dolma-1.2.0.dev0.dist-info/METADATA,sha256=trTaCrZcQ069Mlf0H0AbGxKRSuMJdheTX1Q9sXHslP8,7595
dolma-1.2.0.dev0.dist-info/WHEEL,sha256=D7_pNqSjRbyY3kt95Yp891xv96lWCEp21NtKEAemZ_g,92
dolma-1.2.0.dev0.dist-info/entry_points.txt,sha256=ujDqnT7r2W8ndsvrIIkFajfDuLyv3VmZwwBQ4YjE3fM,48
dolma-1.2.0.dev0.dist-info/licenses/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
dolma/cli/analyzer.py,sha256=fcSnXG4gVgMzTDk5eU-WXV-97I0-lzbcRQrOHfRp9rY,3292
dolma/cli/deduper.py,sha256=2VI1CsugmGxnGzhxCQbiZvtOvDKyutObiz-JR5ZlXCU,12560
dolma/cli/main.py,sha256=jUKA1VEwP4aPiShe_WsigI1LycpmMVjyyz-nHqQrrR0,3059
dolma/cli/mixer.py,sha256=9q9SmFSlHq78JLNQWejvG1DWl1XWaSKYiW2-StMCs1c,9438
dolma/cli/resolvers.py,sha256=vsDlIoMdchh1UGWDWo4SGfSX4usLV4-nUCPYoTazJOs,840
dolma/cli/shared.py,sha256=5hLmWiHfZr63Bf7PbSY06C7KJFrJm7dJb0qXpRM_2vE,1567
dolma/cli/tagger.py,sha256=QUvmhZHSuYJtsTN11djMgWsO8A_ci5Mescz7HDUrndw,6366
dolma/cli/tokenizer.py,sha256=MCUmOpTWlWvqSkAhErAYCEYDwEHUQ7SCWPgGY_zEezs,9482
dolma/cli/warc.py,sha256=qNpIvdqZDTQR5JyXUangZzNMMWVzYTysTEvR1hZyG1w,4784
dolma/cli/__init__.py,sha256=uwKCsZCDxra5AhqS2JL-GqnKAQaSxvf6jF-KRB0wFKk,6925
dolma/cli/__main__.py,sha256=2sBtcI7pWPsnZ9E6VzEYAefTP-vFCzOOxmrvcypj5zE,75
dolma/core/analyzer.py,sha256=cKDazF6xr4x4Vm6cF-jMCgMM8iYgF3KlULvrw6iI_kg,13751
dolma/core/binning.py,sha256=J4KC_HVu46dZouGRaCx25N9eTpELpXOTMVoJuz15pL0,18645
dolma/core/data_types.py,sha256=D0qmToVSZDwXpwww_DDTKGh_UQKCzWVLbC1ph57kNlA,10435
dolma/core/errors.py,sha256=uHFdOIEVqka7SBUqpPzpg7Q4HYPeuJIDLvF0IiJA0VM,505
dolma/core/ft_dataset.py,sha256=MwRmAzXnxmgeKqg27AUZT3i7Osve9dlcMNlTxQBKk10,6605
dolma/core/ft_tagger.py,sha256=JXlOzRa-Q010086kLyQRbQmjaHM9Ard2iDzXPPxTUNw,5766
dolma/core/loggers.py,sha256=O4qA4PxAh8uGhNXwutylKa_KOLcaXchXCLoefpgTzFk,1536
dolma/core/parallel.py,sha256=EeYxAhgO43wTqZNdHYXQdTdV-HIJjmLKt_KCVG-a3sY,23506
dolma/core/paths.py,sha256=h9MofPz_uxAHYmL17fl791qW469fkcnnL5rwLEYlYsE,16057
dolma/core/registry.py,sha256=Y6dolBV1El_LC6pzU3Hc4Jq5sTGnD6sCaTFxg_CitUc,2234
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=igTwWQ_pARdhRyKYQvLGLsde77u2Tk4Qmny5PGafR54,6964
