepiece/src/unigram_model.h sentencepiece/src/unigram_model_test.cc sentencepiece/src/unigram_model_trainer.cc sentencepiece/src/unigram_model_trainer.h sentencepiece/src/unigram_model_trainer_test.cc sentencepiece/src/util.cc sentencepiece/src/util.h sentencepiece/src/util_test.cc sentencepiece/src/word_model.cc sentencepiece/src/word_model.h sentencepiece/src/word_model_test.cc sentencepiece/src/word_model_trainer.cc sentencepiece/src/word_model_trainer.h sentencepiece/src/word_model_trainer_test.cc sentencepiece/src/builtin_pb/sentencepiece.pb.cc sentencepiece/src/builtin_pb/sentencepiece.pb.h sentencepiece/src/builtin_pb/sentencepiece_model.pb.cc sentencepiece/src/builtin_pb/sentencepiece_model.pb.h sentencepiece/third_party/absl/container/flat_hash_map.h sentencepiece/third_party/absl/container/flat_hash_set.h sentencepiece/third_party/absl/flags/flag.cc sentencepiece/third_party/absl/flags/flag.h sentencepiece/third_party/absl/flags/parse.h sentencepiece/third_party/absl/memory/memory.h sentencepiece/third_party/absl/strings/ascii.h sentencepiece/third_party/absl/strings/match.h sentencepiece/third_party/absl/strings/numbers.h sentencepiece/third_party/absl/strings/str_cat.h sentencepiece/third_party/absl/strings/str_format.h sentencepiece/third_party/absl/strings/str_join.h sentencepiece/third_party/absl/strings/str_replace.h sentencepiece/third_party/absl/strings/str_split.h sentencepiece/third_party/absl/strings/string_view.cc sentencepiece/third_party/absl/strings/string_view.h sentencepiece/third_party/absl/strings/strip.h sentencepiece/third_party/darts_clone/darts.h sentencepiece/third_party/protobuf-lite/arena.cc sentencepiece/third_party/protobuf-lite/arenastring.cc sentencepiece/third_party/protobuf-lite/bytestream.cc sentencepiece/third_party/protobuf-lite/coded_stream.cc sentencepiece/third_party/protobuf-lite/common.cc sentencepiece/third_party/protobuf-lite/extension_set.cc sentencepiece/third_party/protobuf-lite/generated_enum_util.cc sentencepiece/third_party/protobuf-lite/generated_message_table_driven_lite.cc sentencepiece/third_party/protobuf-lite/generated_message_util.cc sentencepiece/third_party/protobuf-lite/implicit_weak_message.cc sentencepiece/third_party/protobuf-lite/int128.cc sentencepiece/third_party/protobuf-lite/io_win32.cc sentencepiece/third_party/protobuf-lite/message_lite.cc sentencepiece/third_party/protobuf-lite/parse_context.cc sentencepiece/third_party/protobuf-lite/repeated_field.cc sentencepiece/third_party/protobuf-lite/status.cc sentencepiece/third_party/protobuf-lite/statusor.cc sentencepiece/third_party/protobuf-lite/stringpiece.cc sentencepiece/third_party/protobuf-lite/stringprintf.cc sentencepiece/third_party/protobuf-lite/structurally_valid.cc sentencepiece/third_party/protobuf-lite/strutil.cc sentencepiece/third_party/protobuf-lite/time.cc sentencepiece/third_party/protobuf-lite/wire_format_lite.cc sentencepiece/third_party/protobuf-lite/zero_copy_stream.cc sentencepiece/third_party/protobuf-lite/zero_copy_stream_impl.cc sentencepiece/third_party/protobuf-lite/zero_copy_stream_impl_lite.cc sentencepiece/third_party/protobuf-lite/google/protobuf/any.h sentencepiece/third_party/protobuf-lite/google/protobuf/arena.h sentencepiece/third_party/protobuf-lite/google/protobuf/arena_impl.h sentencepiece/third_party/protobuf-lite/google/protobuf/arenastring.h sentencepiece/third_party/protobuf-lite/google/protobuf/descriptor.h sentencepiece/third_party/protobuf-lite/google/protobuf/extension_set.h sentencepiece/third_party/protobuf-lite/google/protobuf/extension_set_inl.h sentencepiece/third_party/protobuf-lite/google/protobuf/generated_enum_reflection.h sentencepiece/third_party/protobuf-lite/google/protobuf/generated_enum_util.h sentencepiece/third_party/protobuf-lite/google/protobuf/generated_message_table_driven.h sentencepiece/third_party/protobuf-lite/google/protobuf/generated_message_table_driven_lite.h sentencepiece/third_party/protobuf-lite/google/protobuf/generated_message_util.h sentencepiece/third_party/protobuf-lite/google/protobuf/has_bits.h sentencepiece/third_party/protobuf-lite/google/protobuf/implicit_weak_message.h sentencepiece/third_party/protobuf-lite/google/protobuf/map.h sentencepiece/third_party/protobuf-lite/google/protobuf/map_entry_lite.h sentencepiece/third_party/protobuf-lite/google/protobuf/map_field_lite.h sentencepiece/third_party/protobuf-lite/google/protobuf/map_type_handler.h sentencepiece/third_party/protobuf-lite/google/protobuf/message_lite.h sentencepiece/third_party/protobuf-lite/google/protobuf/metadata_lite.h sentencepiece/third_party/protobuf-lite/google/protobuf/parse_context.h sentencepiece/third_party/protobuf-lite/google/protobuf/port.h sentencepiece/third_party/protobuf-lite/google/protobuf/port_def.inc sentencepiece/third_party/protobuf-lite/google/protobuf/port_undef.inc sentencepiece/third_party/protobuf-lite/google/protobuf/repeated_field.h sentencepiece/third_party/protobuf-lite/google/protobuf/unknown_field_set.h sentencepiece/third_party/protobuf-lite/google/protobuf/wire_format_lite.h sentencepiece/third_party/protobuf-lite/google/protobuf/io/coded_stream.h sentencepiece/third_party/protobuf-lite/google/protobuf/io/io_win32.h sentencepiece/third_party/protobuf-lite/google/protobuf/io/zero_copy_stream.h sentencepiece/third_party/protobuf-lite/google/protobuf/io/zero_copy_stream_impl.h sentencepiece/third_party/protobuf-lite/google/protobuf/io/zero_copy_stream_impl_lite.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/bytestream.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/callback.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/casts.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/common.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/hash.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/int128.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/logging.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/macros.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/map_util.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/mutex.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/once.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/platform_macros.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/port.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/status.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/statusor.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/stl_util.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/stringpiece.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/stringprintf.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/strutil.h sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/time.h