cerebras.modelzoo.data_preparation.nlp.slimpajama.dedup.generate_duplicate_pairs.lsh

cerebras.modelzoo.data_preparation.nlp.slimpajama.dedup.generate_duplicate_pairs.lsh(out_file, doc_queue, idx)

previous

cerebras.modelzoo.data_preparation.nlp.slimpajama.dedup.generate_duplicate_pairs.get_hashes

next

cerebras.modelzoo.data_preparation.nlp.slimpajama.dedup.generate_duplicate_pairs.split_files