modelzoo.transformers.data_processing.slimpajama.dedup.generate_duplicate_pairs.get_hashes#

modelzoo.transformers.data_processing.slimpajama.dedup.generate_duplicate_pairs.get_hashes(files, doc_queues, r)[source]#

previous

modelzoo.transformers.data_processing.slimpajama.dedup.generate_duplicate_pairs.generate_pairs

next

modelzoo.transformers.data_processing.slimpajama.dedup.generate_duplicate_pairs.lsh