dolma-1.0.2.dist-info/METADATA,sha256=_lFImoDDGLN6IFXpNoJ34prLOgi34fEHzlLyIioI1j8,6459
dolma-1.0.2.dist-info/WHEEL,sha256=z8Ql1a7I9FwgD4RlNJNTj6LCRFMzqXuIukXregoopCg,91
dolma-1.0.2.dist-info/entry_points.txt,sha256=ujDqnT7r2W8ndsvrIIkFajfDuLyv3VmZwwBQ4YjE3fM,48
dolma-1.0.2.dist-info/license_files/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
dolma/cli/analyzer.py,sha256=KMoHqtg3aG2alym-UZOJ6vhmO49e_p-_PaoW9Id_TtY,3115
dolma/cli/deduper.py,sha256=Z7Bju2GsQYK9OcRRaXhlrPi9K102lq4KTdNNMml92ek,10569
dolma/cli/mixer.py,sha256=dy-6PHQU8w071GIJazr9qq7UniEXuAJqreNrX96c29Q,8934
dolma/cli/resolvers.py,sha256=vsDlIoMdchh1UGWDWo4SGfSX4usLV4-nUCPYoTazJOs,840
dolma/cli/shared.py,sha256=vPgIJ6Ikd-6x5ST7dxnWiDbXvT3KK-4GvGhqS8RkhW8,1321
dolma/cli/tagger.py,sha256=0E5EraN2y8qDzzm5hgTg8dA1SN8JstiQF9K1vse-Its,6368
dolma/cli/tokenizer.py,sha256=YZyudXzfs0-zmLYhgL9W1iyemRY2pRBgQSyxC3XwPKY,8249
dolma/cli/__init__.py,sha256=uwKCsZCDxra5AhqS2JL-GqnKAQaSxvf6jF-KRB0wFKk,6925
dolma/cli/__main__.py,sha256=LpMujeI2JkU7TPHnyycI11XDxsFnjZNCW9591ZmSW4Q,2992
dolma/core/analyzer.py,sha256=aKQw1kik9QsgR-lrHLyjFmbAY7u5Ioernjji3SzHlQ4,11203
dolma/core/binning.py,sha256=S-_2-wQI0E1lo56VqZam7pra0XnaDRFMGO8kVI_PkM8,16819
dolma/core/data_types.py,sha256=H0gAHaeq6bVBuhO2nY0ZmthduSgIr2RDkwgEIZ8BqXo,8470
dolma/core/errors.py,sha256=uHFdOIEVqka7SBUqpPzpg7Q4HYPeuJIDLvF0IiJA0VM,505
dolma/core/ft_dataset.py,sha256=MwRmAzXnxmgeKqg27AUZT3i7Osve9dlcMNlTxQBKk10,6605
dolma/core/ft_tagger.py,sha256=rx06zjLS_d4zCfvJ5E1ShO1g01t6ElTuvy4McgvliWE,5714
dolma/core/loggers.py,sha256=O4qA4PxAh8uGhNXwutylKa_KOLcaXchXCLoefpgTzFk,1536
dolma/core/parallel.py,sha256=EeYxAhgO43wTqZNdHYXQdTdV-HIJjmLKt_KCVG-a3sY,23506
dolma/core/paths.py,sha256=tdz-Ay2kAlrON5haScpGNVZ1Tsflu8QnmYEgMNWClAw,15272
dolma/core/registry.py,sha256=wCmkPW1Q12kujUfoU_QJG5jyd_OOP9L23uyYXIF3BWU,1958
dolma/core/runtime.py,sha256=dmU2Kex_i5XgfZ8cSNQYMZGwQMDx_bQjM2YNLgyTM6M,20876
dolma/core/taggers.py,sha256=hQ0EDIasL_DJgPYCclWXX9GEQoQ4MqncR8NK9ZSnruI,2072
dolma/core/trainer.py,sha256=Dq68dy_WBUQQS6vSKS0XZ87CBO3GGqLqUsoaV21UHSQ,49
dolma/core/url_blocker.py,sha256=_KSrcgd-wpwanSsJBs5lJZ4f5qE-NiYKeqRRu93AJU4,2894
dolma/core/utils.py,sha256=2sfyVJD5Qc4TyLIneGvo2u8qRK7HcF9WuUigtJAM-gA,5589
dolma/core/vizualizer.py,sha256=hrNqgO3-aq1g0GBPC2GHsWPPFg9yDVczcWb2Zt4ww-A,9764
dolma/core/__init__.py,sha256=PxQ2G89gXVbL72BbneTGblCi-QAoB64TtRt41NnmI2E,230
