.gitignore
.pre-commit-config.yaml
CITATION.cff
LICENSE
Makefile
README.md
pyproject.toml
uv.lock
.github/workflows/ci.yaml
.github/workflows/integration.yaml
.github/workflows/release.yaml
assets/vgogh_skeleton.jpeg
docs/1_saving_and_loading.md
docs/2_automatic_checks.md
docs/3_editing_models.md
docs/README.md
skeletoken/__init__.py
skeletoken/addedtoken.py
skeletoken/base.py
skeletoken/cache_utils.py
skeletoken/common.py
skeletoken/decoders.py
skeletoken/empty.py
skeletoken/merges.py
skeletoken/model_delta.py
skeletoken/models.py
skeletoken/normalizers.py
skeletoken/padding.py
skeletoken/post_processors.py
skeletoken/pre_tokenizers.py
skeletoken/py.typed
skeletoken/transformers_compat.py
skeletoken/truncation.py
skeletoken/version.py
skeletoken/vocabulary.py
skeletoken.egg-info/PKG-INFO
skeletoken.egg-info/SOURCES.txt
skeletoken.egg-info/dependency_links.txt
skeletoken.egg-info/requires.txt
skeletoken.egg-info/scm_file_list.json
skeletoken.egg-info/scm_version.json
skeletoken.egg-info/top_level.txt
skeletoken/clean/__init__.py
skeletoken/clean/clean.py
skeletoken/external/model2vec.py
skeletoken/external/pylate.py
skeletoken/external/sentence_transformers.py
skeletoken/external/transformers.py
skeletoken/preprocessor/__init__.py
skeletoken/preprocessor/preprocessor.py
skeletoken/trainer/__init__.py
skeletoken/trainer/trainer.py
tests/__init__.py
tests/conftest.py
tests/test_addedtoken.py
tests/test_base.py
tests/test_common.py
tests/test_decoder.py
tests/test_merges.py
tests/test_model_delta.py
tests/test_models.py
tests/test_normalizers.py
tests/test_padding.py
tests/test_post_processors.py
tests/test_pre_tokenizers.py
tests/test_preprocessor.py
tests/test_trainer.py
tests/test_vocabulary.py
tests/clean/test_clean.py
tests/data/bert-base-cased
tests/data/ModernBERT-base/special_tokens_map.json
tests/data/ModernBERT-base/tokenizer.json
tests/data/ModernBERT-base/tokenizer_config.json
tests/data/bert-base-uncased/special_tokens_map.json
tests/data/bert-base-uncased/tokenizer.json
tests/data/bert-base-uncased/tokenizer_config.json
tests/data/bert-base-uncased/vocab.txt
tests/data/gpt2/merges.txt
tests/data/gpt2/special_tokens_map.json
tests/data/gpt2/tokenizer.json
tests/data/gpt2/tokenizer_config.json
tests/data/gpt2/vocab.json
tests/data/multilingual-e5-base/special_tokens_map.json
tests/data/multilingual-e5-base/tokenizer.json
tests/data/multilingual-e5-base/tokenizer_config.json
tests/data/wordpiece/special_tokens_map.json
tests/data/wordpiece/tokenizer.json
tests/data/wordpiece/tokenizer_config.json
tests/integration/conftest.py
tests/integration/test_bert_cased.py
tests/integration/test_bert_uncased.py
tests/integration/test_external_model2vec.py
tests/integration/test_external_pylate.py
tests/integration/test_external_sentence_transformers.py
tests/integration/test_external_transformers.py
tests/integration/test_gpt2.py
tests/integration/test_modernbert_base.py
tests/integration/test_multilingual_e5_base.py
tests/integration/test_to_transformers_file_parity.py
tests/integration/test_to_transformers_regressions.py