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=XCjPornxnMEvFMNtDQ8evWtW8DIC3fPQgGI2jTR7Fvs,14463
dolma/taggers/code/starcoder.py,sha256=otOe4RkB6rbjq7Ii0sTQSYKZVVijZodFJUs-F7bVaB0,4313
dolma/taggers/code/utils.py,sha256=8GykSglLVsg4p5SrSZcFa03Mp1dyixnBZ2XdwefTK5Y,4652
dolma/taggers/code/__init__.py,sha256=QPP0c9tVtPCCbILTf3jMMuiv-60uPKrP6peOic49xP0,374
dolma/taggers/gopher.py,sha256=w38gS9OCGwXQQLPYOCxRUpYHiygCkTYfhThdmQH-kkM,8352
dolma/taggers/jigsaw.py,sha256=HOzQh_qZvURM-T4DyXZcdQs8y_e_qbnPW-1_gDMiULE,1913
dolma/taggers/language.py,sha256=Ff9_ewDFHiNncBJIgbXl0fVk6VPsFANTza6q17_zbbk,12572
dolma/taggers/length.py,sha256=fXbDW3064YFdqcxiXhfbV7WV5znvb5sG6LWD1Ckj3As,7357
dolma/taggers/licenses.py,sha256=R-6OFDbXo5SfWrXNp0UeP6NI30CYPaETyjGKCbkn3SQ,3434
dolma/taggers/pii.py,sha256=SIQyulmpVEWXZnbqzrl10asZaTo6mdugDoBgrNh0sug,11002
dolma/taggers/punctuation.py,sha256=IujtK9-Q5eLm0Jkr9Xy7GZH6cV1Veh2JRuwmiLnnQww,1267
dolma/taggers/quality.py,sha256=c6kZpn_b9bPXlpN2prngalZpRsd9pMsSoY0PQghB4XA,2654
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=13-BgL3jYNk1XSlNlrsB24hLaVPWi-9113vyQ_-RIgY,211
dolma/tokenizer/data_types.py,sha256=NGNAFDJT12E8f9Z3OVzDfNiN6IZ5_SG8nfRDrioCnak,1264
dolma/tokenizer/executor.py,sha256=qcXa1pNaJnjHr2ZNBEHnB_W9KyozVQyV1VOMFHojMt4,18524
dolma/tokenizer/memmap_writer.py,sha256=2NvL4WKXDbKveHdaxlOrQwdSlz7w6M4JSH0WwqJvHuc,8796
dolma/tokenizer/tokenizer.py,sha256=9nESJtLUKDYd_zSIoMMRC-5A9YlDwc3swngDltmDBhU,16884
dolma/tokenizer/__init__.py,sha256=-gA-Nhsg_tif5fCVcGyow4LIo3CQZ3uN36bXTfIuPyc,245
dolma/warc/linearizers.py,sha256=OmjTG5FB_ClGKVjydrPIF_JQnHf79lbkjgPtR5blsl4,5578
dolma/warc/processor.py,sha256=FNxXiFtjYykagUW9TkemMxYtzZnbiO5TEaqLBd-uDlU,13473
dolma/warc/utils.py,sha256=rZ29qs6v3oJyiATT9KmV-ms6Vgmdyvftp-Jq4DikqpM,1675
dolma/warc/__init__.py,sha256=vGshefqKvSmWawLLePjerIK8t-EYIDPRM7NQrMtsdh4,99
dolma/__init__.py,sha256=Ms9YiawSWtf93mcz2IVe2MNXF8rUcP62EdTBsUaPeEU,1796
dolma/dolma.cp313-win32.pyd,sha256=nVLofqzbvLvmi7VntaGCdxvLTFIj1B-hAp8TB6rhvH0,14408704
dolma-1.2.0.dev0.dist-info/RECORD,,