dolma/data/ext_to_lang_mapping.json,sha256=GDfONldIZpRmUwzyQ6raYbB8405TF9mRmJlnD31fTEE,19477
dolma/data/naughty_words_en.txt,sha256=sFPpdy2XnolVqyZ_jvVyfDdfpId0cXqFKUmTbnIG2aU,4180
dolma/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dolma/taggers/c4.py,sha256=DJF1N20JPvsAcWf7EAm4EPhDI8gYFTL_kYexWc3SNRU,4857
dolma/taggers/code/code_taggers.py,sha256=o7Fvdb3APPnNSZuHxKl-itbl8Fy3oQWRz6b_55hI6K8,9904
dolma/taggers/code/starcoder.py,sha256=otOe4RkB6rbjq7Ii0sTQSYKZVVijZodFJUs-F7bVaB0,4313
dolma/taggers/code/utils.py,sha256=LI7RJVQP18fVM5OEtLYR7PTYhvAznIWAWsdRBEDby1Q,2212
dolma/taggers/code/__init__.py,sha256=3lP_OOvIU5iMjHwjjMOy4OgXemp4pCx_HVSmtGiol0E,324
dolma/taggers/gopher.py,sha256=nITf_A9OKaMAmCrkmiUyWTnWfQz75aFw5KEUS-pNmEQ,7873
dolma/taggers/jigsaw.py,sha256=HOzQh_qZvURM-T4DyXZcdQs8y_e_qbnPW-1_gDMiULE,1913
dolma/taggers/language.py,sha256=3J1Xc2ADvdbQUn-LyAe-F42TI8ZAk_9rNdCZ5FJktD8,9058
dolma/taggers/length.py,sha256=wA9xszFZOCCaaClIy0EonSE6zE4oQKhn0gsZ4RqRjPA,5814
dolma/taggers/pii.py,sha256=SIQyulmpVEWXZnbqzrl10asZaTo6mdugDoBgrNh0sug,11002
dolma/taggers/punctuation.py,sha256=Z4L6hWCWxsoCyJI8g-fGeXG1CNPBhOoPSAiqeLI-Kt4,1267
dolma/taggers/repetitions/repetitions_taggers.py,sha256=XlZsLuFtqcBoQUGtpTRKjoQ0i7PmaqSRpHz63hQZo5M,6674
dolma/taggers/repetitions/utils.py,sha256=hr0tDuGo32ZnTK_Myb1qy1ra_jYOVRGpyGbWwbHbvLI,5225
dolma/taggers/repetitions/__init__.py,sha256=iE-Q__6IPoOJSRDEdwFc5mYAW8ztvafHbWPbTOMbM6Y,329
dolma/taggers/sampling.py,sha256=nWY112ZvpogukfQw0rKGcLf38p2gpQOAsl1PRcFmo2Q,764
dolma/taggers/tokenizers.py,sha256=B7xpBZYv94WFMkbshLqfM8xJW9EBwJZtzH2pmmWBoSc,1078
dolma/taggers/url.py,sha256=cgN3QuVNj3elsrfa3fwwcu0imLV6AJWZudOQQBIKCos,21719
dolma/taggers/__init__.py,sha256=HqkG-LDxoNxfE-GHKcrdCCSSqUY5Wku2H0wDdRiiCxY,182
dolma/tokenizer/data_types.py,sha256=NGNAFDJT12E8f9Z3OVzDfNiN6IZ5_SG8nfRDrioCnak,1264
dolma/tokenizer/executor.py,sha256=bcEPCRCBPs6mq8JduBMVUx83uAzlReu9vtiv7utwWFQ,14876
dolma/tokenizer/memmap_writer.py,sha256=2NvL4WKXDbKveHdaxlOrQwdSlz7w6M4JSH0WwqJvHuc,8796
dolma/tokenizer/tokenizer.py,sha256=OYtrIo0ecLlQrtmCZEgGCwzDsd6dg1IL51EK5kqcdhM,13074
dolma/tokenizer/__init__.py,sha256=-gA-Nhsg_tif5fCVcGyow4LIo3CQZ3uN36bXTfIuPyc,245
dolma/tokenizer/__main__.py,sha256=fgal1qkOIyy15cbSpREunPjjsJJ2koTBsNiq12gFoy4,1046
dolma/__init__.py,sha256=Ms9YiawSWtf93mcz2IVe2MNXF8rUcP62EdTBsUaPeEU,1796
dolma/dolma.cp312-win32.pyd,sha256=1oEE_Xh31bDzLW_VQImZdW7zTgAjZcJsSKPHrCF8_2E,13513216
dolma-1.0.2.dist-info/RECORD,,
