added q75 BPE

[KushGrandhi]

Byte Pair Encoding (BPE) for Subword Tokenization

Problem Statement:
Design and implement an algorithm to tokenize a given corpus into subword units based on the frequency of adjacent character pairs using the Byte Pair Encoding (BPE) method. The algorithm should iteratively merge the most frequent character pairs in the corpus to create a compact and meaningful token vocabulary.

The task is to implement BPE by:

Iteratively finding and merging the most frequent pairs of adjacent characters or subwords.
Updating the corpus and token vocabulary after each merge.
Continuing the process until a stopping criterion is reached (e.g., a fixed number of merges or achieving a desired vocabulary size).

[moe18]

would you be able to add some tests to this solution