dolma-1.2.0.dev7.dist-info/METADATA,sha256=VPBQnTCFigej5O_vhoxyDmiME7CIYseqTmrI1u9umxY,7549
dolma-1.2.0.dev7.dist-info/WHEEL,sha256=0fH7c5CxCIoFt96K-9l7xy33zx_yko84DIdMQ8tKXw0,116
dolma-1.2.0.dev7.dist-info/entry_points.txt,sha256=ujDqnT7r2W8ndsvrIIkFajfDuLyv3VmZwwBQ4YjE3fM,48
dolma-1.2.0.dev7.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
dolma/cli/main.py,sha256=BqWARWa3oUiJNdZJ6437_878BFS8NpOi1eU9eo1fNSg,2966
dolma/cli/warc.py,sha256=cEmO5UBfNhO3eNDujQaOquk9oLQSJRvoqbvv5euudEo,4665
dolma/cli/shared.py,sha256=6gJVToOfQp6ieftrmW-xoLBUWOZxI4sqrqrdcRaz1DY,1520
dolma/cli/__main__.py,sha256=i8Xffknyz7Hg_K1z4UE2mq660gDbHCL2WyrLr8zHmhk,71
dolma/cli/tokenizer.py,sha256=WPkkXS9OoRW-3DDl17gDn5-g225ITAslmfLTxtPaK-k,9258
dolma/cli/deduper.py,sha256=lDBSesqF5o47pTAJVbg7lFvwFMCTVIbnp4GMkYhkymM,12286
dolma/cli/analyzer.py,sha256=_RRf31u47aQTiC8ZhgHNok38E8b9zYa-QDlrTq28tM8,3205
dolma/cli/resolvers.py,sha256=d5hB1HiFqOA5xVtOSr_6xhyC6wsGI3jA9QtrcPqG5Ls,804
dolma/cli/tagger.py,sha256=vWJXy9o0veIBlgP3AQ9BAMoo4n4vFAby4QRNLkotDB4,6194
dolma/cli/__init__.py,sha256=23e9uWZqzB0OVgsax01ZaU8t8mNzWO30anqrr5053iw,6724
dolma/cli/mixer.py,sha256=5zQwtTo3Mp_5JB6e4pwgd8rwA0lKaSFC2PND2WkT_CM,9405
dolma/tokenizer/data_types.py,sha256=qAi498CJE7_W2r2-wi-iJvOhw6jSKfP8VYaZQOc6hqM,1214
dolma/tokenizer/memmap_writer.py,sha256=dA5nuCjU-RbpmvyskwvgMFvYVgmcmtCvqN0m3Ijwvqs,8581
dolma/tokenizer/tokenizer.py,sha256=V87KKmENyLiQ4GC-J2HtUm2_0NjtqyVavwzeX6IIHNk,16495
dolma/tokenizer/__init__.py,sha256=QeJVOvXyF-zk9Qo8_7dHNAzKTCvYb5aKo_voYJhIrQY,235
dolma/tokenizer/executor.py,sha256=SFZTNIpRTuWs2jBiQZmViMtKg30-09an0uLBSLplcRo,18141
dolma/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dolma/core/ft_tagger.py,sha256=QS_yOsP_bUcZYuDf9MfnoHZt_tydb-FB-cWC4VMW71U,5610
dolma/core/data_types.py,sha256=D2itFsRPSuNxc92Pi-yCVMMaJNgGailpctVKqV06YwM,10117
dolma/core/binning.py,sha256=oZlqNAewFR7WdkKNtuHtqjkqnRwbdrFetDLMcTTthdc,18194
dolma/core/taggers.py,sha256=8laX9NqQP4gfi1NK1sM5rpwQ70gv0vScwQTGunim49o,2003
dolma/core/trainer.py,sha256=yfDTEkPq8OgiYWe4_k8xOgMmH2nv3wEWNvalrEOT6cM,42
dolma/core/loggers.py,sha256=FuAqSaG9-PXr3ne06hyhqrUwpPrH-RtyW5dUmanzKhI,1487
dolma/core/registry.py,sha256=q9O_CO2eVqX2EZuyToAK9r4iTwNpDQ-vbZn4M84riMw,2170
dolma/core/errors.py,sha256=FX-zr3v3pdiM_Yu5ktNybaMaIMbLe29LMa7TSiIniQo,483
dolma/core/runtime.py,sha256=s8q9g14TBBGbt9Kt84mY57iwADkkr55RuEMDxV8yjNQ,20387
dolma/core/analyzer.py,sha256=Vug-ACENROeWQS3CtxX5Ectdj2plbU8cuwi8sntuC78,13416
dolma/core/url_blocker.py,sha256=T2gqJW4xd3FCDHLCTWXQHfOF2GPngMlLcTI0vVtFnYU,2802
dolma/core/utils.py,sha256=_cW0u1c8_-EO0sai1QE0Unmm81RkwMFGDRwo-EK6-OM,6776
dolma/core/paths.py,sha256=0wtO8hHIO8R0pztXKYgULCtiAOsRLJMy7f5xVqGdoh0,15518
