dolma-1.0.3.dist-info/METADATA,sha256=dMcINgRJ5W1OI5_muc1RrasynLbw3cIIcCPhAdKwvKM,6413
dolma-1.0.3.dist-info/WHEEL,sha256=UPIUwY4szp2AwisA5SezobKUBRpTJR4uSZ-CaSPyzVk,108
dolma-1.0.3.dist-info/entry_points.txt,sha256=ujDqnT7r2W8ndsvrIIkFajfDuLyv3VmZwwBQ4YjE3fM,48
dolma-1.0.3.dist-info/license_files/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
dolma/data/ext_to_lang_mapping.json,sha256=432dWmIB-qPV7BZAyU_PvUkWL45fhyRmiUvonSYMcWE,18623
dolma/data/naughty_words_en.txt,sha256=r4UezvHV8hLKuhczmxKsOcwv7314x0h29nI3ZE_O6L0,3777
dolma/__init__.py,sha256=FnNv81L5wLOJ7_y3GjPwnRZahleFs3umHgT1TXtmerA,1740
dolma/core/runtime.py,sha256=s8q9g14TBBGbt9Kt84mY57iwADkkr55RuEMDxV8yjNQ,20387
dolma/core/paths.py,sha256=7FGLSjNviMlV9Q9uwsS6w4XRO4gAzoMVe6_ezKyX2WY,15041
dolma/core/parallel.py,sha256=IiVdVKa-Mhhpox9f29gJLjdKk7oLHzwAEulCi9YEzmM,22985
dolma/core/ft_dataset.py,sha256=17FTgayBxxGiztXyPJXwgNiZZh3vI9GKlEkDPDZVLCE,6364
dolma/core/errors.py,sha256=FX-zr3v3pdiM_Yu5ktNybaMaIMbLe29LMa7TSiIniQo,483
dolma/core/__init__.py,sha256=P1geIB-dicdJyLLWF172-SVx9f_Kb_89tBn-XxikhS4,219
dolma/core/vizualizer.py,sha256=odp58V9yzqPDe8Sx6MShQ7ANxR03Uh24_e01bACD4vI,9515
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/data_types.py,sha256=7-hQewnQWiRpwe2QTv9TCUWQN3xydpQvSsExp_dijj0,8211
dolma/core/url_blocker.py,sha256=T2gqJW4xd3FCDHLCTWXQHfOF2GPngMlLcTI0vVtFnYU,2802
dolma/core/binning.py,sha256=oZlqNAewFR7WdkKNtuHtqjkqnRwbdrFetDLMcTTthdc,18194
dolma/core/utils.py,sha256=7XkjOE2wP54WHzuqsPdJzdkld_rvCkl0Xvd_ktuBY4w,5439
dolma/core/analyzer.py,sha256=Vug-ACENROeWQS3CtxX5Ectdj2plbU8cuwi8sntuC78,13416
dolma/core/registry.py,sha256=iQJkqU7d_r7bQkcERAGT8Li4Iaoc3dumW4SmWbF2yks,1899
dolma/core/ft_tagger.py,sha256=cjvnz7pbtanGL-zJ3qrCyQKr6BPvH3Sz_VEmuOh8NyU,5558
dolma/taggers/jigsaw.py,sha256=pdyB4FPfQWsWr-0X_Cusysp3gKmopiue8EmYfnSn56M,1868
dolma/taggers/repetitions/__init__.py,sha256=gVSqSuci_7txxCiZNpwTHwg8wvl4ihx2MZjSX6qOhAY,316
dolma/taggers/repetitions/repetitions_taggers.py,sha256=fhZn30K1BVHvXdUeJ-xpPSJlRYI1uaGMSiR8EGquhMg,6500
dolma/taggers/repetitions/utils.py,sha256=Xs-H0MP0zkhLecxRxfvI3yekaOb82JI5gmig9KjF0PQ,5107
dolma/taggers/tokenizers.py,sha256=86-bBa87RdEyJ83LBzddDo3VJ53e2a48YdE5j9h9sDw,1041
dolma/taggers/url.py,sha256=SyUzJc0vcarc6h8l_VxKHhmkIR13oXX3a3kMO0cARIQ,21230
dolma/taggers/sampling.py,sha256=nepjKCTrB09Um4TKdUHMWIIzBKAk_-Pk9vjceY1FvvQ,744
