cerebras.modelzoo.data_preparation.data_preprocessing.data_dedup.generate_duplicate_pairs.get_hashes#

cerebras.modelzoo.data_preparation.data_preprocessing.data_dedup.generate_duplicate_pairs.get_hashes(files, doc_queues, r)[source]#

previous

cerebras.modelzoo.data_preparation.data_preprocessing.data_dedup.generate_duplicate_pairs.generate_pairs

next

cerebras.modelzoo.data_preparation.data_preprocessing.data_dedup.generate_duplicate_pairs.lsh