New tokenizer implementation for MPT and GPT-J

Improves output quality by making these tokenizers more closely
match the behavior of the huggingface `tokenizers` based BPE
tokenizers these models were trained with.

Featuring:
 * Fixed unicode handling (via ICU)
 * Fixed BPE token merge handling
 * Complete added vocabulary handling

.codespellrc

@@ -1,4 +1,4 @@
 [codespell]
-skip = .git,*.pdf,*.svg
+skip = .git,*.pdf,*.svg,*_tokenizer_config.h
 #
 # ignore-words-list =