dolma/taggers/__init__.py,sha256=3iXIbnV7ccA3XezThTBSLwnaW9PVCRYGjb4zdeHYAXc,168
dolma/taggers/length.py,sha256=GOMeEUyMOWCa-94apKAGSlx0gl2gEbcUPMs8TiD9-k4,5674
dolma/taggers/language.py,sha256=5hPyF0JjqjgxC3sWLi9aqx5L1M-fJvdCA71kSEYNtq4,8843
dolma/taggers/c4.py,sha256=7xZqdw_XohrTQaJIU5hZ2cO7oo9n4d9oaQKNJcHKSuo,4730
dolma/taggers/code/__init__.py,sha256=uwOCYx7CQ7o3xdJ7iaZRgv2swiFiYkAmePKYZsSMCNg,309
dolma/taggers/code/starcoder.py,sha256=-Z6xV3Mx5kquFC5c0doLf35GHvazwgpqde8hXhZQpfs,4184
dolma/taggers/code/code_taggers.py,sha256=7ymowSDZAYFB3Tq7wQ1LWrKJ3XrCg-wEhm-ouwiNZC8,9633
dolma/taggers/code/utils.py,sha256=y0qsh2JlMWd-55idxVoR64W9YXSnM3KGqU-q5U7VL7o,2130
dolma/taggers/gopher.py,sha256=aHpM2ZQKMIBOLzMFQZOapeDI5QVAlKTK6MXuxL1SWC8,7654
dolma/taggers/pii.py,sha256=Br1qqiLxHlv5a4U56gXPxOebhTL3Q_9HGFgvRPIe2jw,10710
dolma/taggers/punctuation.py,sha256=x7UJdBdQcZDzegUvsoRDY-n9hB1id66Ni7BLBTPavls,1228
dolma/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
dolma/tokenizer/executor.py,sha256=c4VFzetKVEq_cclDuVy8d8gfKU2d_JtVu7P_gCMCutY,16888
dolma/tokenizer/tokenizer.py,sha256=S6pcayKMWvEzabjk8ULB3tJwTR-y9UtK6D7xFXGag_8,12766
dolma/tokenizer/__init__.py,sha256=QeJVOvXyF-zk9Qo8_7dHNAzKTCvYb5aKo_voYJhIrQY,235
dolma/tokenizer/__main__.py,sha256=Bkh1o5kaG9xd7o0rYruxMTBbUCiKAjkhyd-lZSBhXZg,1014
dolma/tokenizer/data_types.py,sha256=qAi498CJE7_W2r2-wi-iJvOhw6jSKfP8VYaZQOc6hqM,1214
dolma/tokenizer/memmap_writer.py,sha256=dA5nuCjU-RbpmvyskwvgMFvYVgmcmtCvqN0m3Ijwvqs,8581
dolma/cli/deduper.py,sha256=WGUmiR7Wc0fZHhSm6F5Duc2ryQEXymTw78x0MUcQEio,10341
dolma/cli/shared.py,sha256=_Wflzx2bElOJoynpqnSAp09ZEQK9VDfajwDRmJ8P5Dw,1280
dolma/cli/tokenizer.py,sha256=nZdCKcWcAch5vMDpQhH9drzCG9TRkZUVM5Yv-8J2Xec,8281
dolma/cli/tagger.py,sha256=vsgoQSDO1D-HkMAe2-SiC3uMirqNYMMNANy9nTsJk-4,6196
dolma/cli/__init__.py,sha256=23e9uWZqzB0OVgsax01ZaU8t8mNzWO30anqrr5053iw,6724
dolma/cli/resolvers.py,sha256=d5hB1HiFqOA5xVtOSr_6xhyC6wsGI3jA9QtrcPqG5Ls,804
dolma/cli/__main__.py,sha256=Zl_fAZR4fT1dYQ26_lNqktsA2CL7HN8ZDObW9fyEem0,2901
dolma/cli/analyzer.py,sha256=_RRf31u47aQTiC8ZhgHNok38E8b9zYa-QDlrTq28tM8,3205
dolma/cli/mixer.py,sha256=A1sODJ-cLQzCqIzA8zThsXXtFICcmFHopV_NFxwkQGM,8749
dolma/dolma.cpython-310-arm-linux-gnueabihf.so,sha256=Yr9QyiwXh35j7p0xsKiRzywtpPpZvSweQbjt_U0mT0E,25885612
dolma-1.0.3.dist-info/RECORD,,
