Fix gemma3 token vocab mismatch

[Saibo-creator]

Gemma 3 tokenizer has an inconsistency between the vocab_size value (262144) and the size of the vocab dictionary (262145)

It has a special token called <image_soft_token> of token id 262144 and this token is part of the vocab dictionary from tokenizer.get_vocab() but is not counted into the vocab size.

[urroxyz]

I think is #126 is more robust because it aligns after analyzing the mismatch rather than always truncating, so that it isn't just a fix for Gemma 3, but for other models with their own niche vocabulary problems.