Path |
Digest |
Size |
cc_net/__init__.py |
sha256=JcPipJgiSziQWRMpEpG6fli3FLSWJ0UGhGuoknzEHRw
|
198 |
cc_net/__main__.py |
sha256=RIaYC1kd1YVdlwEAcyccVhvDFXoGZ4bzpj5wlL2tfbY
|
752 |
cc_net/dedup.py |
sha256=Hdcq71K2x_O_VuH2m41o_H7Wa_yHqrZAbsgOA3gOhOk
|
17323 |
cc_net/execution.py |
sha256=OrA9HkhGOxQI7oi9HifSC2j8JFI6u3wcZNVCEgukqVc
|
5274 |
cc_net/flat_hash_set.py |
sha256=UC592PMjEHk0rHBTgx-3zOn2vPP3sEyh3PzxBs4k_58
|
7425 |
cc_net/get_wiki_cirrus.py |
sha256=QQQhkujOHUNET4OehYEcnd5VcIv6rgY16bhQewawIiA
|
3798 |
cc_net/jsonql.py |
sha256=vuz4UOrMGgSTyJk3GLamZ8_FY8LObtwJ8qHuLEWYW1M
|
42262 |
cc_net/mine.py |
sha256=4Od3wYd8xIvq-CNdmz9HbUCCMEy2nUp9FUbNUvpl5Sw
|
17837 |
cc_net/minify.py |
sha256=M1Ji3f8LpmylXAaqWpQIHGXPzrUQ0g9nZMxz3xkG3fo
|
11276 |
cc_net/perplexity.py |
sha256=1j3TdKtZsuZNSJmOVCMimCQv3yK9_NUHGXHrB90fPYs
|
10943 |
cc_net/process_wet_file.py |
sha256=aal1c1s9ks1sZEPzqEufBZfkWjZQsrV3A4hmjumwN4Y
|
6293 |
cc_net/regroup.py |
sha256=vsAZVnBUMgF4NekF4uW9fMCMowSTu25Xd09XuDc1jOc
|
3511 |
cc_net/split_by_lang.py |
sha256=ihNv_TdINdKNNXZwVDKYdhXCCMHX5GnSGZT0mU5V93M
|
4760 |
cc_net/text_normalizer.py |
sha256=zZDEjm7nKXmFxdmsPWsJhyI2o2plG3s9a0J9EU3Fe3M
|
4524 |
cc_net/tokenizer.py |
sha256=xZPBSU5z-thHGHGSr2q3h_Qt3zPIloBAP8NCx0s7qxI
|
2429 |
cc_net/data/cutoff.csv |
sha256=YqL_PFh6EQYQ3X2HUHEsu6naCAiM5PFYeA00msNdQw0
|
21364 |
cc_net/data/test_stats.json |
sha256=8MLuKTB_LLMWC5Ezrx3ttzAGWDCa164So9-ZFtQ-xj4
|
1173 |
cc_net-0.0.0.dist-info/LICENSE |
sha256=o3spUuXPrgFTnlk6ZBY4-6pNXuot5nNmI60b3yGOYEE
|
19338 |
cc_net-0.0.0.dist-info/METADATA |
sha256=mCt01okdpgnF4l_fXTv8H7nEix1BbwWLY-mCB-XHJcI
|
1110 |
cc_net-0.0.0.dist-info/WHEEL |
sha256=_NOXIqFgOaYmlm9RJLPQZ13BJuEIrp5jx5ptRD5uh3Y
|
92 |
cc_net-0.0.0.dist-info/top_level.txt |
sha256=TGXdHaLHZU9hFVEQ3P0A6X7TVYl0JxJUBAXRaAhpQqw
|
7 |
cc_net-0.0.0.dist-info/RECORD |
— |
— |