dolma/core/__init__.py,sha256=P1geIB-dicdJyLLWF172-SVx9f_Kb_89tBn-XxikhS4,219
dolma/core/parallel.py,sha256=IiVdVKa-Mhhpox9f29gJLjdKk7oLHzwAEulCi9YEzmM,22985
dolma/core/vizualizer.py,sha256=odp58V9yzqPDe8Sx6MShQ7ANxR03Uh24_e01bACD4vI,9515
dolma/core/ft_dataset.py,sha256=17FTgayBxxGiztXyPJXwgNiZZh3vI9GKlEkDPDZVLCE,6364
dolma/__init__.py,sha256=FnNv81L5wLOJ7_y3GjPwnRZahleFs3umHgT1TXtmerA,1740
dolma/data/naughty_words_en.txt,sha256=r4UezvHV8hLKuhczmxKsOcwv7314x0h29nI3ZE_O6L0,3777
dolma/data/ext_to_lang_mapping.json,sha256=432dWmIB-qPV7BZAyU_PvUkWL45fhyRmiUvonSYMcWE,18623
dolma/taggers/code/starcoder.py,sha256=-Z6xV3Mx5kquFC5c0doLf35GHvazwgpqde8hXhZQpfs,4184
dolma/taggers/code/code_taggers.py,sha256=8zg6Ihajj5DE_ML3t715xmzoY1hdsGasZUQDsmEgq7w,14081
dolma/taggers/code/utils.py,sha256=91eu6c0Ytu1TjPrzA19Znn1uIpUctxjxP4E6CAurhLI,4488
dolma/taggers/code/__init__.py,sha256=6MFXM07GaqFAuonL5wNshSTFeJ2CC-WH0xUgp0dQo8Y,357
dolma/taggers/length.py,sha256=e5sbAi9uKFM6gQWy1urbIo5QCfNxwANmCFZlTz2tCxo,7179
dolma/taggers/pii.py,sha256=Br1qqiLxHlv5a4U56gXPxOebhTL3Q_9HGFgvRPIe2jw,10710
dolma/taggers/quality.py,sha256=hFpvNaH_r_YY2h-VWDFfl615iE9_QAQH3y0ttGPAgHA,2586
dolma/taggers/sampling.py,sha256=nepjKCTrB09Um4TKdUHMWIIzBKAk_-Pk9vjceY1FvvQ,744
dolma/taggers/licenses.py,sha256=GhCPrJYMA0yjvbIQNyjUDR4VqR-CYuXm-xW7RrpI_X0,3357
dolma/taggers/gopher.py,sha256=ALsk1G-BgEp1yqni5wNaaFTw79LXqo8uMgPY1m9B_Mo,8119
dolma/taggers/__init__.py,sha256=ifZAB8zlLzISAMhdgu_I9GKhLwWDtH6CRM8-1mdp1Q8,195
dolma/taggers/language.py,sha256=-9JF4ica8b8-2QLKvuHvFtyq1JMcRSlhrK-KVMEj6sU,12233
dolma/taggers/c4.py,sha256=7xZqdw_XohrTQaJIU5hZ2cO7oo9n4d9oaQKNJcHKSuo,4730
dolma/taggers/repetitions/repetitions_taggers.py,sha256=fhZn30K1BVHvXdUeJ-xpPSJlRYI1uaGMSiR8EGquhMg,6500
dolma/taggers/repetitions/utils.py,sha256=Xs-H0MP0zkhLecxRxfvI3yekaOb82JI5gmig9KjF0PQ,5107
dolma/taggers/repetitions/__init__.py,sha256=gVSqSuci_7txxCiZNpwTHwg8wvl4ihx2MZjSX6qOhAY,316
dolma/taggers/tokenizers.py,sha256=86-bBa87RdEyJ83LBzddDo3VJ53e2a48YdE5j9h9sDw,1041
dolma/taggers/url.py,sha256=SyUzJc0vcarc6h8l_VxKHhmkIR13oXX3a3kMO0cARIQ,21230
dolma/taggers/jigsaw.py,sha256=pdyB4FPfQWsWr-0X_Cusysp3gKmopiue8EmYfnSn56M,1868
dolma/taggers/punctuation.py,sha256=2IbfGz7osTl33Qu1q4lQIGs5oMm3CZXVDm9ZG8FsX1I,1228
dolma/warc/utils.py,sha256=hz5LuZn3Ff9Bn8PTbFnBogTYzVMmzkJWbTzKLmgQIH4,1629
dolma/warc/__init__.py,sha256=N8bWrAOosPjfVctEDykyoWTr8HOGlFSJZFJ24qJZPrg,96
dolma/warc/linearizers.py,sha256=vuthyf210WeT7ZU3Qmof6VhIjm8bjV_dSMnkbTQ52gE,5433
dolma/warc/processor.py,sha256=C4YOxeT8oK_bg5A-Q_RpIsBcu79il06vzdAXFZN799k,13168
dolma/dolma.pypy310-pp73-aarch64-linux-gnu.so,sha256=tsM1569RYTWML4pa7yeX51MA2yvm2ZpGFzN86pDqIKs,23654664
dolma-1.2.0.dev7.dist-info/RECORD,,
