while len(ranks) < vocab_size:
    stats = collections.Counter()
    for piece in words:
        for pair in zip(piece[:-1], piece[1:]):
            stats[pair] += 1
    most_common_pair = max(stats, key=lambda x: stats[x])
    token_bytes = most_common_pair[0] + most_common_pair[1]
    token = len(ranks)
    # Add the new token!
    ranks[token_bytes] = token
    # ... then replace that pair through the corpus, and loop