I am confused about the sub-sampler in corpus2pairs. I think 1 - sqrt(subsample / count) should be replaced with 1 - sqrt(subsample / (count / total_word_count_in_vocab)).

ps. I might misunderstand your implementation, and in actual implementation of original word2vec.c ，the subsample probability equals 1 - (sqrt(subsample / (count / total_word_count_in_vocab)) + subsample / (count / total_word_count_in_vocab) ).